id	sid	tid	token	lemma	pos
ajst-23570	1	1	academic	academic	ADJ
ajst-23570	1	2	journal	journal	NOUN
ajst-23570	1	3	of	of	ADP
ajst-23570	1	4	science	science	NOUN
ajst-23570	1	5	and	and	CCONJ
ajst-23570	1	6	technology	technology	NOUN
ajst-23570	1	7	issn	issn	NOUN
ajst-23570	1	8	:	:	PUNCT
ajst-23570	1	9	2771	2771	NUM
ajst-23570	1	10	-	-	SYM
ajst-23570	1	11	3032	3032	NUM
ajst-23570	1	12	|	|	NOUN
ajst-23570	1	13	vol	vol	NOUN
ajst-23570	1	14	.	.	PROPN
ajst-23570	2	1	11	11	NUM
ajst-23570	2	2	,	,	PUNCT
ajst-23570	2	3	no	no	INTJ
ajst-23570	2	4	.	.	NOUN
ajst-23570	2	5	3	3	NUM
ajst-23570	2	6	,	,	PUNCT
ajst-23570	2	7	2024	2024	NUM
ajst-23570	2	8	106	106	NUM
ajst-23570	2	9	application	application	NOUN
ajst-23570	2	10	of	of	ADP
ajst-23570	2	11	bayesian	bayesian	NOUN
ajst-23570	2	12	method	method	NOUN
ajst-23570	2	13	in	in	ADP
ajst-23570	2	14	linear	linear	PROPN
ajst-23570	2	15	regression	regression	NOUN
ajst-23570	2	16	yiteng	yiteng	PROPN
ajst-23570	2	17	zhang	zhang	PROPN
ajst-23570	3	1	*	*	PUNCT
ajst-23570	3	2	jurong	jurong	PROPN
ajst-23570	3	3	country	country	PROPN
ajst-23570	3	4	garden	garden	PROPN
ajst-23570	3	5	school	school	PROPN
ajst-23570	3	6	,	,	PUNCT
ajst-23570	3	7	zhenjiang	zhenjiang	PROPN
ajst-23570	3	8	,	,	PUNCT
ajst-23570	3	9	jiangsu	jiangsu	PROPN
ajst-23570	3	10	,	,	PUNCT
ajst-23570	3	11	212499	212499	NUM
ajst-23570	3	12	,	,	PUNCT
ajst-23570	3	13	china	china	PROPN
ajst-23570	3	14	*	*	PUNCT
ajst-23570	3	15	corresponding	correspond	VERB
ajst-23570	3	16	author	author	NOUN
ajst-23570	3	17	email	email	NOUN
ajst-23570	3	18	:	:	PUNCT
ajst-23570	3	19	z2406254047@foxmail.com	z2406254047@foxmail.com	X
ajst-23570	3	20	abstract	abstract	PROPN
ajst-23570	3	21	:	:	PUNCT
ajst-23570	3	22	this	this	DET
ajst-23570	3	23	paper	paper	NOUN
ajst-23570	3	24	investigates	investigate	VERB
ajst-23570	3	25	the	the	DET
ajst-23570	3	26	application	application	NOUN
ajst-23570	3	27	of	of	ADP
ajst-23570	3	28	bayesian	bayesian	NOUN
ajst-23570	3	29	methods	method	NOUN
ajst-23570	3	30	in	in	ADP
ajst-23570	3	31	linear	linear	PROPN
ajst-23570	3	32	regression	regression	NOUN
ajst-23570	3	33	.	.	PUNCT
ajst-23570	4	1	firstly	firstly	ADV
ajst-23570	4	2	,	,	PUNCT
ajst-23570	4	3	the	the	DET
ajst-23570	4	4	basic	basic	ADJ
ajst-23570	4	5	principles	principle	NOUN
ajst-23570	4	6	of	of	ADP
ajst-23570	4	7	linear	linear	ADJ
ajst-23570	4	8	regression	regression	NOUN
ajst-23570	4	9	and	and	CCONJ
ajst-23570	4	10	bayesian	bayesian	NOUN
ajst-23570	4	11	methods	method	NOUN
ajst-23570	4	12	were	be	AUX
ajst-23570	4	13	introduced	introduce	VERB
ajst-23570	4	14	.	.	PUNCT
ajst-23570	5	1	then	then	ADV
ajst-23570	5	2	,	,	PUNCT
ajst-23570	5	3	the	the	DET
ajst-23570	5	4	construction	construction	NOUN
ajst-23570	5	5	and	and	CCONJ
ajst-23570	5	6	inference	inference	NOUN
ajst-23570	5	7	methods	method	NOUN
ajst-23570	5	8	of	of	ADP
ajst-23570	5	9	bayesian	bayesian	NOUN
ajst-23570	5	10	linear	linear	PROPN
ajst-23570	5	11	regression	regression	NOUN
ajst-23570	5	12	models	model	NOUN
ajst-23570	5	13	were	be	AUX
ajst-23570	5	14	discussed	discuss	VERB
ajst-23570	5	15	in	in	ADP
ajst-23570	5	16	detail	detail	NOUN
ajst-23570	5	17	.	.	PUNCT
ajst-23570	6	1	furthermore	furthermore	ADV
ajst-23570	6	2	,	,	PUNCT
ajst-23570	6	3	the	the	DET
ajst-23570	6	4	application	application	NOUN
ajst-23570	6	5	of	of	ADP
ajst-23570	6	6	bayesian	bayesian	NOUN
ajst-23570	6	7	methods	method	NOUN
ajst-23570	6	8	in	in	ADP
ajst-23570	6	9	other	other	ADJ
ajst-23570	6	10	regression	regression	NOUN
ajst-23570	6	11	problems	problem	NOUN
ajst-23570	6	12	was	be	AUX
ajst-23570	6	13	explored	explore	VERB
ajst-23570	6	14	,	,	PUNCT
ajst-23570	6	15	and	and	CCONJ
ajst-23570	6	16	their	their	PRON
ajst-23570	6	17	limitations	limitation	NOUN
ajst-23570	6	18	and	and	CCONJ
ajst-23570	6	19	improvement	improvement	NOUN
ajst-23570	6	20	directions	direction	NOUN
ajst-23570	6	21	in	in	ADP
ajst-23570	6	22	practice	practice	NOUN
ajst-23570	6	23	were	be	AUX
ajst-23570	6	24	analyzed	analyze	VERB
ajst-23570	6	25	.	.	PUNCT
ajst-23570	7	1	finally	finally	ADV
ajst-23570	7	2	,	,	PUNCT
ajst-23570	7	3	the	the	DET
ajst-23570	7	4	main	main	ADJ
ajst-23570	7	5	research	research	NOUN
ajst-23570	7	6	findings	finding	NOUN
ajst-23570	7	7	were	be	AUX
ajst-23570	7	8	summarized	summarize	VERB
ajst-23570	7	9	and	and	CCONJ
ajst-23570	7	10	suggestions	suggestion	NOUN
ajst-23570	7	11	for	for	ADP
ajst-23570	7	12	future	future	ADJ
ajst-23570	7	13	research	research	NOUN
ajst-23570	7	14	directions	direction	NOUN
ajst-23570	7	15	were	be	AUX
ajst-23570	7	16	proposed	propose	VERB
ajst-23570	7	17	.	.	PUNCT
ajst-23570	8	1	keywords	keyword	NOUN
ajst-23570	8	2	:	:	PUNCT
ajst-23570	8	3	bayesian	bayesian	NOUN
ajst-23570	8	4	method	method	NOUN
ajst-23570	8	5	;	;	PUNCT
ajst-23570	8	6	linear	linear	ADJ
ajst-23570	8	7	regression	regression	NOUN
ajst-23570	8	8	;	;	PUNCT
ajst-23570	8	9	bayesian	bayesian	NOUN
ajst-23570	8	10	linear	linear	PROPN
ajst-23570	8	11	regression	regression	NOUN
ajst-23570	8	12	model	model	NOUN
ajst-23570	8	13	.	.	PUNCT
ajst-23570	9	1	1	1	X
ajst-23570	9	2	.	.	X
ajst-23570	9	3	introduction	introduction	NOUN
ajst-23570	9	4	linear	linear	PROPN
ajst-23570	9	5	regression	regression	NOUN
ajst-23570	9	6	is	be	AUX
ajst-23570	9	7	an	an	DET
ajst-23570	9	8	important	important	ADJ
ajst-23570	9	9	forecasting	forecasting	NOUN
ajst-23570	9	10	model	model	NOUN
ajst-23570	9	11	in	in	ADP
ajst-23570	9	12	statistics	statistic	NOUN
ajst-23570	9	13	,	,	PUNCT
ajst-23570	9	14	which	which	PRON
ajst-23570	9	15	is	be	AUX
ajst-23570	9	16	widely	widely	ADV
ajst-23570	9	17	used	use	VERB
ajst-23570	9	18	in	in	ADP
ajst-23570	9	19	economic	economic	ADJ
ajst-23570	9	20	,	,	PUNCT
ajst-23570	9	21	financial	financial	ADJ
ajst-23570	9	22	,	,	PUNCT
ajst-23570	9	23	medical	medical	ADJ
ajst-23570	9	24	and	and	CCONJ
ajst-23570	9	25	other	other	ADJ
ajst-23570	9	26	fields	field	NOUN
ajst-23570	9	27	.	.	PUNCT
ajst-23570	10	1	the	the	DET
ajst-23570	10	2	traditional	traditional	ADJ
ajst-23570	10	3	linear	linear	ADJ
ajst-23570	10	4	regression	regression	NOUN
ajst-23570	10	5	method	method	NOUN
ajst-23570	10	6	is	be	AUX
ajst-23570	10	7	mainly	mainly	ADV
ajst-23570	10	8	based	base	VERB
ajst-23570	10	9	on	on	ADP
ajst-23570	10	10	least	least	ADJ
ajst-23570	10	11	square	square	ADJ
ajst-23570	10	12	method	method	NOUN
ajst-23570	10	13	,	,	PUNCT
ajst-23570	10	14	but	but	CCONJ
ajst-23570	10	15	this	this	DET
ajst-23570	10	16	method	method	NOUN
ajst-23570	10	17	may	may	AUX
ajst-23570	10	18	have	have	VERB
ajst-23570	10	19	bias	bias	NOUN
ajst-23570	10	20	and	and	CCONJ
ajst-23570	10	21	instability	instability	NOUN
ajst-23570	10	22	when	when	SCONJ
ajst-23570	10	23	dealing	deal	VERB
ajst-23570	10	24	with	with	ADP
ajst-23570	10	25	some	some	DET
ajst-23570	10	26	complex	complex	ADJ
ajst-23570	10	27	data	datum	NOUN
ajst-23570	10	28	problems	problem	NOUN
ajst-23570	10	29	.	.	PUNCT
ajst-23570	11	1	in	in	ADP
ajst-23570	11	2	recent	recent	ADJ
ajst-23570	11	3	years	year	NOUN
ajst-23570	11	4	,	,	PUNCT
ajst-23570	11	5	bayes	bayes	PROPN
ajst-23570	11	6	method	method	NOUN
ajst-23570	11	7	as	as	ADP
ajst-23570	11	8	a	a	DET
ajst-23570	11	9	statistical	statistical	ADJ
ajst-23570	11	10	inference	inference	NOUN
ajst-23570	11	11	method	method	NOUN
ajst-23570	11	12	has	have	AUX
ajst-23570	11	13	gradually	gradually	ADV
ajst-23570	11	14	attracted	attract	VERB
ajst-23570	11	15	attention	attention	NOUN
ajst-23570	11	16	.	.	PUNCT
ajst-23570	12	1	bayesian	bayesian	NOUN
ajst-23570	12	2	methods	method	NOUN
ajst-23570	12	3	provide	provide	VERB
ajst-23570	12	4	more	more	ADV
ajst-23570	12	5	accurate	accurate	ADJ
ajst-23570	12	6	parameter	parameter	NOUN
ajst-23570	12	7	estimates	estimate	NOUN
ajst-23570	12	8	and	and	CCONJ
ajst-23570	12	9	model	model	NOUN
ajst-23570	12	10	uncertainties	uncertainty	NOUN
ajst-23570	12	11	,	,	PUNCT
ajst-23570	12	12	and	and	CCONJ
ajst-23570	12	13	therefore	therefore	ADV
ajst-23570	12	14	have	have	VERB
ajst-23570	12	15	unique	unique	ADJ
ajst-23570	12	16	advantages	advantage	NOUN
ajst-23570	12	17	when	when	SCONJ
ajst-23570	12	18	dealing	deal	VERB
ajst-23570	12	19	with	with	ADP
ajst-23570	12	20	linear	linear	ADJ
ajst-23570	12	21	regression	regression	NOUN
ajst-23570	12	22	problems	problem	NOUN
ajst-23570	12	23	.	.	PUNCT
ajst-23570	13	1	in	in	ADP
ajst-23570	13	2	the	the	DET
ajst-23570	13	3	real	real	ADJ
ajst-23570	13	4	world	world	NOUN
ajst-23570	13	5	,	,	PUNCT
ajst-23570	13	6	data	datum	NOUN
ajst-23570	13	7	often	often	ADV
ajst-23570	13	8	has	have	VERB
ajst-23570	13	9	problems	problem	NOUN
ajst-23570	13	10	such	such	ADJ
ajst-23570	13	11	as	as	ADP
ajst-23570	13	12	noise	noise	NOUN
ajst-23570	13	13	,	,	PUNCT
ajst-23570	13	14	outliers	outlier	NOUN
ajst-23570	13	15	and	and	CCONJ
ajst-23570	13	16	missing	miss	VERB
ajst-23570	13	17	values	value	NOUN
ajst-23570	13	18	,	,	PUNCT
ajst-23570	13	19	which	which	PRON
ajst-23570	13	20	can	can	AUX
ajst-23570	13	21	lead	lead	VERB
ajst-23570	13	22	to	to	ADP
ajst-23570	13	23	the	the	DET
ajst-23570	13	24	failure	failure	NOUN
ajst-23570	13	25	of	of	ADP
ajst-23570	13	26	traditional	traditional	ADJ
ajst-23570	13	27	linear	linear	ADJ
ajst-23570	13	28	regression	regression	NOUN
ajst-23570	13	29	methods	method	NOUN
ajst-23570	13	30	.	.	PUNCT
ajst-23570	14	1	bayesian	bayesian	NOUN
ajst-23570	14	2	method	method	NOUN
ajst-23570	14	3	can	can	AUX
ajst-23570	14	4	deal	deal	VERB
ajst-23570	14	5	with	with	ADP
ajst-23570	14	6	these	these	DET
ajst-23570	14	7	problems	problem	NOUN
ajst-23570	14	8	better	well	ADV
ajst-23570	14	9	,	,	PUNCT
ajst-23570	14	10	and	and	CCONJ
ajst-23570	14	11	can	can	AUX
ajst-23570	14	12	provide	provide	VERB
ajst-23570	14	13	more	more	ADV
ajst-23570	14	14	comprehensive	comprehensive	ADJ
ajst-23570	14	15	information	information	NOUN
ajst-23570	14	16	,	,	PUNCT
ajst-23570	14	17	including	include	VERB
ajst-23570	14	18	the	the	DET
ajst-23570	14	19	prior	prior	ADJ
ajst-23570	14	20	distribution	distribution	NOUN
ajst-23570	14	21	of	of	ADP
ajst-23570	14	22	parameters	parameter	NOUN
ajst-23570	14	23	,	,	PUNCT
ajst-23570	14	24	the	the	DET
ajst-23570	14	25	uncertainty	uncertainty	NOUN
ajst-23570	14	26	of	of	ADP
ajst-23570	14	27	the	the	DET
ajst-23570	14	28	model	model	NOUN
ajst-23570	14	29	and	and	CCONJ
ajst-23570	14	30	the	the	DET
ajst-23570	14	31	evaluation	evaluation	NOUN
ajst-23570	14	32	of	of	ADP
ajst-23570	14	33	the	the	DET
ajst-23570	14	34	model	model	NOUN
ajst-23570	14	35	effect	effect	NOUN
ajst-23570	14	36	.	.	PUNCT
ajst-23570	15	1	therefore	therefore	ADV
ajst-23570	15	2	,	,	PUNCT
ajst-23570	15	3	the	the	DET
ajst-23570	15	4	purpose	purpose	NOUN
ajst-23570	15	5	of	of	ADP
ajst-23570	15	6	this	this	DET
ajst-23570	15	7	study	study	NOUN
ajst-23570	15	8	is	be	AUX
ajst-23570	15	9	to	to	PART
ajst-23570	15	10	explore	explore	VERB
ajst-23570	15	11	the	the	DET
ajst-23570	15	12	application	application	NOUN
ajst-23570	15	13	of	of	ADP
ajst-23570	15	14	bayesian	bayesian	NOUN
ajst-23570	15	15	method	method	NOUN
ajst-23570	15	16	in	in	ADP
ajst-23570	15	17	linear	linear	PROPN
ajst-23570	15	18	regression	regression	NOUN
ajst-23570	15	19	,	,	PUNCT
ajst-23570	15	20	in	in	ADP
ajst-23570	15	21	order	order	NOUN
ajst-23570	15	22	to	to	PART
ajst-23570	15	23	provide	provide	VERB
ajst-23570	15	24	new	new	ADJ
ajst-23570	15	25	ideas	idea	NOUN
ajst-23570	15	26	and	and	CCONJ
ajst-23570	15	27	methods	method	NOUN
ajst-23570	15	28	for	for	ADP
ajst-23570	15	29	practical	practical	ADJ
ajst-23570	15	30	application	application	NOUN
ajst-23570	15	31	.	.	PUNCT
ajst-23570	16	1	by	by	ADP
ajst-23570	16	2	combing	comb	VERB
ajst-23570	16	3	and	and	CCONJ
ajst-23570	16	4	analyzing	analyze	VERB
ajst-23570	16	5	the	the	DET
ajst-23570	16	6	relevant	relevant	ADJ
ajst-23570	16	7	literature	literature	NOUN
ajst-23570	16	8	,	,	PUNCT
ajst-23570	16	9	it	it	PRON
ajst-23570	16	10	can	can	AUX
ajst-23570	16	11	be	be	AUX
ajst-23570	16	12	found	find	VERB
ajst-23570	16	13	that	that	SCONJ
ajst-23570	16	14	the	the	DET
ajst-23570	16	15	existing	exist	VERB
ajst-23570	16	16	researches	research	NOUN
ajst-23570	16	17	mainly	mainly	ADV
ajst-23570	16	18	focus	focus	VERB
ajst-23570	16	19	on	on	ADP
ajst-23570	16	20	the	the	DET
ajst-23570	16	21	theoretical	theoretical	ADJ
ajst-23570	16	22	research	research	NOUN
ajst-23570	16	23	,	,	PUNCT
ajst-23570	16	24	algorithm	algorithm	NOUN
ajst-23570	16	25	optimization	optimization	NOUN
ajst-23570	16	26	and	and	CCONJ
ajst-23570	16	27	numerical	numerical	ADJ
ajst-23570	16	28	calculation	calculation	NOUN
ajst-23570	16	29	of	of	ADP
ajst-23570	16	30	bayesian	bayesian	NOUN
ajst-23570	16	31	linear	linear	PROPN
ajst-23570	16	32	regression	regression	NOUN
ajst-23570	16	33	model	model	NOUN
ajst-23570	16	34	.	.	PUNCT
ajst-23570	17	1	however	however	ADV
ajst-23570	17	2	,	,	PUNCT
ajst-23570	17	3	there	there	PRON
ajst-23570	17	4	are	be	VERB
ajst-23570	17	5	still	still	ADV
ajst-23570	17	6	relatively	relatively	ADV
ajst-23570	17	7	few	few	ADJ
ajst-23570	17	8	researches	research	NOUN
ajst-23570	17	9	on	on	ADP
ajst-23570	17	10	the	the	DET
ajst-23570	17	11	application	application	NOUN
ajst-23570	17	12	of	of	ADP
ajst-23570	17	13	bayesian	bayesian	NOUN
ajst-23570	17	14	method	method	NOUN
ajst-23570	17	15	in	in	ADP
ajst-23570	17	16	linear	linear	PROPN
ajst-23570	17	17	regression	regression	NOUN
ajst-23570	17	18	,	,	PUNCT
ajst-23570	17	19	and	and	CCONJ
ajst-23570	17	20	the	the	DET
ajst-23570	17	21	existing	exist	VERB
ajst-23570	17	22	researches	research	NOUN
ajst-23570	17	23	have	have	VERB
ajst-23570	17	24	some	some	DET
ajst-23570	17	25	problems	problem	NOUN
ajst-23570	17	26	such	such	ADJ
ajst-23570	17	27	as	as	ADP
ajst-23570	17	28	sample	sample	NOUN
ajst-23570	17	29	selection	selection	NOUN
ajst-23570	17	30	bias	bias	NOUN
ajst-23570	17	31	.	.	PUNCT
ajst-23570	18	1	therefore	therefore	ADV
ajst-23570	18	2	,	,	PUNCT
ajst-23570	18	3	this	this	DET
ajst-23570	18	4	study	study	NOUN
ajst-23570	18	5	aims	aim	VERB
ajst-23570	18	6	to	to	PART
ajst-23570	18	7	explore	explore	VERB
ajst-23570	18	8	the	the	DET
ajst-23570	18	9	application	application	NOUN
ajst-23570	18	10	of	of	ADP
ajst-23570	18	11	bayesian	bayesian	NOUN
ajst-23570	18	12	method	method	NOUN
ajst-23570	18	13	in	in	ADP
ajst-23570	18	14	linear	linear	PROPN
ajst-23570	18	15	regression	regression	NOUN
ajst-23570	18	16	in	in	ADP
ajst-23570	18	17	order	order	NOUN
ajst-23570	18	18	to	to	PART
ajst-23570	18	19	provide	provide	VERB
ajst-23570	18	20	a	a	DET
ajst-23570	18	21	more	more	ADV
ajst-23570	18	22	comprehensive	comprehensive	ADJ
ajst-23570	18	23	,	,	PUNCT
ajst-23570	18	24	accurate	accurate	ADJ
ajst-23570	18	25	and	and	CCONJ
ajst-23570	18	26	reliable	reliable	ADJ
ajst-23570	18	27	method	method	NOUN
ajst-23570	18	28	for	for	ADP
ajst-23570	18	29	practical	practical	ADJ
ajst-23570	18	30	application	application	NOUN
ajst-23570	18	31	.	.	PUNCT
ajst-23570	19	1	linear	linear	ADJ
ajst-23570	19	2	regression	regression	NOUN
ajst-23570	19	3	is	be	AUX
ajst-23570	19	4	a	a	DET
ajst-23570	19	5	common	common	ADJ
ajst-23570	19	6	forecasting	forecasting	NOUN
ajst-23570	19	7	model	model	NOUN
ajst-23570	19	8	in	in	ADP
ajst-23570	19	9	statistics	statistic	NOUN
ajst-23570	19	10	,	,	PUNCT
ajst-23570	19	11	which	which	PRON
ajst-23570	19	12	is	be	AUX
ajst-23570	19	13	widely	widely	ADV
ajst-23570	19	14	used	use	VERB
ajst-23570	19	15	in	in	ADP
ajst-23570	19	16	various	various	ADJ
ajst-23570	19	17	practical	practical	ADJ
ajst-23570	19	18	problems	problem	NOUN
ajst-23570	19	19	.	.	PUNCT
ajst-23570	20	1	however	however	ADV
ajst-23570	20	2	,	,	PUNCT
ajst-23570	20	3	the	the	DET
ajst-23570	20	4	traditional	traditional	ADJ
ajst-23570	20	5	linear	linear	ADJ
ajst-23570	20	6	regression	regression	NOUN
ajst-23570	20	7	method	method	NOUN
ajst-23570	20	8	may	may	AUX
ajst-23570	20	9	have	have	VERB
ajst-23570	20	10	some	some	DET
ajst-23570	20	11	limitations	limitation	NOUN
ajst-23570	20	12	when	when	SCONJ
ajst-23570	20	13	dealing	deal	VERB
ajst-23570	20	14	with	with	ADP
ajst-23570	20	15	some	some	DET
ajst-23570	20	16	complex	complex	ADJ
ajst-23570	20	17	data	datum	NOUN
ajst-23570	20	18	.	.	PUNCT
ajst-23570	21	1	as	as	ADP
ajst-23570	21	2	a	a	DET
ajst-23570	21	3	statistical	statistical	ADJ
ajst-23570	21	4	inference	inference	NOUN
ajst-23570	21	5	method	method	NOUN
ajst-23570	21	6	,	,	PUNCT
ajst-23570	21	7	bayesian	bayesian	NOUN
ajst-23570	21	8	method	method	NOUN
ajst-23570	21	9	can	can	AUX
ajst-23570	21	10	provide	provide	VERB
ajst-23570	21	11	a	a	DET
ajst-23570	21	12	more	more	ADV
ajst-23570	21	13	robust	robust	ADJ
ajst-23570	21	14	and	and	CCONJ
ajst-23570	21	15	flexible	flexible	ADJ
ajst-23570	21	16	model	model	NOUN
ajst-23570	21	17	,	,	PUNCT
ajst-23570	21	18	so	so	SCONJ
ajst-23570	21	19	it	it	PRON
ajst-23570	21	20	has	have	VERB
ajst-23570	21	21	great	great	ADJ
ajst-23570	21	22	research	research	NOUN
ajst-23570	21	23	significance	significance	NOUN
ajst-23570	21	24	in	in	ADP
ajst-23570	21	25	dealing	deal	VERB
ajst-23570	21	26	with	with	ADP
ajst-23570	21	27	linear	linear	ADJ
ajst-23570	21	28	regression	regression	NOUN
ajst-23570	21	29	problems	problem	NOUN
ajst-23570	21	30	.	.	PUNCT
ajst-23570	22	1	bayesian	bayesian	NOUN
ajst-23570	22	2	method	method	NOUN
ajst-23570	22	3	can	can	AUX
ajst-23570	22	4	better	well	ADV
ajst-23570	22	5	deal	deal	VERB
ajst-23570	22	6	with	with	ADP
ajst-23570	22	7	uncertainty	uncertainty	NOUN
ajst-23570	22	8	in	in	ADP
ajst-23570	22	9	data	data	PROPN
ajst-23570	22	10	.	.	PUNCT
ajst-23570	23	1	in	in	ADP
ajst-23570	23	2	traditional	traditional	ADJ
ajst-23570	23	3	linear	linear	PROPN
ajst-23570	23	4	regression	regression	NOUN
ajst-23570	23	5	,	,	PUNCT
ajst-23570	23	6	models	model	NOUN
ajst-23570	23	7	are	be	AUX
ajst-23570	23	8	usually	usually	ADV
ajst-23570	23	9	built	build	VERB
ajst-23570	23	10	based	base	VERB
ajst-23570	23	11	on	on	ADP
ajst-23570	23	12	limited	limited	ADJ
ajst-23570	23	13	observational	observational	ADJ
ajst-23570	23	14	data	datum	NOUN
ajst-23570	23	15	,	,	PUNCT
ajst-23570	23	16	while	while	SCONJ
ajst-23570	23	17	bayesian	bayesian	NOUN
ajst-23570	23	18	methods	method	NOUN
ajst-23570	23	19	allow	allow	VERB
ajst-23570	23	20	for	for	ADP
ajst-23570	23	21	both	both	PRON
ajst-23570	23	22	data	datum	NOUN
ajst-23570	23	23	uncertainty	uncertainty	NOUN
ajst-23570	23	24	and	and	CCONJ
ajst-23570	23	25	prior	prior	ADJ
ajst-23570	23	26	information	information	NOUN
ajst-23570	23	27	to	to	PART
ajst-23570	23	28	be	be	AUX
ajst-23570	23	29	used	use	VERB
ajst-23570	23	30	to	to	PART
ajst-23570	23	31	build	build	VERB
ajst-23570	23	32	models	model	NOUN
ajst-23570	23	33	.	.	PUNCT
ajst-23570	24	1	this	this	PRON
ajst-23570	24	2	gives	give	VERB
ajst-23570	24	3	bayesian	bayesian	NOUN
ajst-23570	24	4	methods	method	NOUN
ajst-23570	24	5	greater	great	ADJ
ajst-23570	24	6	flexibility	flexibility	NOUN
ajst-23570	24	7	and	and	CCONJ
ajst-23570	24	8	accuracy	accuracy	NOUN
ajst-23570	24	9	when	when	SCONJ
ajst-23570	24	10	dealing	deal	VERB
ajst-23570	24	11	with	with	ADP
ajst-23570	24	12	complex	complex	ADJ
ajst-23570	24	13	data	datum	NOUN
ajst-23570	24	14	.	.	PUNCT
ajst-23570	25	1	second	second	ADJ
ajst-23570	25	2	,	,	PUNCT
ajst-23570	25	3	bayesian	bayesian	NOUN
ajst-23570	25	4	methods	method	NOUN
ajst-23570	25	5	can	can	AUX
ajst-23570	25	6	provide	provide	VERB
ajst-23570	25	7	more	more	ADJ
ajst-23570	25	8	robust	robust	ADJ
ajst-23570	25	9	models	model	NOUN
ajst-23570	25	10	.	.	PUNCT
ajst-23570	26	1	traditional	traditional	ADJ
ajst-23570	26	2	linear	linear	ADJ
ajst-23570	26	3	regression	regression	NOUN
ajst-23570	26	4	methods	method	NOUN
ajst-23570	26	5	usually	usually	ADV
ajst-23570	26	6	build	build	VERB
ajst-23570	26	7	models	model	NOUN
ajst-23570	26	8	based	base	VERB
ajst-23570	26	9	on	on	ADP
ajst-23570	26	10	linear	linear	PROPN
ajst-23570	26	11	assumptions	assumption	NOUN
ajst-23570	26	12	,	,	PUNCT
ajst-23570	26	13	but	but	CCONJ
ajst-23570	26	14	in	in	ADP
ajst-23570	26	15	practical	practical	ADJ
ajst-23570	26	16	applications	application	NOUN
ajst-23570	26	17	,	,	PUNCT
ajst-23570	26	18	the	the	DET
ajst-23570	26	19	distribution	distribution	NOUN
ajst-23570	26	20	of	of	ADP
ajst-23570	26	21	data	datum	NOUN
ajst-23570	26	22	is	be	AUX
ajst-23570	26	23	often	often	ADV
ajst-23570	26	24	non	non	ADJ
ajst-23570	26	25	-	-	ADJ
ajst-23570	26	26	linear	linear	ADJ
ajst-23570	26	27	.	.	PUNCT
ajst-23570	27	1	bayesian	bayesian	NOUN
ajst-23570	27	2	methods	method	NOUN
ajst-23570	27	3	are	be	AUX
ajst-23570	27	4	better	well	ADJ
ajst-23570	27	5	able	able	ADJ
ajst-23570	27	6	to	to	PART
ajst-23570	27	7	capture	capture	VERB
ajst-23570	27	8	the	the	DET
ajst-23570	27	9	nonlinear	nonlinear	ADJ
ajst-23570	27	10	features	feature	NOUN
ajst-23570	27	11	of	of	ADP
ajst-23570	27	12	the	the	DET
ajst-23570	27	13	data	datum	NOUN
ajst-23570	27	14	,	,	PUNCT
ajst-23570	27	15	thus	thus	ADV
ajst-23570	27	16	providing	provide	VERB
ajst-23570	27	17	a	a	DET
ajst-23570	27	18	more	more	ADV
ajst-23570	27	19	robust	robust	ADJ
ajst-23570	27	20	and	and	CCONJ
ajst-23570	27	21	accurate	accurate	ADJ
ajst-23570	27	22	model	model	NOUN
ajst-23570	27	23	.	.	PUNCT
ajst-23570	28	1	finally	finally	ADV
ajst-23570	28	2	,	,	PUNCT
ajst-23570	28	3	bayesian	bayesian	NOUN
ajst-23570	28	4	methods	method	NOUN
ajst-23570	28	5	are	be	AUX
ajst-23570	28	6	more	more	ADV
ajst-23570	28	7	interpretive	interpretive	ADJ
ajst-23570	28	8	when	when	SCONJ
ajst-23570	28	9	dealing	deal	VERB
ajst-23570	28	10	with	with	ADP
ajst-23570	28	11	complex	complex	ADJ
ajst-23570	28	12	data	datum	NOUN
ajst-23570	28	13	.	.	PUNCT
ajst-23570	29	1	traditional	traditional	ADJ
ajst-23570	29	2	linear	linear	PROPN
ajst-23570	29	3	regression	regression	NOUN
ajst-23570	29	4	methods	method	NOUN
ajst-23570	29	5	often	often	ADV
ajst-23570	29	6	build	build	VERB
ajst-23570	29	7	models	model	NOUN
ajst-23570	29	8	based	base	VERB
ajst-23570	29	9	on	on	ADP
ajst-23570	29	10	statistical	statistical	ADJ
ajst-23570	29	11	assumptions	assumption	NOUN
ajst-23570	29	12	that	that	PRON
ajst-23570	29	13	are	be	AUX
ajst-23570	29	14	often	often	ADV
ajst-23570	29	15	difficult	difficult	ADJ
ajst-23570	29	16	to	to	PART
ajst-23570	29	17	explain	explain	VERB
ajst-23570	29	18	.	.	PUNCT
ajst-23570	30	1	bayesian	bayesian	NOUN
ajst-23570	30	2	methods	method	NOUN
ajst-23570	30	3	,	,	PUNCT
ajst-23570	30	4	on	on	ADP
ajst-23570	30	5	the	the	DET
ajst-23570	30	6	other	other	ADJ
ajst-23570	30	7	hand	hand	NOUN
ajst-23570	30	8	,	,	PUNCT
ajst-23570	30	9	pay	pay	VERB
ajst-23570	30	10	more	more	ADJ
ajst-23570	30	11	attention	attention	NOUN
ajst-23570	30	12	to	to	ADP
ajst-23570	30	13	the	the	DET
ajst-23570	30	14	interpretability	interpretability	NOUN
ajst-23570	30	15	of	of	ADP
ajst-23570	30	16	the	the	DET
ajst-23570	30	17	model	model	NOUN
ajst-23570	30	18	,	,	PUNCT
ajst-23570	30	19	allowing	allow	VERB
ajst-23570	30	20	the	the	DET
ajst-23570	30	21	selection	selection	NOUN
ajst-23570	30	22	of	of	ADP
ajst-23570	30	23	appropriate	appropriate	ADJ
ajst-23570	30	24	model	model	NOUN
ajst-23570	30	25	parameters	parameter	NOUN
ajst-23570	30	26	according	accord	VERB
ajst-23570	30	27	to	to	ADP
ajst-23570	30	28	the	the	DET
ajst-23570	30	29	characteristics	characteristic	NOUN
ajst-23570	30	30	of	of	ADP
ajst-23570	30	31	the	the	DET
ajst-23570	30	32	data	datum	NOUN
ajst-23570	30	33	,	,	PUNCT
ajst-23570	30	34	so	so	SCONJ
ajst-23570	30	35	as	as	SCONJ
ajst-23570	30	36	to	to	PART
ajst-23570	30	37	better	well	ADV
ajst-23570	30	38	interpret	interpret	VERB
ajst-23570	30	39	the	the	DET
ajst-23570	30	40	model	model	NOUN
ajst-23570	30	41	's	's	PART
ajst-23570	30	42	predictions	prediction	NOUN
ajst-23570	30	43	.	.	PUNCT
ajst-23570	31	1	the	the	DET
ajst-23570	31	2	application	application	NOUN
ajst-23570	31	3	of	of	ADP
ajst-23570	31	4	bayesian	bayesian	NOUN
ajst-23570	31	5	method	method	NOUN
ajst-23570	31	6	in	in	ADP
ajst-23570	31	7	linear	linear	PROPN
ajst-23570	31	8	regression	regression	NOUN
ajst-23570	31	9	has	have	VERB
ajst-23570	31	10	great	great	ADJ
ajst-23570	31	11	research	research	NOUN
ajst-23570	31	12	significance	significance	NOUN
ajst-23570	31	13	.	.	PUNCT
ajst-23570	32	1	it	it	PRON
ajst-23570	32	2	can	can	AUX
ajst-23570	32	3	better	well	ADV
ajst-23570	32	4	handle	handle	VERB
ajst-23570	32	5	uncertainty	uncertainty	NOUN
ajst-23570	32	6	in	in	ADP
ajst-23570	32	7	data	datum	NOUN
ajst-23570	32	8	,	,	PUNCT
ajst-23570	32	9	provide	provide	VERB
ajst-23570	32	10	more	more	ADV
ajst-23570	32	11	robust	robust	ADJ
ajst-23570	32	12	and	and	CCONJ
ajst-23570	32	13	accurate	accurate	ADJ
ajst-23570	32	14	models	model	NOUN
ajst-23570	32	15	,	,	PUNCT
ajst-23570	32	16	and	and	CCONJ
ajst-23570	32	17	have	have	VERB
ajst-23570	32	18	higher	high	ADJ
ajst-23570	32	19	interpretability	interpretability	NOUN
ajst-23570	32	20	when	when	SCONJ
ajst-23570	32	21	dealing	deal	VERB
ajst-23570	32	22	with	with	ADP
ajst-23570	32	23	complex	complex	ADJ
ajst-23570	32	24	data	datum	NOUN
ajst-23570	32	25	.	.	PUNCT
ajst-23570	33	1	these	these	DET
ajst-23570	33	2	advantages	advantage	NOUN
ajst-23570	33	3	make	make	VERB
ajst-23570	33	4	the	the	DET
ajst-23570	33	5	bayesian	bayesian	NOUN
ajst-23570	33	6	method	method	NOUN
ajst-23570	33	7	has	have	VERB
ajst-23570	33	8	great	great	ADJ
ajst-23570	33	9	application	application	NOUN
ajst-23570	33	10	value	value	NOUN
ajst-23570	33	11	in	in	ADP
ajst-23570	33	12	dealing	deal	VERB
ajst-23570	33	13	with	with	ADP
ajst-23570	33	14	practical	practical	ADJ
ajst-23570	33	15	problems	problem	NOUN
ajst-23570	33	16	.	.	PUNCT
ajst-23570	34	1	2	2	X
ajst-23570	34	2	.	.	X
ajst-23570	34	3	overview	overview	NOUN
ajst-23570	34	4	of	of	ADP
ajst-23570	34	5	linear	linear	ADJ
ajst-23570	34	6	regression	regression	NOUN
ajst-23570	34	7	and	and	CCONJ
ajst-23570	34	8	bayesian	bayesian	NOUN
ajst-23570	34	9	methods	method	NOUN
ajst-23570	34	10	2.1	2.1	NUM
ajst-23570	34	11	.	.	PUNCT
ajst-23570	35	1	basic	basic	ADJ
ajst-23570	35	2	principles	principle	NOUN
ajst-23570	35	3	of	of	ADP
ajst-23570	35	4	linear	linear	ADJ
ajst-23570	35	5	regression	regression	NOUN
ajst-23570	35	6	linear	linear	PROPN
ajst-23570	35	7	regression	regression	NOUN
ajst-23570	35	8	is	be	AUX
ajst-23570	35	9	a	a	DET
ajst-23570	35	10	basic	basic	ADJ
ajst-23570	35	11	forecasting	forecasting	NOUN
ajst-23570	35	12	model	model	NOUN
ajst-23570	35	13	that	that	PRON
ajst-23570	35	14	predicts	predict	VERB
ajst-23570	35	15	future	future	ADJ
ajst-23570	35	16	data	datum	NOUN
ajst-23570	35	17	by	by	ADP
ajst-23570	35	18	predicting	predict	VERB
ajst-23570	35	19	the	the	DET
ajst-23570	35	20	linear	linear	ADJ
ajst-23570	35	21	relationship	relationship	NOUN
ajst-23570	35	22	between	between	ADP
ajst-23570	35	23	the	the	DET
ajst-23570	35	24	dependent	dependent	ADJ
ajst-23570	35	25	variable	variable	NOUN
ajst-23570	35	26	(	(	PUNCT
ajst-23570	35	27	y	y	NOUN
ajst-23570	35	28	)	)	PUNCT
ajst-23570	35	29	and	and	CCONJ
ajst-23570	35	30	the	the	DET
ajst-23570	35	31	independent	independent	ADJ
ajst-23570	35	32	variable	variable	NOUN
ajst-23570	35	33	(	(	PUNCT
ajst-23570	35	34	x	x	NOUN
ajst-23570	35	35	)	)	PUNCT
ajst-23570	35	36	.	.	PUNCT
ajst-23570	36	1	the	the	DET
ajst-23570	36	2	basic	basic	ADJ
ajst-23570	36	3	principle	principle	NOUN
ajst-23570	36	4	of	of	ADP
ajst-23570	36	5	linear	linear	PROPN
ajst-23570	36	6	regression	regression	NOUN
ajst-23570	36	7	is	be	AUX
ajst-23570	36	8	to	to	PART
ajst-23570	36	9	find	find	VERB
ajst-23570	36	10	the	the	DET
ajst-23570	36	11	best	good	ADJ
ajst-23570	36	12	fit	fit	ADJ
ajst-23570	36	13	line	line	NOUN
ajst-23570	36	14	by	by	ADP
ajst-23570	36	15	minimizing	minimize	VERB
ajst-23570	36	16	the	the	DET
ajst-23570	36	17	residuals	residual	NOUN
ajst-23570	36	18	sum	sum	NOUN
ajst-23570	36	19	of	of	ADP
ajst-23570	36	20	squares	square	NOUN
ajst-23570	36	21	(	(	PUNCT
ajst-23570	36	22	rss	rss	NOUN
ajst-23570	36	23	)	)	PUNCT
ajst-23570	36	24	.	.	PUNCT
ajst-23570	37	1	in	in	ADP
ajst-23570	37	2	linear	linear	PROPN
ajst-23570	37	3	regression	regression	NOUN
ajst-23570	37	4	,	,	PUNCT
ajst-23570	37	5	ordinary	ordinary	ADJ
ajst-23570	37	6	least	least	ADJ
ajst-23570	37	7	squares	square	NOUN
ajst-23570	37	8	(	(	PUNCT
ajst-23570	37	9	ols	ol	NOUN
ajst-23570	37	10	)	)	PUNCT
ajst-23570	37	11	are	be	AUX
ajst-23570	37	12	usually	usually	ADV
ajst-23570	37	13	used	use	VERB
ajst-23570	37	14	to	to	PART
ajst-23570	37	15	estimate	estimate	VERB
ajst-23570	37	16	the	the	DET
ajst-23570	37	17	parameters	parameter	NOUN
ajst-23570	37	18	.	.	PUNCT
ajst-23570	38	1	multiple	multiple	ADJ
ajst-23570	38	2	linear	linear	ADJ
ajst-23570	38	3	regression	regression	NOUN
ajst-23570	38	4	analysis	analysis	NOUN
ajst-23570	38	5	is	be	AUX
ajst-23570	38	6	one	one	NUM
ajst-23570	38	7	of	of	ADP
ajst-23570	38	8	the	the	DET
ajst-23570	38	9	most	most	ADV
ajst-23570	38	10	widely	widely	ADV
ajst-23570	38	11	used	use	VERB
ajst-23570	38	12	statistical	statistical	ADJ
ajst-23570	38	13	methods	method	NOUN
ajst-23570	38	14	.	.	PUNCT
ajst-23570	39	1	if	if	SCONJ
ajst-23570	39	2	it	it	PRON
ajst-23570	39	3	is	be	AUX
ajst-23570	39	4	described	describe	VERB
ajst-23570	39	5	by	by	ADP
ajst-23570	39	6	matrix	matrix	NOUN
ajst-23570	39	7	form	form	NOUN
ajst-23570	39	8	,	,	PUNCT
ajst-23570	39	9	its	its	PRON
ajst-23570	39	10	mathematical	mathematical	ADJ
ajst-23570	39	11	postmortem	postmortem	NOUN
ajst-23570	39	12	model	model	NOUN
ajst-23570	39	13	is	be	AUX
ajst-23570	39	14	as	as	SCONJ
ajst-23570	39	15	follows	follow	VERB
ajst-23570	39	16	[	[	X
ajst-23570	39	17	1	1	NUM
ajst-23570	39	18	]	]	X
ajst-23570	39	19	:	:	PUNCT
ajst-23570	39	20	1	1	NUM
ajst-23570	39	21	∪	∪	VERB
ajst-23570	39	22	1	1	NUM
ajst-23570	39	23	(	(	PUNCT
ajst-23570	39	24	1	1	NUM
ajst-23570	39	25	)	)	PUNCT
ajst-23570	39	26	each	each	DET
ajst-23570	39	27	component	component	NOUN
ajst-23570	39	28	in	in	ADP
ajst-23570	39	29	the	the	DET
ajst-23570	39	30	formula	formula	NOUN
ajst-23570	39	31	,	,	PUNCT
ajst-23570	39	32	i=	i=	PROPN
ajst-23570	39	33	1	1	NUM
ajst-23570	39	34	,	,	PUNCT
ajst-23570	39	35	2	2	NUM
ajst-23570	39	36	,	,	PUNCT
ajst-23570	39	37	...	...	PUNCT
ajst-23570	39	38	,	,	PUNCT
ajst-23570	39	39	k	k	PROPN
ajst-23570	39	40	independent	independent	ADJ
ajst-23570	39	41	identically	identically	ADV
ajst-23570	39	42	distributed	distribute	VERB
ajst-23570	39	43	,	,	PUNCT
ajst-23570	39	44	and	and	CCONJ
ajst-23570	39	45	follow	follow	VERB
ajst-23570	39	46	the	the	DET
ajst-23570	39	47	normal	normal	ADJ
ajst-23570	39	48	distribution	distribution	NOUN
ajst-23570	39	49	that	that	PRON
ajst-23570	39	50	mean	mean	VERB
ajst-23570	39	51	is	be	AUX
ajst-23570	39	52	0	0	NUM
ajst-23570	39	53	,	,	PUNCT
ajst-23570	39	54	variance	variance	NOUN
ajst-23570	39	55	is	be	AUX
ajst-23570	39	56	,	,	PUNCT
ajst-23570	39	57	be	be	AUX
ajst-23570	39	58	∪	∪	ADJ
ajst-23570	39	59	~n	~n	NUM
ajst-23570	39	60	0	0	NUM
ajst-23570	39	61	,	,	PUNCT
ajst-23570	39	62	it	it	PRON
ajst-23570	39	63	is	be	AUX
ajst-23570	39	64	obvious	obvious	ADJ
ajst-23570	39	65	that	that	SCONJ
ajst-23570	39	66	the	the	DET
ajst-23570	39	67	sample	sample	NOUN
ajst-23570	39	68	likelihood	likelihood	NOUN
ajst-23570	39	69	function	function	NOUN
ajst-23570	39	70	is	be	AUX
ajst-23570	39	71	:	:	PUNCT
ajst-23570	39	72	107	107	NUM
ajst-23570	39	73	l	l	NOUN
ajst-23570	39	74	β	β	X
ajst-23570	39	75	,	,	PUNCT
ajst-23570	39	76	σ|y	σ|y	PROPN
ajst-23570	39	77	,	,	PUNCT
ajst-23570	39	78	x	x	SYM
ajst-23570	39	79	=	=	SYM
ajst-23570	39	80	2	2	NUM
ajst-23570	39	81	⁄	⁄	NOUN
ajst-23570	39	82	exp	exp	NOUN
ajst-23570	39	83	´	´	NOUN
ajst-23570	39	84	´	´	NOUN
ajst-23570	39	85	´	´	NOUN
ajst-23570	39	86	(	(	PUNCT
ajst-23570	39	87	2	2	NUM
ajst-23570	39	88	)	)	PUNCT
ajst-23570	39	89	in	in	ADP
ajst-23570	39	90	the	the	DET
ajst-23570	39	91	equation	equation	NOUN
ajst-23570	39	92	,	,	PUNCT
ajst-23570	39	93	v	v	NOUN
ajst-23570	39	94	n	n	CCONJ
ajst-23570	39	95	k	k	NOUN
ajst-23570	39	96	,	,	PUNCT
ajst-23570	39	97	while	while	SCONJ
ajst-23570	39	98	and	and	CCONJ
ajst-23570	39	99	β	β	X
ajst-23570	39	100	are	be	AUX
ajst-23570	39	101	respectively	respectively	ADV
ajst-23570	39	102	´	´	NOUN
ajst-23570	39	103	⁄	⁄	PROPN
ajst-23570	39	104	and	and	CCONJ
ajst-23570	39	105	β	β	X
ajst-23570	39	106	x´x	x´x	PROPN
ajst-23570	39	107	x´y	x´y	PROPN
ajst-23570	39	108	.	.	PUNCT
ajst-23570	40	1	2.2	2.2	NUM
ajst-23570	40	2	.	.	PUNCT
ajst-23570	41	1	bayesian	bayesian	NOUN
ajst-23570	41	2	method	method	NOUN
ajst-23570	41	3	basics	basic	NOUN
ajst-23570	41	4	bayesian	bayesian	NOUN
ajst-23570	41	5	method	method	NOUN
ajst-23570	41	6	is	be	AUX
ajst-23570	41	7	a	a	DET
ajst-23570	41	8	statistical	statistical	ADJ
ajst-23570	41	9	method	method	NOUN
ajst-23570	41	10	based	base	VERB
ajst-23570	41	11	on	on	ADP
ajst-23570	41	12	probability	probability	NOUN
ajst-23570	41	13	,	,	PUNCT
ajst-23570	41	14	which	which	PRON
ajst-23570	41	15	describes	describe	VERB
ajst-23570	41	16	the	the	DET
ajst-23570	41	17	relationship	relationship	NOUN
ajst-23570	41	18	between	between	ADP
ajst-23570	41	19	data	datum	NOUN
ajst-23570	41	20	and	and	CCONJ
ajst-23570	41	21	model	model	NOUN
ajst-23570	41	22	parameters	parameter	NOUN
ajst-23570	41	23	through	through	ADP
ajst-23570	41	24	probability	probability	NOUN
ajst-23570	41	25	distributions	distribution	NOUN
ajst-23570	41	26	.	.	PUNCT
ajst-23570	42	1	an	an	DET
ajst-23570	42	2	important	important	ADJ
ajst-23570	42	3	feature	feature	NOUN
ajst-23570	42	4	of	of	ADP
ajst-23570	42	5	the	the	DET
ajst-23570	42	6	bayesian	bayesian	NOUN
ajst-23570	42	7	approach	approach	NOUN
ajst-23570	42	8	is	be	AUX
ajst-23570	42	9	to	to	PART
ajst-23570	42	10	treat	treat	VERB
ajst-23570	42	11	the	the	DET
ajst-23570	42	12	parameters	parameter	NOUN
ajst-23570	42	13	as	as	ADP
ajst-23570	42	14	random	random	ADJ
ajst-23570	42	15	variables	variable	NOUN
ajst-23570	42	16	and	and	CCONJ
ajst-23570	42	17	infer	infer	VERB
ajst-23570	42	18	their	their	PRON
ajst-23570	42	19	posterior	posterior	ADJ
ajst-23570	42	20	distributions	distribution	NOUN
ajst-23570	42	21	based	base	VERB
ajst-23570	42	22	on	on	ADP
ajst-23570	42	23	the	the	DET
ajst-23570	42	24	data	datum	NOUN
ajst-23570	42	25	.	.	PUNCT
ajst-23570	43	1	this	this	DET
ajst-23570	43	2	posterior	posterior	ADJ
ajst-23570	43	3	distribution	distribution	NOUN
ajst-23570	43	4	describes	describe	VERB
ajst-23570	43	5	parameter	parameter	NOUN
ajst-23570	43	6	uncertainty	uncertainty	NOUN
ajst-23570	43	7	and	and	CCONJ
ajst-23570	43	8	provides	provide	VERB
ajst-23570	43	9	more	more	ADV
ajst-23570	43	10	comprehensive	comprehensive	ADJ
ajst-23570	43	11	information	information	NOUN
ajst-23570	43	12	.	.	PUNCT
ajst-23570	44	1	the	the	DET
ajst-23570	44	2	main	main	ADJ
ajst-23570	44	3	advantage	advantage	NOUN
ajst-23570	44	4	of	of	ADP
ajst-23570	44	5	the	the	DET
ajst-23570	44	6	bayesian	bayesian	NOUN
ajst-23570	44	7	approach	approach	NOUN
ajst-23570	44	8	is	be	AUX
ajst-23570	44	9	its	its	PRON
ajst-23570	44	10	ability	ability	NOUN
ajst-23570	44	11	to	to	PART
ajst-23570	44	12	deal	deal	VERB
ajst-23570	44	13	with	with	ADP
ajst-23570	44	14	uncertainty	uncertainty	NOUN
ajst-23570	44	15	and	and	CCONJ
ajst-23570	44	16	noisy	noisy	ADJ
ajst-23570	44	17	data	datum	NOUN
ajst-23570	44	18	and	and	CCONJ
ajst-23570	44	19	provide	provide	VERB
ajst-23570	44	20	more	more	ADV
ajst-23570	44	21	precise	precise	ADJ
ajst-23570	44	22	predictions	prediction	NOUN
ajst-23570	44	23	and	and	CCONJ
ajst-23570	44	24	interpretations	interpretation	NOUN
ajst-23570	44	25	.	.	PUNCT
ajst-23570	45	1	in	in	ADP
ajst-23570	45	2	addition	addition	NOUN
ajst-23570	45	3	,	,	PUNCT
ajst-23570	45	4	bayesian	bayesian	NOUN
ajst-23570	45	5	methods	method	NOUN
ajst-23570	45	6	can	can	AUX
ajst-23570	45	7	also	also	ADV
ajst-23570	45	8	be	be	AUX
ajst-23570	45	9	used	use	VERB
ajst-23570	45	10	for	for	ADP
ajst-23570	45	11	model	model	NOUN
ajst-23570	45	12	selection	selection	NOUN
ajst-23570	45	13	and	and	CCONJ
ajst-23570	45	14	diagnosis	diagnosis	NOUN
ajst-23570	45	15	to	to	PART
ajst-23570	45	16	determine	determine	VERB
ajst-23570	45	17	the	the	DET
ajst-23570	45	18	complexity	complexity	NOUN
ajst-23570	45	19	and	and	CCONJ
ajst-23570	45	20	effect	effect	NOUN
ajst-23570	45	21	of	of	ADP
ajst-23570	45	22	the	the	DET
ajst-23570	45	23	model	model	NOUN
ajst-23570	45	24	.	.	PUNCT
ajst-23570	46	1	2.3	2.3	NUM
ajst-23570	46	2	.	.	PUNCT
ajst-23570	47	1	bayesian	bayesian	NOUN
ajst-23570	47	2	linear	linear	PROPN
ajst-23570	47	3	regression	regression	NOUN
ajst-23570	47	4	model	model	NOUN
ajst-23570	47	5	the	the	DET
ajst-23570	47	6	bayesian	bayesian	NOUN
ajst-23570	47	7	linear	linear	PROPN
ajst-23570	47	8	regression	regression	NOUN
ajst-23570	47	9	model	model	NOUN
ajst-23570	47	10	is	be	AUX
ajst-23570	47	11	a	a	DET
ajst-23570	47	12	model	model	NOUN
ajst-23570	47	13	that	that	PRON
ajst-23570	47	14	combines	combine	VERB
ajst-23570	47	15	the	the	DET
ajst-23570	47	16	bayesian	bayesian	NOUN
ajst-23570	47	17	approach	approach	NOUN
ajst-23570	47	18	and	and	CCONJ
ajst-23570	47	19	linear	linear	PROPN
ajst-23570	47	20	regression[2	regression[2	PROPN
ajst-23570	47	21	]	]	PUNCT
ajst-23570	47	22	.	.	PUNCT
ajst-23570	48	1	in	in	ADP
ajst-23570	48	2	such	such	ADJ
ajst-23570	48	3	models	model	NOUN
ajst-23570	48	4	,	,	PUNCT
ajst-23570	48	5	the	the	DET
ajst-23570	48	6	independent	independent	ADJ
ajst-23570	48	7	and	and	CCONJ
ajst-23570	48	8	dependent	dependent	ADJ
ajst-23570	48	9	variables	variable	NOUN
ajst-23570	48	10	are	be	AUX
ajst-23570	48	11	treated	treat	VERB
ajst-23570	48	12	as	as	ADP
ajst-23570	48	13	random	random	ADJ
ajst-23570	48	14	variables	variable	NOUN
ajst-23570	48	15	and	and	CCONJ
ajst-23570	48	16	bayes	bayes	NOUN
ajst-23570	48	17	theorem	theorem	VERB
ajst-23570	48	18	is	be	AUX
ajst-23570	48	19	used	use	VERB
ajst-23570	48	20	to	to	PART
ajst-23570	48	21	infer	infer	VERB
ajst-23570	48	22	their	their	PRON
ajst-23570	48	23	joint	joint	ADJ
ajst-23570	48	24	distribution	distribution	NOUN
ajst-23570	48	25	.	.	PUNCT
ajst-23570	49	1	in	in	ADP
ajst-23570	49	2	this	this	DET
ajst-23570	49	3	way	way	NOUN
ajst-23570	49	4	,	,	PUNCT
ajst-23570	49	5	bayesian	bayesian	NOUN
ajst-23570	49	6	methods	method	NOUN
ajst-23570	49	7	can	can	AUX
ajst-23570	49	8	be	be	AUX
ajst-23570	49	9	utilized	utilize	VERB
ajst-23570	49	10	to	to	PART
ajst-23570	49	11	deal	deal	VERB
ajst-23570	49	12	with	with	ADP
ajst-23570	49	13	the	the	DET
ajst-23570	49	14	uncertainty	uncertainty	NOUN
ajst-23570	49	15	and	and	CCONJ
ajst-23570	49	16	noise	noise	NOUN
ajst-23570	49	17	in	in	ADP
ajst-23570	49	18	the	the	DET
ajst-23570	49	19	data	datum	NOUN
ajst-23570	49	20	and	and	CCONJ
ajst-23570	49	21	the	the	DET
ajst-23570	49	22	posterior	posterior	ADJ
ajst-23570	49	23	distribution	distribution	NOUN
ajst-23570	49	24	can	can	AUX
ajst-23570	49	25	be	be	AUX
ajst-23570	49	26	used	use	VERB
ajst-23570	49	27	to	to	PART
ajst-23570	49	28	evaluate	evaluate	VERB
ajst-23570	49	29	the	the	DET
ajst-23570	49	30	performance	performance	NOUN
ajst-23570	49	31	of	of	ADP
ajst-23570	49	32	the	the	DET
ajst-23570	49	33	model	model	NOUN
ajst-23570	49	34	and	and	CCONJ
ajst-23570	49	35	to	to	PART
ajst-23570	49	36	interpret	interpret	VERB
ajst-23570	49	37	the	the	DET
ajst-23570	49	38	results[3	results[3	NOUN
ajst-23570	49	39	]	]	X
ajst-23570	49	40	.	.	PUNCT
ajst-23570	50	1	in	in	ADP
ajst-23570	50	2	bayesian	bayesian	PROPN
ajst-23570	50	3	linear	linear	PROPN
ajst-23570	50	4	regression	regression	NOUN
ajst-23570	50	5	,	,	PUNCT
ajst-23570	50	6	algorithms	algorithm	NOUN
ajst-23570	50	7	such	such	ADJ
ajst-23570	50	8	as	as	ADP
ajst-23570	50	9	gaussian	gaussian	ADJ
ajst-23570	50	10	process	process	NOUN
ajst-23570	50	11	regression	regression	NOUN
ajst-23570	50	12	(	(	PUNCT
ajst-23570	50	13	gpr	gpr	PROPN
ajst-23570	50	14	)	)	PUNCT
ajst-23570	50	15	or	or	CCONJ
ajst-23570	50	16	bayesian	bayesian	NOUN
ajst-23570	50	17	linear	linear	PROPN
ajst-23570	50	18	regression	regression	NOUN
ajst-23570	50	19	(	(	PUNCT
ajst-23570	50	20	blr	blr	PROPN
ajst-23570	50	21	)	)	PUNCT
ajst-23570	50	22	are	be	AUX
ajst-23570	50	23	commonly	commonly	ADV
ajst-23570	50	24	used	use	VERB
ajst-23570	50	25	to	to	PART
ajst-23570	50	26	fit	fit	VERB
ajst-23570	50	27	the	the	DET
ajst-23570	50	28	model	model	NOUN
ajst-23570	50	29	.	.	PUNCT
ajst-23570	51	1	these	these	DET
ajst-23570	51	2	algorithms	algorithm	NOUN
ajst-23570	51	3	are	be	AUX
ajst-23570	51	4	able	able	ADJ
ajst-23570	51	5	to	to	PART
ajst-23570	51	6	automatically	automatically	ADV
ajst-23570	51	7	deal	deal	VERB
ajst-23570	51	8	with	with	ADP
ajst-23570	51	9	nonlinear	nonlinear	ADJ
ajst-23570	51	10	relationships	relationship	NOUN
ajst-23570	51	11	and	and	CCONJ
ajst-23570	51	12	outliers	outlier	NOUN
ajst-23570	51	13	in	in	ADP
ajst-23570	51	14	the	the	DET
ajst-23570	51	15	data	datum	NOUN
ajst-23570	51	16	and	and	CCONJ
ajst-23570	51	17	provide	provide	VERB
ajst-23570	51	18	more	more	ADV
ajst-23570	51	19	flexible	flexible	ADJ
ajst-23570	51	20	and	and	CCONJ
ajst-23570	51	21	accurate	accurate	ADJ
ajst-23570	51	22	predictions[4	predictions[4	NOUN
ajst-23570	51	23	]	]	PUNCT
ajst-23570	51	24	.	.	PUNCT
ajst-23570	52	1	the	the	DET
ajst-23570	52	2	application	application	NOUN
ajst-23570	52	3	of	of	ADP
ajst-23570	52	4	bayesian	bayesian	NOUN
ajst-23570	52	5	methods	method	NOUN
ajst-23570	52	6	in	in	ADP
ajst-23570	52	7	linear	linear	PROPN
ajst-23570	52	8	regression	regression	NOUN
ajst-23570	52	9	provides	provide	VERB
ajst-23570	52	10	a	a	DET
ajst-23570	52	11	more	more	ADV
ajst-23570	52	12	comprehensive	comprehensive	ADJ
ajst-23570	52	13	and	and	CCONJ
ajst-23570	52	14	precise	precise	ADJ
ajst-23570	52	15	way	way	NOUN
ajst-23570	52	16	to	to	PART
ajst-23570	52	17	deal	deal	VERB
ajst-23570	52	18	with	with	ADP
ajst-23570	52	19	the	the	DET
ajst-23570	52	20	uncertainty	uncertainty	NOUN
ajst-23570	52	21	and	and	CCONJ
ajst-23570	52	22	noise	noise	NOUN
ajst-23570	52	23	in	in	ADP
ajst-23570	52	24	the	the	DET
ajst-23570	52	25	data	datum	NOUN
ajst-23570	52	26	,	,	PUNCT
ajst-23570	52	27	and	and	CCONJ
ajst-23570	52	28	provides	provide	VERB
ajst-23570	52	29	more	more	ADV
ajst-23570	52	30	flexible	flexible	ADJ
ajst-23570	52	31	and	and	CCONJ
ajst-23570	52	32	accurate	accurate	ADJ
ajst-23570	52	33	prediction	prediction	NOUN
ajst-23570	52	34	results[4	results[4	NOUN
ajst-23570	52	35	]	]	PUNCT
ajst-23570	52	36	.	.	PUNCT
ajst-23570	53	1	bayesian	bayesian	NOUN
ajst-23570	53	2	analysis	analysis	NOUN
ajst-23570	53	3	of	of	ADP
ajst-23570	53	4	multiple	multiple	ADJ
ajst-23570	53	5	linear	linear	ADJ
ajst-23570	53	6	regression	regression	NOUN
ajst-23570	53	7	model	model	NOUN
ajst-23570	53	8	:	:	PUNCT
ajst-23570	53	9	assume	assume	VERB
ajst-23570	53	10	that	that	SCONJ
ajst-23570	53	11	there	there	PRON
ajst-23570	53	12	are	be	VERB
ajst-23570	53	13	k	k	PROPN
ajst-23570	53	14	independent	independent	ADJ
ajst-23570	53	15	variables	variable	NOUN
ajst-23570	53	16	in	in	ADP
ajst-23570	53	17	the	the	DET
ajst-23570	53	18	model	model	NOUN
ajst-23570	53	19	:	:	PUNCT
ajst-23570	53	20	,	,	PUNCT
ajst-23570	53	21	,	,	PUNCT
ajst-23570	53	22	⋯	⋯	PROPN
ajst-23570	53	23	,	,	PUNCT
ajst-23570	53	24	,	,	PUNCT
ajst-23570	53	25	dependent	dependent	ADJ
ajst-23570	53	26	variable	variable	NOUN
ajst-23570	53	27	:	:	PUNCT
ajst-23570	53	28	,	,	PUNCT
ajst-23570	53	29	⋯	⋯	PROPN
ajst-23570	53	30	,	,	PUNCT
ajst-23570	53	31	,	,	PUNCT
ajst-23570	53	32	there	there	PRON
ajst-23570	53	33	is	be	VERB
ajst-23570	53	34	the	the	DET
ajst-23570	53	35	following	following	ADJ
ajst-23570	53	36	linear	linear	ADJ
ajst-23570	53	37	functional	functional	ADJ
ajst-23570	53	38	relationship	relationship	NOUN
ajst-23570	53	39	between	between	ADP
ajst-23570	53	40	them	they	PRON
ajst-23570	54	1	[	[	X
ajst-23570	54	2	4	4	NUM
ajst-23570	54	3	]	]	PUNCT
ajst-23570	54	4	⋯	⋯	PROPN
ajst-23570	54	5	⋯	⋯	PROPN
ajst-23570	54	6	⋯	⋯	PROPN
ajst-23570	54	7	⋯	⋯	PROPN
ajst-23570	54	8	(	(	PUNCT
ajst-23570	54	9	3	3	NUM
ajst-23570	54	10	)	)	PUNCT
ajst-23570	54	11	in	in	ADP
ajst-23570	54	12	the	the	DET
ajst-23570	54	13	equation	equation	NOUN
ajst-23570	54	14	,	,	PUNCT
ajst-23570	54	15	(	(	PUNCT
ajst-23570	54	16	i=0,1,	i=0,1,	NOUN
ajst-23570	54	17	…	…	PUNCT
ajst-23570	54	18	,k;j=1,2,	,k;j=1,2,	ADJ
ajst-23570	54	19	…	…	PUNCT
ajst-23570	54	20	,m	,m	PUNCT
ajst-23570	54	21	)	)	PUNCT
ajst-23570	54	22	are	be	AUX
ajst-23570	54	23	unknown	unknown	ADJ
ajst-23570	54	24	parameter	parameter	NOUN
ajst-23570	54	25	,	,	PUNCT
ajst-23570	54	26	,	,	PUNCT
ajst-23570	54	27	,	,	PUNCT
ajst-23570	54	28	,	,	PUNCT
ajst-23570	54	29	⋯	⋯	PROPN
ajst-23570	54	30	,	,	PUNCT
ajst-23570	54	31	is	be	AUX
ajst-23570	54	32	the	the	DET
ajst-23570	54	33	random	random	ADJ
ajst-23570	54	34	error	error	NOUN
ajst-23570	54	35	term	term	NOUN
ajst-23570	54	36	,	,	PUNCT
ajst-23570	54	37	they	they	PRON
ajst-23570	54	38	are	be	AUX
ajst-23570	54	39	not	not	PART
ajst-23570	54	40	necessarily	necessarily	ADV
ajst-23570	54	41	independent	independent	ADJ
ajst-23570	54	42	of	of	ADP
ajst-23570	54	43	each	each	DET
ajst-23570	54	44	other	other	ADJ
ajst-23570	54	45	,	,	PUNCT
ajst-23570	54	46	assuming	assume	VERB
ajst-23570	54	47	that	that	SCONJ
ajst-23570	54	48	they	they	PRON
ajst-23570	54	49	follow	follow	VERB
ajst-23570	54	50	a	a	DET
ajst-23570	54	51	multivariate	multivariate	NOUN
ajst-23570	54	52	normal	normal	ADJ
ajst-23570	54	53	distribution	distribution	NOUN
ajst-23570	54	54	,	,	PUNCT
ajst-23570	54	55	i.e.	i.e.	X
ajst-23570	54	56	,	,	PUNCT
ajst-23570	54	57	,	,	PUNCT
ajst-23570	54	58	⋯	⋯	PROPN
ajst-23570	54	59	,	,	PUNCT
ajst-23570	54	60	~	~	PUNCT
ajst-23570	54	61	0,∑	0,∑	NUM
ajst-23570	54	62	,	,	PUNCT
ajst-23570	54	63	∑	∑	PROPN
ajst-23570	54	64	0	0	NUM
ajst-23570	54	65	(	(	PUNCT
ajst-23570	54	66	4	4	NUM
ajst-23570	54	67	)	)	PUNCT
ajst-23570	54	68	since	since	SCONJ
ajst-23570	54	69	it	it	PRON
ajst-23570	54	70	is	be	AUX
ajst-23570	54	71	convenient	convenient	ADJ
ajst-23570	54	72	to	to	PART
ajst-23570	54	73	study	study	VERB
ajst-23570	54	74	the	the	DET
ajst-23570	54	75	problem	problem	NOUN
ajst-23570	54	76	of	of	ADP
ajst-23570	54	77	multiple	multiple	ADJ
ajst-23570	54	78	linear	linear	ADJ
ajst-23570	54	79	regression	regression	NOUN
ajst-23570	54	80	model	model	NOUN
ajst-23570	54	81	by	by	ADP
ajst-23570	54	82	matrix	matrix	NOUN
ajst-23570	54	83	method	method	NOUN
ajst-23570	54	84	,	,	PUNCT
ajst-23570	54	85	the	the	DET
ajst-23570	54	86	above	above	ADJ
ajst-23570	54	87	model	model	NOUN
ajst-23570	54	88	is	be	AUX
ajst-23570	54	89	transformed	transform	VERB
ajst-23570	54	90	into	into	ADP
ajst-23570	54	91	matrix	matrix	NOUN
ajst-23570	54	92	form	form	NOUN
ajst-23570	54	93	⋮	⋮	NOUN
ajst-23570	54	94	⋯	⋯	VERB
ajst-23570	54	95	⋮	⋮	NOUN
ajst-23570	54	96	⋯	⋯	NOUN
ajst-23570	54	97	⋮	⋮	NOUN
ajst-23570	54	98	⋮	⋮	NOUN
ajst-23570	54	99	⋯	⋯	ADP
ajst-23570	54	100	1	1	NUM
ajst-23570	54	101	1	1	NUM
ajst-23570	54	102	⋮	⋮	NOUN
ajst-23570	54	103	1	1	NUM
ajst-23570	54	104	⋮	⋮	NOUN
ajst-23570	54	105	(	(	PUNCT
ajst-23570	54	106	5	5	NUM
ajst-23570	54	107	)	)	PUNCT
ajst-23570	54	108	assuming	assume	VERB
ajst-23570	54	109	that	that	SCONJ
ajst-23570	54	110	n	n	NOUN
ajst-23570	54	111	sets	set	NOUN
ajst-23570	54	112	of	of	ADP
ajst-23570	54	113	values	value	NOUN
ajst-23570	54	114	of	of	ADP
ajst-23570	54	115	k	k	PROPN
ajst-23570	54	116	independent	independent	ADJ
ajst-23570	54	117	variables	variable	NOUN
ajst-23570	54	118	are	be	AUX
ajst-23570	54	119	given	give	VERB
ajst-23570	54	120	and	and	CCONJ
ajst-23570	54	121	the	the	DET
ajst-23570	54	122	corresponding	correspond	VERB
ajst-23570	54	123	m	m	VERB
ajst-23570	54	124	dependent	dependent	ADJ
ajst-23570	54	125	variables	variable	NOUN
ajst-23570	54	126	are	be	AUX
ajst-23570	54	127	observed	observe	VERB
ajst-23570	54	128	,	,	PUNCT
ajst-23570	54	129	the	the	DET
ajst-23570	54	130	following	follow	VERB
ajst-23570	54	131	n	n	PRON
ajst-23570	54	132	sets	set	NOUN
ajst-23570	54	133	of	of	ADP
ajst-23570	54	134	observed	observed	ADJ
ajst-23570	54	135	values	value	NOUN
ajst-23570	54	136	are	be	AUX
ajst-23570	54	137	obtained	obtain	VERB
ajst-23570	54	138	:	:	PUNCT
ajst-23570	54	139	,	,	PUNCT
ajst-23570	54	140	,	,	PUNCT
ajst-23570	54	141	⋯	⋯	PROPN
ajst-23570	54	142	,	,	PUNCT
ajst-23570	54	143	;	;	PUNCT
ajst-23570	54	144	,	,	PUNCT
ajst-23570	54	145	,	,	PUNCT
ajst-23570	54	146	⋯	⋯	PROPN
ajst-23570	54	147	,	,	PUNCT
ajst-23570	54	148	,	,	PUNCT
ajst-23570	54	149	,	,	PUNCT
ajst-23570	54	150	⋯	⋯	PROPN
ajst-23570	54	151	,	,	PUNCT
ajst-23570	54	152	;	;	PUNCT
ajst-23570	54	153	,	,	PUNCT
ajst-23570	54	154	,	,	PUNCT
ajst-23570	54	155	⋯	⋯	PROPN
ajst-23570	54	156	,	,	PUNCT
ajst-23570	54	157	⋯	⋯	PROPN
ajst-23570	54	158	⋯	⋯	PROPN
ajst-23570	54	159	⋯	⋯	PROPN
ajst-23570	54	160	⋯	⋯	PROPN
ajst-23570	54	161	⋯	⋯	PROPN
ajst-23570	54	162	⋯	⋯	PROPN
ajst-23570	54	163	,	,	PUNCT
ajst-23570	54	164	,	,	PUNCT
ajst-23570	54	165	⋯	⋯	PROPN
ajst-23570	54	166	,	,	PUNCT
ajst-23570	54	167	;	;	PUNCT
ajst-23570	54	168	,	,	PUNCT
ajst-23570	54	169	,	,	PUNCT
ajst-23570	54	170	⋯	⋯	PROPN
ajst-23570	54	171	,	,	PUNCT
ajst-23570	54	172	by	by	ADP
ajst-23570	54	173	substituting	substitute	VERB
ajst-23570	54	174	it	it	PRON
ajst-23570	54	175	for	for	ADP
ajst-23570	54	176	model	model	NOUN
ajst-23570	54	177	(	(	PUNCT
ajst-23570	54	178	5	5	NUM
ajst-23570	54	179	)	)	PUNCT
ajst-23570	54	180	,	,	PUNCT
ajst-23570	54	181	there	there	PRON
ajst-23570	54	182	is	be	VERB
ajst-23570	54	183	⋯	⋯	NOUN
ajst-23570	54	184	⋮	⋮	NOUN
ajst-23570	54	185	⋮	⋮	NOUN
ajst-23570	54	186	⋯	⋯	PROPN
ajst-23570	54	187	⋯	⋯	PROPN
ajst-23570	54	188	⋮	⋮	NOUN
ajst-23570	54	189	1	1	NUM
ajst-23570	54	190	⋯	⋯	SYM
ajst-23570	54	191	1	1	NUM
ajst-23570	54	192	⋮	⋮	NOUN
ajst-23570	54	193	1	1	NUM
ajst-23570	54	194	⋮	⋮	NOUN
ajst-23570	54	195	⋯	⋯	PROPN
ajst-23570	54	196	⋯	⋯	NOUN
ajst-23570	54	197	⋮	⋮	NOUN
ajst-23570	54	198	⋯	⋯	NOUN
ajst-23570	54	199	⋮	⋮	PROPN
ajst-23570	54	200	⋮	⋮	PROPN
ajst-23570	54	201	⋯	⋯	PROPN
ajst-23570	54	202	⋯	⋯	PROPN
ajst-23570	54	203	⋮	⋮	NOUN
ajst-23570	54	204	⋯	⋯	NOUN
ajst-23570	54	205	⋮	⋮	PROPN
ajst-23570	54	206	⋮	⋮	PROPN
ajst-23570	54	207	⋯	⋯	PROPN
ajst-23570	54	208	⋯	⋯	PROPN
ajst-23570	54	209	⋮	⋮	NOUN
ajst-23570	54	210	(	(	PUNCT
ajst-23570	54	211	6	6	NUM
ajst-23570	54	212	)	)	PUNCT
ajst-23570	54	213	if	if	SCONJ
ajst-23570	54	214	each	each	DET
ajst-23570	54	215	matrix	matrix	NOUN
ajst-23570	54	216	in	in	ADP
ajst-23570	54	217	the	the	DET
ajst-23570	54	218	above	above	ADJ
ajst-23570	54	219	equation	equation	NOUN
ajst-23570	54	220	is	be	AUX
ajst-23570	54	221	denoted	denote	VERB
ajst-23570	54	222	as	as	ADP
ajst-23570	54	223	y	y	PROPN
ajst-23570	54	224	,	,	PUNCT
ajst-23570	54	225	x	x	NOUN
ajst-23570	54	226	,	,	PUNCT
ajst-23570	54	227	β	β	X
ajst-23570	54	228	and	and	CCONJ
ajst-23570	54	229	ε	ε	PROPN
ajst-23570	54	230	from	from	ADP
ajst-23570	54	231	left	left	ADJ
ajst-23570	54	232	to	to	ADP
ajst-23570	54	233	right	right	NOUN
ajst-23570	54	234	,	,	PUNCT
ajst-23570	54	235	it	it	PRON
ajst-23570	54	236	can	can	AUX
ajst-23570	54	237	be	be	AUX
ajst-23570	54	238	further	far	ADV
ajst-23570	54	239	reduced	reduce	VERB
ajst-23570	54	240	to	to	ADP
ajst-23570	54	241	(	(	PUNCT
ajst-23570	54	242	7	7	NUM
ajst-23570	54	243	)	)	PUNCT
ajst-23570	54	244	or	or	CCONJ
ajst-23570	54	245	its	its	PRON
ajst-23570	54	246	equivalent	equivalent	ADJ
ajst-23570	54	247	⋮	⋮	NOUN
ajst-23570	54	248	⋮	⋮	ADJ
ajst-23570	54	249	⋮	⋮	NOUN
ajst-23570	54	250	,	,	PUNCT
ajst-23570	54	251	~	~	PUNCT
ajst-23570	54	252	0	0	NUM
ajst-23570	54	253	,	,	PUNCT
ajst-23570	54	254	,	,	PUNCT
ajst-23570	54	255	1,2,⋯	1,2,⋯	NUM
ajst-23570	54	256	,	,	PUNCT
ajst-23570	54	257	(	(	PUNCT
ajst-23570	54	258	8)	8)	NUM
ajst-23570	54	259	here	here	ADV
ajst-23570	54	260	,	,	PUNCT
ajst-23570	54	261	,	,	PUNCT
ajst-23570	54	262	,	,	PUNCT
ajst-23570	54	263	j=1	j=1	PROPN
ajst-23570	54	264	,	,	PUNCT
ajst-23570	54	265	2	2	NUM
ajst-23570	54	266	,	,	PUNCT
ajst-23570	54	267	...	...	PUNCT
ajst-23570	54	268	,	,	PUNCT
ajst-23570	54	269	denote	denote	VERB
ajst-23570	54	270	the	the	DET
ajst-23570	54	271	transpose	transpose	NOUN
ajst-23570	54	272	of	of	ADP
ajst-23570	54	273	the	the	DET
ajst-23570	54	274	matrix	matrix	NOUN
ajst-23570	54	275	y	y	NOUN
ajst-23570	54	276	,	,	PUNCT
ajst-23570	54	277	xβ	xβ	ADV
ajst-23570	54	278	and	and	CCONJ
ajst-23570	54	279	row	row	VERB
ajst-23570	54	280	j	j	PROPN
ajst-23570	54	281	of	of	ADP
ajst-23570	54	282	ε	ε	PROPN
ajst-23570	54	283	respectively	respectively	ADV
ajst-23570	54	284	,	,	PUNCT
ajst-23570	54	285	which	which	PRON
ajst-23570	54	286	are	be	AUX
ajst-23570	54	287	mdimensional	mdimensional	ADJ
ajst-23570	54	288	column	column	NOUN
ajst-23570	54	289	vectors	vector	NOUN
ajst-23570	54	290	.	.	PUNCT
ajst-23570	55	1	obviously	obviously	ADV
ajst-23570	55	2	,	,	PUNCT
ajst-23570	55	3	,	,	PUNCT
ajst-23570	55	4	1,2,⋯	1,2,⋯	INTJ
ajst-23570	55	5	,	,	PUNCT
ajst-23570	55	6	since	since	SCONJ
ajst-23570	55	7	,	,	PUNCT
ajst-23570	55	8	,	,	PUNCT
ajst-23570	55	9	⋯	⋯	PROPN
ajst-23570	55	10	,	,	PUNCT
ajst-23570	55	11	~	~	PUNCT
ajst-23570	56	1	.i.d	.i.d	PROPN
ajst-23570	56	2	.	.	PROPN
ajst-23570	57	1	0	0	NUM
ajst-23570	57	2	,	,	PUNCT
ajst-23570	58	1	so	so	ADV
ajst-23570	58	2	,	,	PUNCT
ajst-23570	58	3	,	,	PUNCT
ajst-23570	58	4	⋯	⋯	PROPN
ajst-23570	58	5	,	,	PUNCT
ajst-23570	58	6	is	be	AUX
ajst-23570	58	7	also	also	ADV
ajst-23570	58	8	independent	independent	ADJ
ajst-23570	58	9	of	of	ADP
ajst-23570	58	10	each	each	DET
ajst-23570	58	11	other	other	ADJ
ajst-23570	58	12	and	and	CCONJ
ajst-23570	58	13	follows	follow	VERB
ajst-23570	58	14	the	the	DET
ajst-23570	58	15	multivariate	multivariate	NOUN
ajst-23570	58	16	normal	normal	ADJ
ajst-23570	58	17	distribution	distribution	NOUN
ajst-23570	58	18	with	with	ADP
ajst-23570	58	19	mean	mean	ADJ
ajst-23570	58	20	vector	vector	NOUN
ajst-23570	58	21	and	and	CCONJ
ajst-23570	58	22	covariance	covariance	NOUN
ajst-23570	58	23	matrix	matrix	NOUN
ajst-23570	58	24	is	be	AUX
ajst-23570	58	25	σ	σ	PROPN
ajst-23570	58	26	,	,	PUNCT
ajst-23570	58	27	i.e	i.e	X
ajst-23570	58	28	~	~	PUNCT
ajst-23570	58	29	,	,	PUNCT
ajst-23570	58	30	,	,	PUNCT
ajst-23570	58	31	1,2,⋯	1,2,⋯	NUM
ajst-23570	58	32	,	,	PUNCT
ajst-23570	58	33	(	(	PUNCT
ajst-23570	58	34	9	9	NUM
ajst-23570	58	35	)	)	PUNCT
ajst-23570	58	36	in	in	ADP
ajst-23570	58	37	this	this	DET
ajst-23570	58	38	case	case	NOUN
ajst-23570	58	39	,	,	PUNCT
ajst-23570	58	40	the	the	DET
ajst-23570	58	41	sample	sample	NOUN
ajst-23570	58	42	likelihood	likelihood	NOUN
ajst-23570	58	43	function	function	NOUN
ajst-23570	58	44	is	be	AUX
ajst-23570	58	45	l	l	NOUN
ajst-23570	58	46	β	β	X
ajst-23570	58	47	,	,	PUNCT
ajst-23570	58	48	∏	∏	PROPN
ajst-23570	58	49	2π	2π	NOUN
ajst-23570	59	1	⁄	⁄	ADP
ajst-23570	60	1	|	|	ADV
ajst-23570	60	2	|	|	ADV
ajst-23570	60	3	⁄	⁄	ADP
ajst-23570	60	4	exp	exp	NOUN
ajst-23570	60	5	y	y	PROPN
ajst-23570	60	6	2π	2π	PROPN
ajst-23570	61	1	⁄	⁄	ADP
ajst-23570	62	1	|	|	ADV
ajst-23570	62	2	|	|	ADV
ajst-23570	62	3	⁄	⁄	ADP
ajst-23570	62	4	exp	exp	NOUN
ajst-23570	62	5	∑	∑	PROPN
ajst-23570	62	6	y	y	PROPN
ajst-23570	62	7	xβ	xβ	PROPN
ajst-23570	62	8	y	y	PROPN
ajst-23570	62	9	xβ	xβ	PROPN
ajst-23570	62	10	2π	2π	PROPN
ajst-23570	63	1	⁄	⁄	ADP
ajst-23570	64	1	|	|	ADV
ajst-23570	64	2	|	|	ADV
ajst-23570	64	3	⁄	⁄	ADJ
ajst-23570	64	4	exp	exp	NOUN
ajst-23570	64	5	tr	tr	PROPN
ajst-23570	64	6	y	y	PROPN
ajst-23570	64	7	xβ	xβ	PROPN
ajst-23570	64	8	y	y	PROPN
ajst-23570	64	9	xβ	xβ	PROPN
ajst-23570	64	10	(	(	PUNCT
ajst-23570	64	11	10	10	NUM
ajst-23570	64	12	)	)	PUNCT
ajst-23570	64	13	before	before	ADP
ajst-23570	64	14	further	further	ADJ
ajst-23570	64	15	analysis	analysis	NOUN
ajst-23570	64	16	of	of	ADP
ajst-23570	64	17	the	the	DET
ajst-23570	64	18	model	model	NOUN
ajst-23570	64	19	,	,	PUNCT
ajst-23570	64	20	matrix	matrix	VERB
ajst-23570	64	21	normal	normal	ADJ
ajst-23570	64	22	distribution	distribution	NOUN
ajst-23570	64	23	is	be	AUX
ajst-23570	64	24	introduced	introduce	VERB
ajst-23570	64	25	,	,	PUNCT
ajst-23570	64	26	which	which	PRON
ajst-23570	64	27	is	be	AUX
ajst-23570	64	28	a	a	DET
ajst-23570	64	29	generalization	generalization	NOUN
ajst-23570	64	30	of	of	ADP
ajst-23570	64	31	108	108	NUM
ajst-23570	64	32	multivariate	multivariate	NOUN
ajst-23570	64	33	normal	normal	ADJ
ajst-23570	64	34	distribution	distribution	NOUN
ajst-23570	64	35	and	and	CCONJ
ajst-23570	64	36	is	be	AUX
ajst-23570	64	37	defined	define	VERB
ajst-23570	64	38	as	as	SCONJ
ajst-23570	64	39	follows	follow	VERB
ajst-23570	64	40	:	:	PUNCT
ajst-23570	64	41	if	if	SCONJ
ajst-23570	64	42	is	be	AUX
ajst-23570	64	43	a	a	DET
ajst-23570	64	44	random	random	ADJ
ajst-23570	64	45	matrix	matrix	NOUN
ajst-23570	64	46	of	of	ADP
ajst-23570	64	47	households	household	NOUN
ajst-23570	64	48	the	the	DET
ajst-23570	64	49	distribution	distribution	NOUN
ajst-23570	64	50	density	density	NOUN
ajst-23570	64	51	function	function	NOUN
ajst-23570	64	52	of	of	ADP
ajst-23570	64	53	vec	vec	PROPN
ajst-23570	64	54	y	y	PROPN
ajst-23570	64	55	is	be	AUX
ajst-23570	64	56	ʄ	ʄ	PROPN
ajst-23570	64	57	|	|	ADV
ajst-23570	64	58	,	,	PUNCT
ajst-23570	64	59	,	,	PUNCT
ajst-23570	64	60	/	/	PUNCT
ajst-23570	65	1	|	|	ADV
ajst-23570	65	2	|	|	ADV
ajst-23570	65	3	⁄	⁄	ADV
ajst-23570	66	1	|	|	INTJ
ajst-23570	66	2	|	|	ADV
ajst-23570	67	1	⁄	⁄	ADJ
ajst-23570	67	2	(	(	PUNCT
ajst-23570	67	3	11	11	NUM
ajst-23570	67	4	)	)	PUNCT
ajst-23570	67	5	the	the	DET
ajst-23570	67	6	random	random	ADJ
ajst-23570	67	7	matrix	matrix	NOUN
ajst-23570	67	8	is	be	AUX
ajst-23570	67	9	said	say	VERB
ajst-23570	67	10	to	to	PART
ajst-23570	67	11	follow	follow	VERB
ajst-23570	67	12	the	the	DET
ajst-23570	67	13	matrix	matrix	NOUN
ajst-23570	67	14	normal	normal	ADJ
ajst-23570	67	15	distribution	distribution	NOUN
ajst-23570	67	16	,	,	PUNCT
ajst-23570	67	17	and	and	CCONJ
ajst-23570	67	18	let	let	VERB
ajst-23570	67	19	's	us	PRON
ajst-23570	67	20	write	write	VERB
ajst-23570	67	21	it	it	PRON
ajst-23570	67	22	as	as	ADP
ajst-23570	67	23	~	~	PUNCT
ajst-23570	67	24	,	,	PUNCT
ajst-23570	67	25	⨂	⨂	PROPN
ajst-23570	67	26	;	;	PUNCT
ajst-23570	67	27	here	here	ADV
ajst-23570	67	28	the	the	PRON
ajst-23570	67	29	and	and	CCONJ
ajst-23570	67	30	is	be	AUX
ajst-23570	67	31	a	a	DET
ajst-23570	67	32	positive	positive	ADJ
ajst-23570	67	33	definite	definite	ADJ
ajst-23570	67	34	matrix	matrix	NOUN
ajst-23570	67	35	∈	∈	NOUN
ajst-23570	67	36	,	,	PUNCT
ajst-23570	67	37	∈	∈	PROPN
ajst-23570	67	38	,	,	PUNCT
ajst-23570	67	39	while	while	SCONJ
ajst-23570	67	40	the	the	DET
ajst-23570	67	41	symbol	symbol	NOUN
ajst-23570	67	42	"	"	PUNCT
ajst-23570	67	43	⨂	⨂	PROPN
ajst-23570	67	44	"	"	PUNCT
ajst-23570	67	45	denotes	denote	VERB
ajst-23570	67	46	the	the	DET
ajst-23570	67	47	kronecker	kronecker	NOUN
ajst-23570	67	48	product	product	NOUN
ajst-23570	67	49	of	of	ADP
ajst-23570	67	50	the	the	DET
ajst-23570	67	51	matrix	matrix	NOUN
ajst-23570	67	52	.	.	PUNCT
ajst-23570	68	1	if	if	SCONJ
ajst-23570	68	2	write	write	VERB
ajst-23570	68	3	,	,	PUNCT
ajst-23570	68	4	s=	s=	NOUN
ajst-23570	68	5	it	it	PRON
ajst-23570	68	6	is	be	AUX
ajst-23570	68	7	not	not	PART
ajst-23570	68	8	difficult	difficult	ADJ
ajst-23570	68	9	to	to	PART
ajst-23570	68	10	verify	verify	VERB
ajst-23570	68	11	that	that	SCONJ
ajst-23570	68	12	the	the	DET
ajst-23570	68	13	following	follow	VERB
ajst-23570	68	14	equation	equation	NOUN
ajst-23570	68	15	holds	hold	VERB
ajst-23570	68	16	0	0	NUM
ajst-23570	68	17	(	(	PUNCT
ajst-23570	68	18	12	12	NUM
ajst-23570	68	19	)	)	PUNCT
ajst-23570	68	20	using	use	VERB
ajst-23570	68	21	this	this	DET
ajst-23570	68	22	condition	condition	NOUN
ajst-23570	68	23	,	,	PUNCT
ajst-23570	68	24	the	the	DET
ajst-23570	68	25	quadratic	quadratic	ADJ
ajst-23570	68	26	term	term	NOUN
ajst-23570	68	27	in	in	ADP
ajst-23570	68	28	equation	equation	NOUN
ajst-23570	68	29	(	(	PUNCT
ajst-23570	68	30	10	10	NUM
ajst-23570	68	31	)	)	PUNCT
ajst-23570	68	32	is	be	AUX
ajst-23570	68	33	decomposed	decompose	VERB
ajst-23570	68	34	as	as	SCONJ
ajst-23570	68	35	follows	follow	VERB
ajst-23570	68	36	(	(	PUNCT
ajst-23570	68	37	13	13	NUM
ajst-23570	68	38	)	)	PUNCT
ajst-23570	68	39	accordingly	accordingly	ADV
ajst-23570	68	40	,	,	PUNCT
ajst-23570	68	41	the	the	DET
ajst-23570	68	42	sample	sample	NOUN
ajst-23570	68	43	likelihood	likelihood	NOUN
ajst-23570	68	44	function	function	NOUN
ajst-23570	68	45	in	in	ADP
ajst-23570	68	46	equation	equation	NOUN
ajst-23570	68	47	(	(	PUNCT
ajst-23570	68	48	10	10	NUM
ajst-23570	68	49	)	)	PUNCT
ajst-23570	68	50	can	can	AUX
ajst-23570	68	51	be	be	AUX
ajst-23570	68	52	decomposed	decompose	VERB
ajst-23570	68	53	as	as	SCONJ
ajst-23570	68	54	follows	follow	VERB
ajst-23570	68	55	:	:	PUNCT
ajst-23570	68	56	l	l	NOUN
ajst-23570	68	57	β	β	X
ajst-23570	68	58	,	,	PUNCT
ajst-23570	68	59	⁄	⁄	PROPN
ajst-23570	68	60	⁄	⁄	PROPN
ajst-23570	68	61	exp	exp	NOUN
ajst-23570	68	62	tr	tr	VERB
ajst-23570	68	63	∙	∙	PROPN
ajst-23570	69	1	|	|	ADV
ajst-23570	69	2	|	|	ADV
ajst-23570	69	3	⁄	⁄	PROPN
ajst-23570	69	4	exp	exp	NOUN
ajst-23570	69	5	trs	trs	PROPN
ajst-23570	69	6	(	(	PUNCT
ajst-23570	69	7	14	14	NUM
ajst-23570	69	8	)	)	PUNCT
ajst-23570	69	9	it	it	PRON
ajst-23570	69	10	is	be	AUX
ajst-23570	69	11	easy	easy	ADJ
ajst-23570	69	12	to	to	PART
ajst-23570	69	13	see	see	VERB
ajst-23570	69	14	that	that	SCONJ
ajst-23570	69	15	the	the	DET
ajst-23570	69	16	first	first	ADJ
ajst-23570	69	17	term	term	NOUN
ajst-23570	69	18	on	on	ADP
ajst-23570	69	19	the	the	DET
ajst-23570	69	20	right	right	ADJ
ajst-23570	69	21	side	side	NOUN
ajst-23570	69	22	of	of	ADP
ajst-23570	69	23	the	the	DET
ajst-23570	69	24	above	above	ADJ
ajst-23570	69	25	equation	equation	NOUN
ajst-23570	69	26	is	be	AUX
ajst-23570	69	27	when	when	SCONJ
ajst-23570	69	28	the	the	DET
ajst-23570	69	29	precision	precision	NOUN
ajst-23570	69	30	matrix	matrix	NOUN
ajst-23570	69	31	is	be	AUX
ajst-23570	69	32	given	give	VERB
ajst-23570	69	33	,	,	PUNCT
ajst-23570	69	34	the	the	DET
ajst-23570	69	35	mean	mean	ADJ
ajst-23570	69	36	value	value	NOUN
ajst-23570	69	37	is	be	AUX
ajst-23570	69	38	β	β	PROPN
ajst-23570	69	39	,	,	PUNCT
ajst-23570	69	40	the	the	DET
ajst-23570	69	41	covariance	covariance	NOUN
ajst-23570	69	42	matrix	matrix	NOUN
ajst-23570	69	43	is	be	AUX
ajst-23570	69	44	⨂	⨂	NOUN
ajst-23570	69	45	the	the	DET
ajst-23570	69	46	kernel	kernel	NOUN
ajst-23570	69	47	of	of	ADP
ajst-23570	69	48	the	the	DET
ajst-23570	69	49	density	density	NOUN
ajst-23570	69	50	function	function	NOUN
ajst-23570	69	51	of	of	ADP
ajst-23570	69	52	the	the	DET
ajst-23570	69	53	matrix	matrix	NOUN
ajst-23570	69	54	normal	normal	ADJ
ajst-23570	69	55	distribution	distribution	NOUN
ajst-23570	69	56	,	,	PUNCT
ajst-23570	69	57	⨂	⨂	PROPN
ajst-23570	69	58	,	,	PUNCT
ajst-23570	69	59	the	the	DET
ajst-23570	69	60	second	second	ADJ
ajst-23570	69	61	term	term	NOUN
ajst-23570	69	62	is	be	AUX
ajst-23570	69	63	the	the	DET
ajst-23570	69	64	kernel	kernel	NOUN
ajst-23570	69	65	of	of	ADP
ajst-23570	69	66	the	the	DET
ajst-23570	69	67	density	density	NOUN
ajst-23570	69	68	function	function	NOUN
ajst-23570	69	69	,	,	PUNCT
ajst-23570	69	70	of	of	ADP
ajst-23570	69	71	the	the	DET
ajst-23570	69	72	wishart	wishart	NOUN
ajst-23570	69	73	distribution	distribution	NOUN
ajst-23570	69	74	.because	.because	SCONJ
ajst-23570	69	75	the	the	DET
ajst-23570	69	76	family	family	NOUN
ajst-23570	69	77	of	of	ADP
ajst-23570	69	78	conjugate	conjugate	ADJ
ajst-23570	69	79	distributions	distribution	NOUN
ajst-23570	69	80	of	of	ADP
ajst-23570	69	81	matrix	matrix	NOUN
ajst-23570	69	82	normal	normal	ADJ
ajst-23570	69	83	distributions	distribution	NOUN
ajst-23570	69	84	is	be	AUX
ajst-23570	69	85	matrix	matrix	VERB
ajst-23570	69	86	normal	normal	ADJ
ajst-23570	69	87	when	when	SCONJ
ajst-23570	69	88	the	the	DET
ajst-23570	69	89	covariance	covariance	NOUN
ajst-23570	69	90	matrix	matrix	NOUN
ajst-23570	69	91	is	be	AUX
ajst-23570	69	92	known	know	VERB
ajst-23570	69	93	,	,	PUNCT
ajst-23570	69	94	the	the	DET
ajst-23570	69	95	conjugate	conjugate	ADJ
ajst-23570	69	96	family	family	NOUN
ajst-23570	69	97	of	of	ADP
ajst-23570	69	98	wishart	wishart	PROPN
ajst-23570	69	99	distributions	distribution	NOUN
ajst-23570	69	100	is	be	AUX
ajst-23570	69	101	still	still	ADV
ajst-23570	69	102	wishart	wishart	PROPN
ajst-23570	69	103	.therefore	.therefore	NOUN
ajst-23570	69	104	,	,	PUNCT
ajst-23570	69	105	the	the	DET
ajst-23570	69	106	matrix	matrix	NOUN
ajst-23570	69	107	normal	normal	ADJ
ajst-23570	69	108	wishart	wishart	NOUN
ajst-23570	69	109	distribution	distribution	NOUN
ajst-23570	69	110	is	be	AUX
ajst-23570	69	111	the	the	DET
ajst-23570	69	112	joint	joint	ADJ
ajst-23570	69	113	conjugate	conjugate	ADJ
ajst-23570	69	114	prior	prior	ADJ
ajst-23570	69	115	distribution	distribution	NOUN
ajst-23570	69	116	of	of	ADP
ajst-23570	69	117	the	the	DET
ajst-23570	69	118	coefficient	coefficient	NOUN
ajst-23570	69	119	matrix	matrix	NOUN
ajst-23570	69	120	and	and	CCONJ
ajst-23570	69	121	the	the	DET
ajst-23570	69	122	precision	precision	NOUN
ajst-23570	69	123	matrix	matrix	NOUN
ajst-23570	69	124	in	in	ADP
ajst-23570	69	125	the	the	DET
ajst-23570	69	126	multi	multi	ADJ
ajst-23570	69	127	-	-	ADJ
ajst-23570	69	128	equation	equation	ADJ
ajst-23570	69	129	linear	linear	NOUN
ajst-23570	69	130	model	model	NOUN
ajst-23570	69	131	system	system	NOUN
ajst-23570	69	132	.	.	PUNCT
ajst-23570	70	1	it	it	PRON
ajst-23570	70	2	can	can	AUX
ajst-23570	70	3	be	be	AUX
ajst-23570	70	4	seen	see	VERB
ajst-23570	70	5	that	that	SCONJ
ajst-23570	70	6	there	there	PRON
ajst-23570	70	7	isa	isa	VERB
ajst-23570	70	8	theoretical	theoretical	ADJ
ajst-23570	70	9	basis	basis	NOUN
ajst-23570	70	10	for	for	ADP
ajst-23570	70	11	choosing	choose	VERB
ajst-23570	70	12	the	the	DET
ajst-23570	70	13	following	follow	VERB
ajst-23570	70	14	matrix	matrix	NOUN
ajst-23570	70	15	normal	normal	ADJ
ajst-23570	70	16	-	-	PUNCT
ajst-23570	70	17	wishart	wishart	NOUN
ajst-23570	70	18	distribution	distribution	NOUN
ajst-23570	70	19	as	as	ADP
ajst-23570	70	20	the	the	DET
ajst-23570	70	21	conjugate	conjugate	ADJ
ajst-23570	70	22	prior	prior	ADJ
ajst-23570	70	23	distribution	distribution	NOUN
ajst-23570	70	24	of	of	ADP
ajst-23570	70	25	the	the	DET
ajst-23570	70	26	parameters	parameter	NOUN
ajst-23570	70	27	π	π	X
ajst-23570	70	28	β	β	X
ajst-23570	70	29	,	,	PUNCT
ajst-23570	70	30	π	π	PROPN
ajst-23570	70	31	β|	β|	ADP
ajst-23570	70	32	π	π	PROPN
ajst-23570	70	33	(	(	PUNCT
ajst-23570	70	34	15	15	NUM
ajst-23570	70	35	)	)	PUNCT
ajst-23570	70	36	of	of	ADP
ajst-23570	70	37	which	which	PRON
ajst-23570	70	38	π	π	PROPN
ajst-23570	70	39	β|	β|	ADP
ajst-23570	70	40	=	=	SYM
ajst-23570	70	41	,	,	PUNCT
ajst-23570	70	42	,	,	PUNCT
ajst-23570	70	43	|	|	ADV
ajst-23570	70	44	|	|	ADV
ajst-23570	70	45	⁄	⁄	ADJ
ajst-23570	70	46	exp	exp	NOUN
ajst-23570	70	47	tr	tr	VERB
ajst-23570	70	48	β	β	PROPN
ajst-23570	70	49	μ	μ	PROPN
ajst-23570	70	50	a	a	X
ajst-23570	70	51	β	β	PROPN
ajst-23570	70	52	μ	μ	PROPN
ajst-23570	70	53	,	,	PUNCT
ajst-23570	70	54	β	β	X
ajst-23570	70	55	∈	∈	PROPN
ajst-23570	70	56	r	r	NOUN
ajst-23570	70	57	,	,	PUNCT
ajst-23570	70	58	>	>	PUNCT
ajst-23570	70	59	0	0	NUM
ajst-23570	70	60	π	π	NOUN
ajst-23570	70	61	,	,	PUNCT
ajst-23570	70	62	,	,	PUNCT
ajst-23570	70	63	|	|	ADV
ajst-23570	70	64	|	|	ADV
ajst-23570	70	65	⁄	⁄	ADP
ajst-23570	70	66	exp	exp	NOUN
ajst-23570	70	67	trd	trd	NOUN
ajst-23570	70	68	,	,	PUNCT
ajst-23570	70	69	>	>	X
ajst-23570	70	70	0	0	PUNCT
ajst-23570	71	1	(	(	PUNCT
ajst-23570	71	2	16	16	NUM
ajst-23570	71	3	)	)	PUNCT
ajst-23570	71	4	where	where	SCONJ
ajst-23570	71	5	,	,	PUNCT
ajst-23570	71	6	,	,	PUNCT
ajst-23570	71	7	,	,	PUNCT
ajst-23570	71	8	,	,	PUNCT
ajst-23570	71	9	,	,	PUNCT
ajst-23570	71	10	are	be	AUX
ajst-23570	71	11	both	both	PRON
ajst-23570	71	12	regularization	regularization	NOUN
ajst-23570	71	13	constant	constant	ADJ
ajst-23570	71	14	factors	factor	NOUN
ajst-23570	71	15	,	,	PUNCT
ajst-23570	71	16	a	a	PRON
ajst-23570	71	17	is	be	AUX
ajst-23570	71	18	a	a	DET
ajst-23570	71	19	(	(	PUNCT
ajst-23570	71	20	k+1)×(k+1	k+1)×(k+1	NOUN
ajst-23570	71	21	)	)	PUNCT
ajst-23570	71	22	positive	positive	ADJ
ajst-23570	71	23	definite	definite	ADJ
ajst-23570	71	24	matrix	matrix	NOUN
ajst-23570	71	25	,	,	PUNCT
ajst-23570	71	26	μ	μ	PROPN
ajst-23570	71	27	is	be	AUX
ajst-23570	71	28	an	an	DET
ajst-23570	71	29	1	1	NUM
ajst-23570	71	30	m	m	NOUN
ajst-23570	71	31	matrix	matrix	NOUN
ajst-23570	71	32	,	,	PUNCT
ajst-23570	71	33	d	d	PRON
ajst-23570	71	34	is	be	AUX
ajst-23570	71	35	an	an	DET
ajst-23570	71	36	m	m	NOUN
ajst-23570	71	37	m	m	VERB
ajst-23570	71	38	positive	positive	ADJ
ajst-23570	71	39	definite	definite	ADJ
ajst-23570	71	40	matrix	matrix	NOUN
ajst-23570	71	41	,	,	PUNCT
ajst-23570	71	42	and	and	CCONJ
ajst-23570	71	43	,	,	PUNCT
ajst-23570	71	44	v	v	NOUN
ajst-23570	71	45	is	be	AUX
ajst-23570	71	46	a	a	DET
ajst-23570	71	47	positive	positive	ADJ
ajst-23570	71	48	integer	integer	NOUN
ajst-23570	71	49	greater	great	ADJ
ajst-23570	71	50	than	than	ADP
ajst-23570	71	51	m+1	m+1	PRON
ajst-23570	71	52	.	.	PUNCT
ajst-23570	72	1	at	at	ADP
ajst-23570	72	2	this	this	DET
ajst-23570	72	3	point	point	NOUN
ajst-23570	72	4	,	,	PUNCT
ajst-23570	72	5	the	the	DET
ajst-23570	72	6	problem	problem	NOUN
ajst-23570	72	7	of	of	ADP
ajst-23570	72	8	constructing	construct	VERB
ajst-23570	72	9	the	the	DET
ajst-23570	72	10	conjugate	conjugate	ADJ
ajst-23570	72	11	prior	prior	ADJ
ajst-23570	72	12	distribution	distribution	NOUN
ajst-23570	72	13	of	of	ADP
ajst-23570	72	14	the	the	DET
ajst-23570	72	15	parameters	parameter	NOUN
ajst-23570	72	16	of	of	ADP
ajst-23570	72	17	the	the	DET
ajst-23570	72	18	model	model	NOUN
ajst-23570	72	19	system	system	NOUN
ajst-23570	72	20	has	have	AUX
ajst-23570	72	21	been	be	AUX
ajst-23570	72	22	solved	solve	VERB
ajst-23570	72	23	,	,	PUNCT
ajst-23570	72	24	in	in	ADP
ajst-23570	72	25	the	the	DET
ajst-23570	72	26	following	following	NOUN
ajst-23570	72	27	,	,	PUNCT
ajst-23570	72	28	the	the	DET
ajst-23570	72	29	joint	joint	ADJ
ajst-23570	72	30	posterior	posterior	ADJ
ajst-23570	72	31	distribution	distribution	NOUN
ajst-23570	72	32	of	of	ADP
ajst-23570	72	33	the	the	DET
ajst-23570	72	34	coefficient	coefficient	NOUN
ajst-23570	72	35	matrix	matrix	NOUN
ajst-23570	72	36	β	β	X
ajst-23570	72	37	and	and	CCONJ
ajst-23570	72	38	the	the	DET
ajst-23570	72	39	precision	precision	NOUN
ajst-23570	72	40	matrix	matrix	NOUN
ajst-23570	72	41	is	be	AUX
ajst-23570	72	42	inferred	infer	VERB
ajst-23570	72	43	according	accord	VERB
ajst-23570	72	44	to	to	ADP
ajst-23570	72	45	bayes	bayes	PROPN
ajst-23570	72	46	theorem	theorem	VERB
ajst-23570	72	47	.	.	PUNCT
ajst-23570	73	1	in	in	ADP
ajst-23570	73	2	order	order	NOUN
ajst-23570	73	3	to	to	PART
ajst-23570	73	4	simplify	simplify	VERB
ajst-23570	73	5	the	the	DET
ajst-23570	73	6	derivation	derivation	NOUN
ajst-23570	73	7	process	process	NOUN
ajst-23570	73	8	of	of	ADP
ajst-23570	73	9	relevant	relevant	ADJ
ajst-23570	73	10	conclusions	conclusion	NOUN
ajst-23570	73	11	,	,	PUNCT
ajst-23570	73	12	the	the	DET
ajst-23570	73	13	following	follow	VERB
ajst-23570	73	14	two	two	NUM
ajst-23570	73	15	equations	equation	NOUN
ajst-23570	73	16	are	be	AUX
ajst-23570	73	17	proved	prove	VERB
ajst-23570	73	18	first	first	ADV
ajst-23570	73	19	.	.	PUNCT
ajst-23570	74	1	(	(	PUNCT
ajst-23570	74	2	1	1	X
ajst-23570	74	3	)	)	PUNCT
ajst-23570	74	4	note	note	NOUN
ajst-23570	74	5	μ	μ	NOUN
ajst-23570	74	6	c	c	PROPN
ajst-23570	74	7	c	c	PROPN
ajst-23570	74	8	≜	≜	NOUN
ajst-23570	74	9	μ	μ	PROPN
ajst-23570	74	10	β	β	X
ajst-23570	74	11	β	β	X
ajst-23570	74	12	s	s	PROPN
ajst-23570	74	13	μ	μ	PROPN
ajst-23570	74	14	β	β	X
ajst-23570	74	15	β	β	X
ajst-23570	74	16	than	than	ADP
ajst-23570	74	17	d	d	PROPN
ajst-23570	74	18	μ	μ	PROPN
ajst-23570	74	19	μ	μ	PROPN
ajst-23570	74	20	(	(	PUNCT
ajst-23570	74	21	17	17	NUM
ajst-23570	74	22	)	)	SYM
ajst-23570	74	23	2	2	NUM
ajst-23570	75	1	|	|	ADV
ajst-23570	75	2	|	|	ADV
ajst-23570	75	3	⁄	⁄	ADP
ajst-23570	75	4	tr	tr	NOUN
ajst-23570	75	5	c	c	PROPN
ajst-23570	75	6	∝	∝	PROPN
ajst-23570	75	7	⁄	⁄	PROPN
ajst-23570	75	8	(	(	PUNCT
ajst-23570	75	9	18	18	NUM
ajst-23570	75	10	)	)	PUNCT
ajst-23570	75	11	according	accord	VERB
ajst-23570	75	12	to	to	ADP
ajst-23570	75	13	the	the	DET
ajst-23570	75	14	bayes	bayes	PROPN
ajst-23570	75	15	theorem	theorem	VERB
ajst-23570	75	16	,	,	PUNCT
ajst-23570	75	17	the	the	DET
ajst-23570	75	18	density	density	NOUN
ajst-23570	75	19	function	function	NOUN
ajst-23570	75	20	of	of	ADP
ajst-23570	75	21	the	the	DET
ajst-23570	75	22	posterior	posterior	ADJ
ajst-23570	75	23	distribution	distribution	NOUN
ajst-23570	75	24	of	of	ADP
ajst-23570	75	25	the	the	DET
ajst-23570	75	26	parameters	parameter	NOUN
ajst-23570	75	27	is	be	AUX
ajst-23570	75	28	proportional	proportional	ADJ
ajst-23570	75	29	to	to	ADP
ajst-23570	75	30	the	the	DET
ajst-23570	75	31	product	product	NOUN
ajst-23570	75	32	of	of	ADP
ajst-23570	75	33	the	the	DET
ajst-23570	75	34	sample	sample	NOUN
ajst-23570	75	35	likelihood	likelihood	NOUN
ajst-23570	75	36	function	function	NOUN
ajst-23570	75	37	and	and	CCONJ
ajst-23570	75	38	the	the	DET
ajst-23570	75	39	density	density	NOUN
ajst-23570	75	40	function	function	NOUN
ajst-23570	75	41	of	of	ADP
ajst-23570	75	42	the	the	DET
ajst-23570	75	43	prior	prior	ADJ
ajst-23570	75	44	distribution	distribution	NOUN
ajst-23570	75	45	of	of	ADP
ajst-23570	75	46	the	the	DET
ajst-23570	75	47	parameters	parameter	NOUN
ajst-23570	75	48	,	,	PUNCT
ajst-23570	75	49	based	base	VERB
ajst-23570	75	50	on	on	ADP
ajst-23570	75	51	the	the	DET
ajst-23570	75	52	above	above	ADJ
ajst-23570	75	53	conclusions	conclusion	NOUN
ajst-23570	75	54	in	in	ADP
ajst-23570	75	55	equation	equation	NOUN
ajst-23570	75	56	(	(	PUNCT
ajst-23570	75	57	18	18	NUM
ajst-23570	75	58	)	)	PUNCT
ajst-23570	75	59	,	,	PUNCT
ajst-23570	75	60	the	the	DET
ajst-23570	75	61	density	density	NOUN
ajst-23570	75	62	function	function	NOUN
ajst-23570	75	63	of	of	ADP
ajst-23570	75	64	the	the	DET
ajst-23570	75	65	joint	joint	ADJ
ajst-23570	75	66	posterior	posterior	ADJ
ajst-23570	75	67	distribution	distribution	NOUN
ajst-23570	75	68	of	of	ADP
ajst-23570	75	69	the	the	DET
ajst-23570	75	70	coefficient	coefficient	NOUN
ajst-23570	75	71	matrix	matrix	NOUN
ajst-23570	75	72	β	β	X
ajst-23570	75	73	and	and	CCONJ
ajst-23570	75	74	the	the	DET
ajst-23570	75	75	precision	precision	NOUN
ajst-23570	75	76	matrix	matrix	NOUN
ajst-23570	75	77	under	under	ADP
ajst-23570	75	78	the	the	DET
ajst-23570	75	79	matrix	matrix	NOUN
ajst-23570	75	80	normal	normal	ADJ
ajst-23570	75	81	wishart	wishart	NOUN
ajst-23570	75	82	conjugate	conjugate	VERB
ajst-23570	75	83	prior	prior	ADJ
ajst-23570	75	84	distribution	distribution	NOUN
ajst-23570	75	85	in	in	ADP
ajst-23570	75	86	the	the	DET
ajst-23570	75	87	form	form	NOUN
ajst-23570	75	88	of	of	ADP
ajst-23570	75	89	equation	equation	NOUN
ajst-23570	75	90	(	(	PUNCT
ajst-23570	75	91	15	15	NUM
ajst-23570	75	92	)	)	PUNCT
ajst-23570	75	93	is	be	AUX
ajst-23570	75	94	π	π	PROPN
ajst-23570	75	95	,	,	PUNCT
ajst-23570	75	96	|y	|y	NOUN
ajst-23570	75	97	,	,	PUNCT
ajst-23570	75	98	x	x	SYM
ajst-23570	75	99	∝	∝	PROPN
ajst-23570	75	100	π	π	PROPN
ajst-23570	75	101	,	,	PUNCT
ajst-23570	75	102	|y	|y	NOUN
ajst-23570	75	103	,	,	PUNCT
ajst-23570	75	104	x	x	SYM
ajst-23570	75	105	∝	∝	PROPN
ajst-23570	76	1	|	|	ADV
ajst-23570	76	2	|	|	ADV
ajst-23570	76	3	⁄	⁄	ADP
ajst-23570	76	4	exp	exp	NOUN
ajst-23570	76	5	tr	tr	PROPN
ajst-23570	76	6	d	d	PROPN
ajst-23570	76	7	β	β	PROPN
ajst-23570	76	8	μ	μ	PROPN
ajst-23570	76	9	a	a	PRON
ajst-23570	76	10	β	β	PROPN
ajst-23570	76	11	μ	μ	PROPN
ajst-23570	76	12	y	y	PROPN
ajst-23570	76	13	xβ	xβ	PROPN
ajst-23570	76	14	y	y	PROPN
ajst-23570	76	15	xβ	xβ	PROPN
ajst-23570	76	16	∝	∝	PROPN
ajst-23570	77	1	|	|	ADV
ajst-23570	77	2	|	|	ADV
ajst-23570	77	3	⁄	⁄	ADJ
ajst-23570	77	4	exp	exp	NOUN
ajst-23570	77	5	tr	tr	NOUN
ajst-23570	77	6	c	c	PROPN
ajst-23570	77	7	(	(	PUNCT
ajst-23570	77	8	19	19	NUM
ajst-23570	77	9	)	)	PUNCT
ajst-23570	77	10	obviously	obviously	ADV
ajst-23570	77	11	,	,	PUNCT
ajst-23570	77	12	the	the	DET
ajst-23570	77	13	joint	joint	ADJ
ajst-23570	77	14	posterior	posterior	ADJ
ajst-23570	77	15	distribution	distribution	NOUN
ajst-23570	77	16	of	of	ADP
ajst-23570	77	17	the	the	DET
ajst-23570	77	18	coefficient	coefficient	NOUN
ajst-23570	77	19	matrix	matrix	NOUN
ajst-23570	77	20	β	β	X
ajst-23570	77	21	and	and	CCONJ
ajst-23570	77	22	the	the	DET
ajst-23570	77	23	precision	precision	NOUN
ajst-23570	77	24	matrix	matrix	NOUN
ajst-23570	77	25	is	be	AUX
ajst-23570	77	26	still	still	ADV
ajst-23570	77	27	the	the	DET
ajst-23570	77	28	matrix	matrix	NOUN
ajst-23570	77	29	normal	normal	ADJ
ajst-23570	77	30	-	-	PUNCT
ajst-23570	77	31	wishart	wishart	NOUN
ajst-23570	77	32	distribution	distribution	NOUN
ajst-23570	77	33	,	,	PUNCT
ajst-23570	77	34	but	but	CCONJ
ajst-23570	77	35	its	its	PRON
ajst-23570	77	36	distribution	distribution	NOUN
ajst-23570	77	37	parameters	parameter	NOUN
ajst-23570	77	38	are	be	AUX
ajst-23570	77	39	different	different	ADJ
ajst-23570	77	40	from	from	ADP
ajst-23570	77	41	the	the	DET
ajst-23570	77	42	prior	prior	ADJ
ajst-23570	77	43	distribution	distribution	NOUN
ajst-23570	77	44	.	.	PUNCT
ajst-23570	78	1	3	3	X
ajst-23570	78	2	.	.	X
ajst-23570	78	3	expansion	expansion	NOUN
ajst-23570	78	4	and	and	CCONJ
ajst-23570	78	5	application	application	NOUN
ajst-23570	78	6	3.1	3.1	NUM
ajst-23570	78	7	.	.	PUNCT
ajst-23570	78	8	application	application	NOUN
ajst-23570	78	9	of	of	ADP
ajst-23570	78	10	bayesian	bayesian	NOUN
ajst-23570	78	11	methods	method	NOUN
ajst-23570	78	12	to	to	ADP
ajst-23570	78	13	other	other	ADJ
ajst-23570	78	14	regression	regression	NOUN
ajst-23570	78	15	problems	problem	NOUN
ajst-23570	78	16	bayesian	bayesian	NOUN
ajst-23570	78	17	methods	method	NOUN
ajst-23570	78	18	have	have	AUX
ajst-23570	78	19	been	be	AUX
ajst-23570	78	20	widely	widely	ADV
ajst-23570	78	21	used	use	VERB
ajst-23570	78	22	in	in	ADP
ajst-23570	78	23	many	many	ADJ
ajst-23570	78	24	regression	regression	NOUN
ajst-23570	78	25	problems	problem	NOUN
ajst-23570	78	26	,	,	PUNCT
ajst-23570	78	27	not	not	PART
ajst-23570	78	28	limited	limit	VERB
ajst-23570	78	29	to	to	AUX
ajst-23570	78	30	linear	linear	VERB
ajst-23570	78	31	regression	regression	NOUN
ajst-23570	78	32	.	.	PUNCT
ajst-23570	79	1	for	for	ADP
ajst-23570	79	2	example	example	NOUN
ajst-23570	79	3	,	,	PUNCT
ajst-23570	79	4	in	in	ADP
ajst-23570	79	5	polynomial	polynomial	ADJ
ajst-23570	79	6	regression	regression	NOUN
ajst-23570	79	7	,	,	PUNCT
ajst-23570	79	8	bayesian	bayesian	NOUN
ajst-23570	79	9	methods	method	NOUN
ajst-23570	79	10	can	can	AUX
ajst-23570	79	11	better	well	ADV
ajst-23570	79	12	capture	capture	VERB
ajst-23570	79	13	the	the	DET
ajst-23570	79	14	nonlinear	nonlinear	ADJ
ajst-23570	79	15	features	feature	NOUN
ajst-23570	79	16	of	of	ADP
ajst-23570	79	17	the	the	DET
ajst-23570	79	18	data	datum	NOUN
ajst-23570	79	19	by	by	ADP
ajst-23570	79	20	modeling	model	VERB
ajst-23570	79	21	higher	high	ADJ
ajst-23570	79	22	-	-	PUNCT
ajst-23570	79	23	order	order	NOUN
ajst-23570	79	24	terms	term	NOUN
ajst-23570	79	25	.	.	PUNCT
ajst-23570	80	1	in	in	ADP
ajst-23570	80	2	addition	addition	NOUN
ajst-23570	80	3	,	,	PUNCT
ajst-23570	80	4	bayesian	bayesian	NOUN
ajst-23570	80	5	methods	method	NOUN
ajst-23570	80	6	have	have	AUX
ajst-23570	80	7	also	also	ADV
ajst-23570	80	8	been	be	AUX
ajst-23570	80	9	applied	apply	VERB
ajst-23570	80	10	in	in	ADP
ajst-23570	80	11	nonlinear	nonlinear	ADJ
ajst-23570	80	12	autoregressive	autoregressive	ADJ
ajst-23570	80	13	models	model	NOUN
ajst-23570	80	14	,	,	PUNCT
ajst-23570	80	15	such	such	ADJ
ajst-23570	80	16	as	as	ADP
ajst-23570	80	17	arma	arma	NOUN
ajst-23570	80	18	models	model	NOUN
ajst-23570	80	19	,	,	PUNCT
ajst-23570	80	20	to	to	PART
ajst-23570	80	21	capture	capture	VERB
ajst-23570	80	22	nonlinear	nonlinear	ADJ
ajst-23570	80	23	dynamics	dynamic	NOUN
ajst-23570	80	24	in	in	ADP
ajst-23570	80	25	time	time	NOUN
ajst-23570	80	26	series	series	PROPN
ajst-23570	80	27	data	data	PROPN
ajst-23570	80	28	.	.	PUNCT
ajst-23570	81	1	in	in	ADP
ajst-23570	81	2	the	the	DET
ajst-23570	81	3	classification	classification	NOUN
ajst-23570	81	4	regression	regression	NOUN
ajst-23570	81	5	problem	problem	NOUN
ajst-23570	81	6	,	,	PUNCT
ajst-23570	81	7	the	the	DET
ajst-23570	81	8	bayesian	bayesian	NOUN
ajst-23570	81	9	method	method	NOUN
ajst-23570	81	10	has	have	AUX
ajst-23570	81	11	also	also	ADV
ajst-23570	81	12	been	be	AUX
ajst-23570	81	13	applied	apply	VERB
ajst-23570	81	14	,	,	PUNCT
ajst-23570	81	15	which	which	PRON
ajst-23570	81	16	can	can	AUX
ajst-23570	81	17	better	well	ADV
ajst-23570	81	18	capture	capture	VERB
ajst-23570	81	19	the	the	DET
ajst-23570	81	20	classification	classification	NOUN
ajst-23570	81	21	pattern	pattern	NOUN
ajst-23570	81	22	of	of	ADP
ajst-23570	81	23	the	the	DET
ajst-23570	81	24	data	datum	NOUN
ajst-23570	81	25	by	by	ADP
ajst-23570	81	26	transforming	transform	VERB
ajst-23570	81	27	the	the	DET
ajst-23570	81	28	classification	classification	NOUN
ajst-23570	81	29	target	target	NOUN
ajst-23570	81	30	into	into	ADP
ajst-23570	81	31	a	a	DET
ajst-23570	81	32	continuous	continuous	ADJ
ajst-23570	81	33	variable	variable	NOUN
ajst-23570	81	34	and	and	CCONJ
ajst-23570	81	35	using	use	VERB
ajst-23570	81	36	the	the	DET
ajst-23570	81	37	bayesian	bayesian	NOUN
ajst-23570	81	38	method	method	NOUN
ajst-23570	81	39	for	for	ADP
ajst-23570	81	40	modeling	modeling	NOUN
ajst-23570	81	41	.	.	PUNCT
ajst-23570	82	1	109	109	NUM
ajst-23570	82	2	3.2	3.2	NUM
ajst-23570	82	3	.	.	PUNCT
ajst-23570	82	4	limitations	limitation	NOUN
ajst-23570	82	5	and	and	CCONJ
ajst-23570	82	6	improvement	improvement	NOUN
ajst-23570	82	7	directions	direction	NOUN
ajst-23570	82	8	of	of	ADP
ajst-23570	82	9	bayesian	bayesian	NOUN
ajst-23570	82	10	methods	method	NOUN
ajst-23570	82	11	in	in	ADP
ajst-23570	82	12	practice	practice	NOUN
ajst-23570	82	13	despite	despite	SCONJ
ajst-23570	82	14	the	the	DET
ajst-23570	82	15	remarkable	remarkable	ADJ
ajst-23570	82	16	success	success	NOUN
ajst-23570	82	17	of	of	ADP
ajst-23570	82	18	the	the	DET
ajst-23570	82	19	bayesian	bayesian	NOUN
ajst-23570	82	20	approach	approach	NOUN
ajst-23570	82	21	in	in	ADP
ajst-23570	82	22	many	many	ADJ
ajst-23570	82	23	regression	regression	NOUN
ajst-23570	82	24	problems	problem	NOUN
ajst-23570	82	25	,	,	PUNCT
ajst-23570	82	26	there	there	PRON
ajst-23570	82	27	are	be	VERB
ajst-23570	82	28	some	some	DET
ajst-23570	82	29	limitations	limitation	NOUN
ajst-23570	82	30	in	in	ADP
ajst-23570	82	31	practice	practice	NOUN
ajst-23570	82	32	.	.	PUNCT
ajst-23570	83	1	firstly	firstly	ADV
ajst-23570	83	2	,	,	PUNCT
ajst-23570	83	3	bayesian	bayesian	NOUN
ajst-23570	83	4	methods	method	NOUN
ajst-23570	83	5	typically	typically	ADV
ajst-23570	83	6	require	require	VERB
ajst-23570	83	7	large	large	ADJ
ajst-23570	83	8	amounts	amount	NOUN
ajst-23570	83	9	of	of	ADP
ajst-23570	83	10	data	datum	NOUN
ajst-23570	83	11	and	and	CCONJ
ajst-23570	83	12	computational	computational	ADJ
ajst-23570	83	13	resources	resource	NOUN
ajst-23570	83	14	for	for	ADP
ajst-23570	83	15	modeling	modeling	NOUN
ajst-23570	83	16	,	,	PUNCT
ajst-23570	83	17	which	which	PRON
ajst-23570	83	18	may	may	AUX
ajst-23570	83	19	limit	limit	VERB
ajst-23570	83	20	their	their	PRON
ajst-23570	83	21	application	application	NOUN
ajst-23570	83	22	when	when	SCONJ
ajst-23570	83	23	data	datum	NOUN
ajst-23570	83	24	is	be	AUX
ajst-23570	83	25	scarce	scarce	ADJ
ajst-23570	83	26	.	.	PUNCT
ajst-23570	84	1	secondly	secondly	ADV
ajst-23570	84	2	,	,	PUNCT
ajst-23570	84	3	the	the	DET
ajst-23570	84	4	high	high	ADJ
ajst-23570	84	5	sensitivity	sensitivity	NOUN
ajst-23570	84	6	of	of	ADP
ajst-23570	84	7	the	the	DET
ajst-23570	84	8	bayesian	bayesian	NOUN
ajst-23570	84	9	approach	approach	NOUN
ajst-23570	84	10	to	to	ADP
ajst-23570	84	11	model	model	NOUN
ajst-23570	84	12	selection	selection	NOUN
ajst-23570	84	13	may	may	AUX
ajst-23570	84	14	lead	lead	VERB
ajst-23570	84	15	to	to	ADP
ajst-23570	84	16	the	the	DET
ajst-23570	84	17	problem	problem	NOUN
ajst-23570	84	18	of	of	ADP
ajst-23570	84	19	overfitting	overfitting	NOUN
ajst-23570	84	20	or	or	CCONJ
ajst-23570	84	21	underfitting	underfitting	NOUN
ajst-23570	84	22	.	.	PUNCT
ajst-23570	85	1	in	in	ADP
ajst-23570	85	2	order	order	NOUN
ajst-23570	85	3	to	to	PART
ajst-23570	85	4	solve	solve	VERB
ajst-23570	85	5	these	these	DET
ajst-23570	85	6	problems	problem	NOUN
ajst-23570	85	7	,	,	PUNCT
ajst-23570	85	8	the	the	DET
ajst-23570	85	9	following	follow	VERB
ajst-23570	85	10	improvement	improvement	NOUN
ajst-23570	85	11	directions	direction	NOUN
ajst-23570	85	12	can	can	AUX
ajst-23570	85	13	be	be	AUX
ajst-23570	85	14	considered	consider	VERB
ajst-23570	85	15	:	:	PUNCT
ajst-23570	85	16	(	(	PUNCT
ajst-23570	85	17	1	1	X
ajst-23570	85	18	)	)	PUNCT
ajst-23570	85	19	efficient	efficient	ADJ
ajst-23570	85	20	algorithms	algorithm	NOUN
ajst-23570	85	21	:	:	PUNCT
ajst-23570	85	22	more	more	ADV
ajst-23570	85	23	efficient	efficient	ADJ
ajst-23570	85	24	bayesian	bayesian	NOUN
ajst-23570	85	25	method	method	NOUN
ajst-23570	85	26	algorithms	algorithm	NOUN
ajst-23570	85	27	are	be	AUX
ajst-23570	85	28	investigated	investigate	VERB
ajst-23570	85	29	to	to	PART
ajst-23570	85	30	reduce	reduce	VERB
ajst-23570	85	31	computational	computational	ADJ
ajst-23570	85	32	time	time	NOUN
ajst-23570	85	33	and	and	CCONJ
ajst-23570	85	34	resource	resource	NOUN
ajst-23570	85	35	requirements	requirement	NOUN
ajst-23570	85	36	.	.	PUNCT
ajst-23570	86	1	(	(	PUNCT
ajst-23570	86	2	2	2	X
ajst-23570	86	3	)	)	PUNCT
ajst-23570	86	4	model	model	NOUN
ajst-23570	86	5	selection	selection	NOUN
ajst-23570	86	6	and	and	CCONJ
ajst-23570	86	7	tuning	tuning	NOUN
ajst-23570	86	8	:	:	PUNCT
ajst-23570	86	9	by	by	ADP
ajst-23570	86	10	introducing	introduce	VERB
ajst-23570	86	11	more	more	ADV
ajst-23570	86	12	sophisticated	sophisticated	ADJ
ajst-23570	86	13	model	model	NOUN
ajst-23570	86	14	selection	selection	NOUN
ajst-23570	86	15	and	and	CCONJ
ajst-23570	86	16	tuning	tune	VERB
ajst-23570	86	17	techniques	technique	NOUN
ajst-23570	86	18	,	,	PUNCT
ajst-23570	86	19	such	such	ADJ
ajst-23570	86	20	as	as	ADP
ajst-23570	86	21	hyperparameter	hyperparameter	NOUN
ajst-23570	86	22	optimization	optimization	NOUN
ajst-23570	86	23	and	and	CCONJ
ajst-23570	86	24	bayesian	bayesian	NOUN
ajst-23570	86	25	inference	inference	NOUN
ajst-23570	86	26	,	,	PUNCT
ajst-23570	86	27	to	to	PART
ajst-23570	86	28	improve	improve	VERB
ajst-23570	86	29	the	the	DET
ajst-23570	86	30	generalization	generalization	NOUN
ajst-23570	86	31	ability	ability	NOUN
ajst-23570	86	32	of	of	ADP
ajst-23570	86	33	bayesian	bayesian	NOUN
ajst-23570	86	34	methods	method	NOUN
ajst-23570	86	35	.	.	PUNCT
ajst-23570	87	1	(	(	PUNCT
ajst-23570	87	2	3	3	X
ajst-23570	87	3	)	)	PUNCT
ajst-23570	87	4	combining	combine	VERB
ajst-23570	87	5	other	other	ADJ
ajst-23570	87	6	methods	method	NOUN
ajst-23570	87	7	:	:	PUNCT
ajst-23570	87	8	bayesian	bayesian	NOUN
ajst-23570	87	9	methods	method	NOUN
ajst-23570	87	10	are	be	AUX
ajst-23570	87	11	combined	combine	VERB
ajst-23570	87	12	with	with	ADP
ajst-23570	87	13	other	other	ADJ
ajst-23570	87	14	statistical	statistical	ADJ
ajst-23570	87	15	or	or	CCONJ
ajst-23570	87	16	machine	machine	NOUN
ajst-23570	87	17	learning	learning	NOUN
ajst-23570	87	18	methods	method	NOUN
ajst-23570	87	19	,	,	PUNCT
ajst-23570	87	20	such	such	ADJ
ajst-23570	87	21	as	as	ADP
ajst-23570	87	22	random	random	ADJ
ajst-23570	87	23	forest	forest	NOUN
ajst-23570	87	24	,	,	PUNCT
ajst-23570	87	25	gradient	gradient	NOUN
ajst-23570	87	26	boosting	boosting	NOUN
ajst-23570	87	27	,	,	PUNCT
ajst-23570	87	28	etc	etc	X
ajst-23570	87	29	.	.	X
ajst-23570	87	30	,	,	PUNCT
ajst-23570	87	31	for	for	ADP
ajst-23570	87	32	more	more	ADV
ajst-23570	87	33	comprehensive	comprehensive	ADJ
ajst-23570	87	34	data	datum	NOUN
ajst-23570	87	35	interpretation	interpretation	NOUN
ajst-23570	87	36	and	and	CCONJ
ajst-23570	87	37	prediction	prediction	NOUN
ajst-23570	87	38	capabilities	capability	NOUN
ajst-23570	87	39	(	(	PUNCT
ajst-23570	87	40	4	4	X
ajst-23570	87	41	)	)	PUNCT
ajst-23570	87	42	consider	consider	VERB
ajst-23570	87	43	prior	prior	ADJ
ajst-23570	87	44	knowledge	knowledge	NOUN
ajst-23570	87	45	:	:	PUNCT
ajst-23570	87	46	in	in	ADP
ajst-23570	87	47	practice	practice	NOUN
ajst-23570	87	48	,	,	PUNCT
ajst-23570	87	49	domain	domain	NOUN
ajst-23570	87	50	knowledge	knowledge	NOUN
ajst-23570	87	51	and	and	CCONJ
ajst-23570	87	52	prior	prior	ADJ
ajst-23570	87	53	information	information	NOUN
ajst-23570	87	54	can	can	AUX
ajst-23570	87	55	be	be	AUX
ajst-23570	87	56	combined	combine	VERB
ajst-23570	87	57	to	to	PART
ajst-23570	87	58	select	select	VERB
ajst-23570	87	59	an	an	DET
ajst-23570	87	60	appropriate	appropriate	ADJ
ajst-23570	87	61	prior	prior	ADJ
ajst-23570	87	62	distribution	distribution	NOUN
ajst-23570	87	63	to	to	PART
ajst-23570	87	64	improve	improve	VERB
ajst-23570	87	65	the	the	DET
ajst-23570	87	66	prediction	prediction	NOUN
ajst-23570	87	67	accuracy	accuracy	NOUN
ajst-23570	87	68	and	and	CCONJ
ajst-23570	87	69	interpretation	interpretation	NOUN
ajst-23570	87	70	of	of	ADP
ajst-23570	87	71	the	the	DET
ajst-23570	87	72	model	model	NOUN
ajst-23570	87	73	.	.	PUNCT
ajst-23570	88	1	although	although	SCONJ
ajst-23570	88	2	the	the	DET
ajst-23570	88	3	bayesian	bayesian	NOUN
ajst-23570	88	4	method	method	NOUN
ajst-23570	88	5	has	have	VERB
ajst-23570	88	6	some	some	DET
ajst-23570	88	7	limitations	limitation	NOUN
ajst-23570	88	8	in	in	ADP
ajst-23570	88	9	practice	practice	NOUN
ajst-23570	88	10	,	,	PUNCT
ajst-23570	88	11	through	through	ADP
ajst-23570	88	12	continuous	continuous	ADJ
ajst-23570	88	13	research	research	NOUN
ajst-23570	88	14	and	and	CCONJ
ajst-23570	88	15	improvement	improvement	NOUN
ajst-23570	88	16	,	,	PUNCT
ajst-23570	88	17	it	it	PRON
ajst-23570	88	18	can	can	AUX
ajst-23570	88	19	be	be	AUX
ajst-23570	88	20	applied	apply	VERB
ajst-23570	88	21	to	to	ADP
ajst-23570	88	22	more	more	ADJ
ajst-23570	88	23	regression	regression	NOUN
ajst-23570	88	24	problems	problem	NOUN
ajst-23570	88	25	and	and	CCONJ
ajst-23570	88	26	further	far	ADV
ajst-23570	88	27	improve	improve	VERB
ajst-23570	88	28	the	the	DET
ajst-23570	88	29	prediction	prediction	NOUN
ajst-23570	88	30	accuracy	accuracy	NOUN
ajst-23570	88	31	and	and	CCONJ
ajst-23570	88	32	generalization	generalization	NOUN
ajst-23570	88	33	ability	ability	NOUN
ajst-23570	88	34	of	of	ADP
ajst-23570	88	35	the	the	DET
ajst-23570	88	36	model	model	NOUN
ajst-23570	88	37	.	.	PUNCT
ajst-23570	89	1	4	4	X
ajst-23570	89	2	.	.	NOUN
ajst-23570	89	3	conclusion	conclusion	NOUN
ajst-23570	89	4	and	and	CCONJ
ajst-23570	89	5	prospects	prospect	NOUN
ajst-23570	89	6	4.1	4.1	NUM
ajst-23570	89	7	.	.	PUNCT
ajst-23570	90	1	summary	summary	NOUN
ajst-23570	90	2	of	of	ADP
ajst-23570	90	3	key	key	ADJ
ajst-23570	90	4	research	research	NOUN
ajst-23570	90	5	findings	finding	NOUN
ajst-23570	90	6	in	in	ADP
ajst-23570	90	7	this	this	DET
ajst-23570	90	8	study	study	NOUN
ajst-23570	90	9	,	,	PUNCT
ajst-23570	90	10	the	the	DET
ajst-23570	90	11	application	application	NOUN
ajst-23570	90	12	of	of	ADP
ajst-23570	90	13	bayesian	bayesian	NOUN
ajst-23570	90	14	methods	method	NOUN
ajst-23570	90	15	to	to	PART
ajst-23570	90	16	linear	linear	VERB
ajst-23570	90	17	regression	regression	NOUN
ajst-23570	90	18	was	be	AUX
ajst-23570	90	19	explored	explore	VERB
ajst-23570	90	20	.	.	PUNCT
ajst-23570	91	1	by	by	ADP
ajst-23570	91	2	comparing	compare	VERB
ajst-23570	91	3	the	the	DET
ajst-23570	91	4	two	two	NUM
ajst-23570	91	5	methods	method	NOUN
ajst-23570	91	6	of	of	ADP
ajst-23570	91	7	frequency	frequency	NOUN
ajst-23570	91	8	linear	linear	ADJ
ajst-23570	91	9	regression	regression	NOUN
ajst-23570	91	10	and	and	CCONJ
ajst-23570	91	11	bayesian	bayesian	NOUN
ajst-23570	91	12	linear	linear	PROPN
ajst-23570	91	13	regression	regression	NOUN
ajst-23570	91	14	,	,	PUNCT
ajst-23570	91	15	it	it	PRON
ajst-23570	91	16	is	be	AUX
ajst-23570	91	17	found	find	VERB
ajst-23570	91	18	that	that	SCONJ
ajst-23570	91	19	the	the	DET
ajst-23570	91	20	bayesian	bayesian	NOUN
ajst-23570	91	21	linear	linear	PROPN
ajst-23570	91	22	regression	regression	NOUN
ajst-23570	91	23	has	have	VERB
ajst-23570	91	24	the	the	DET
ajst-23570	91	25	following	following	ADJ
ajst-23570	91	26	advantages	advantage	NOUN
ajst-23570	91	27	and	and	CCONJ
ajst-23570	91	28	characteristics	characteristic	NOUN
ajst-23570	91	29	:	:	PUNCT
ajst-23570	91	30	bayesian	bayesian	NOUN
ajst-23570	91	31	linear	linear	ADJ
ajst-23570	91	32	regression	regression	NOUN
ajst-23570	91	33	can	can	AUX
ajst-23570	91	34	provide	provide	VERB
ajst-23570	91	35	the	the	DET
ajst-23570	91	36	probability	probability	NOUN
ajst-23570	91	37	distribution	distribution	NOUN
ajst-23570	91	38	of	of	ADP
ajst-23570	91	39	output	output	NOUN
ajst-23570	91	40	,	,	PUNCT
ajst-23570	91	41	rather	rather	ADV
ajst-23570	91	42	than	than	ADP
ajst-23570	91	43	just	just	ADV
ajst-23570	91	44	a	a	DET
ajst-23570	91	45	single	single	ADJ
ajst-23570	91	46	point	point	NOUN
ajst-23570	91	47	estimate	estimate	NOUN
ajst-23570	91	48	,	,	PUNCT
ajst-23570	91	49	which	which	PRON
ajst-23570	91	50	is	be	AUX
ajst-23570	91	51	particularly	particularly	ADV
ajst-23570	91	52	important	important	ADJ
ajst-23570	91	53	for	for	ADP
ajst-23570	91	54	small	small	ADJ
ajst-23570	91	55	sample	sample	NOUN
ajst-23570	91	56	data	datum	NOUN
ajst-23570	91	57	sets	set	NOUN
ajst-23570	91	58	;	;	PUNCT
ajst-23570	91	59	bayesian	bayesian	NOUN
ajst-23570	91	60	method	method	NOUN
ajst-23570	91	61	can	can	AUX
ajst-23570	91	62	introduce	introduce	VERB
ajst-23570	91	63	prior	prior	ADJ
ajst-23570	91	64	knowledge	knowledge	NOUN
ajst-23570	91	65	to	to	PART
ajst-23570	91	66	improve	improve	VERB
ajst-23570	91	67	the	the	DET
ajst-23570	91	68	robustness	robustness	NOUN
ajst-23570	91	69	and	and	CCONJ
ajst-23570	91	70	generalization	generalization	NOUN
ajst-23570	91	71	ability	ability	NOUN
ajst-23570	91	72	of	of	ADP
ajst-23570	91	73	the	the	DET
ajst-23570	91	74	model	model	NOUN
ajst-23570	91	75	.	.	PUNCT
ajst-23570	92	1	bayesian	bayesian	NOUN
ajst-23570	92	2	linear	linear	PROPN
ajst-23570	92	3	regression	regression	NOUN
ajst-23570	92	4	can	can	AUX
ajst-23570	92	5	handle	handle	VERB
ajst-23570	92	6	noise	noise	NOUN
ajst-23570	92	7	and	and	CCONJ
ajst-23570	92	8	uncertainty	uncertainty	NOUN
ajst-23570	92	9	better	well	ADV
ajst-23570	92	10	by	by	ADP
ajst-23570	92	11	using	use	VERB
ajst-23570	92	12	bayesian	bayesian	NOUN
ajst-23570	92	13	inference	inference	NOUN
ajst-23570	92	14	methods	method	NOUN
ajst-23570	92	15	for	for	ADP
ajst-23570	92	16	parameter	parameter	NOUN
ajst-23570	92	17	estimation	estimation	NOUN
ajst-23570	92	18	.	.	PUNCT
ajst-23570	93	1	4.2	4.2	NUM
ajst-23570	93	2	.	.	PUNCT
ajst-23570	93	3	research	research	NOUN
ajst-23570	93	4	limitations	limitation	NOUN
ajst-23570	93	5	and	and	CCONJ
ajst-23570	93	6	deficiencies	deficiency	NOUN
ajst-23570	93	7	although	although	SCONJ
ajst-23570	93	8	the	the	DET
ajst-23570	93	9	bayesian	bayesian	NOUN
ajst-23570	93	10	linear	linear	NOUN
ajst-23570	93	11	regression	regression	NOUN
ajst-23570	93	12	method	method	NOUN
ajst-23570	93	13	has	have	VERB
ajst-23570	93	14	advantages	advantage	NOUN
ajst-23570	93	15	in	in	ADP
ajst-23570	93	16	many	many	ADJ
ajst-23570	93	17	aspects	aspect	NOUN
ajst-23570	93	18	,	,	PUNCT
ajst-23570	93	19	it	it	PRON
ajst-23570	93	20	also	also	ADV
ajst-23570	93	21	has	have	VERB
ajst-23570	93	22	some	some	DET
ajst-23570	93	23	limitations	limitation	NOUN
ajst-23570	93	24	and	and	CCONJ
ajst-23570	93	25	shortcomings	shortcoming	NOUN
ajst-23570	93	26	:	:	PUNCT
ajst-23570	93	27	(	(	PUNCT
ajst-23570	93	28	1	1	X
ajst-23570	93	29	)	)	PUNCT
ajst-23570	93	30	the	the	DET
ajst-23570	93	31	computational	computational	ADJ
ajst-23570	93	32	complexity	complexity	NOUN
ajst-23570	93	33	of	of	ADP
ajst-23570	93	34	bayesian	bayesian	NOUN
ajst-23570	93	35	methods	method	NOUN
ajst-23570	93	36	is	be	AUX
ajst-23570	93	37	high	high	ADJ
ajst-23570	93	38	,	,	PUNCT
ajst-23570	93	39	especially	especially	ADV
ajst-23570	93	40	when	when	SCONJ
ajst-23570	93	41	dealing	deal	VERB
ajst-23570	93	42	with	with	ADP
ajst-23570	93	43	large	large	ADJ
ajst-23570	93	44	-	-	PUNCT
ajst-23570	93	45	scale	scale	NOUN
ajst-23570	93	46	data	datum	NOUN
ajst-23570	93	47	sets	set	NOUN
ajst-23570	93	48	.	.	PUNCT
ajst-23570	94	1	(	(	PUNCT
ajst-23570	94	2	2	2	X
ajst-23570	94	3	)	)	PUNCT
ajst-23570	94	4	bayesian	bayesian	NOUN
ajst-23570	94	5	linear	linear	ADJ
ajst-23570	94	6	regression	regression	NOUN
ajst-23570	94	7	requires	require	VERB
ajst-23570	94	8	the	the	DET
ajst-23570	94	9	selection	selection	NOUN
ajst-23570	94	10	of	of	ADP
ajst-23570	94	11	an	an	DET
ajst-23570	94	12	appropriate	appropriate	ADJ
ajst-23570	94	13	prior	prior	ADJ
ajst-23570	94	14	distribution	distribution	NOUN
ajst-23570	94	15	,	,	PUNCT
ajst-23570	94	16	which	which	PRON
ajst-23570	94	17	can	can	AUX
ajst-23570	94	18	be	be	AUX
ajst-23570	94	19	challenging	challenge	VERB
ajst-23570	94	20	for	for	ADP
ajst-23570	94	21	researchers	researcher	NOUN
ajst-23570	94	22	unfamiliar	unfamiliar	ADJ
ajst-23570	94	23	with	with	ADP
ajst-23570	94	24	bayesian	bayesian	NOUN
ajst-23570	94	25	statistics	statistic	NOUN
ajst-23570	94	26	.	.	PUNCT
ajst-23570	95	1	(	(	PUNCT
ajst-23570	95	2	3	3	X
ajst-23570	95	3	)	)	PUNCT
ajst-23570	95	4	bayesian	bayesian	NOUN
ajst-23570	95	5	method	method	NOUN
ajst-23570	95	6	requires	require	VERB
ajst-23570	95	7	more	more	ADJ
ajst-23570	95	8	subjective	subjective	ADJ
ajst-23570	95	9	judgment	judgment	NOUN
ajst-23570	95	10	and	and	CCONJ
ajst-23570	95	11	domain	domain	NOUN
ajst-23570	95	12	knowledge	knowledge	NOUN
ajst-23570	95	13	for	for	ADP
ajst-23570	95	14	model	model	NOUN
ajst-23570	95	15	selection	selection	NOUN
ajst-23570	95	16	and	and	CCONJ
ajst-23570	95	17	parameter	parameter	NOUN
ajst-23570	95	18	adjustment	adjustment	NOUN
ajst-23570	95	19	4.3	4.3	NUM
ajst-23570	95	20	.	.	PUNCT
ajst-23570	96	1	suggestions	suggestion	NOUN
ajst-23570	96	2	for	for	ADP
ajst-23570	96	3	future	future	ADJ
ajst-23570	96	4	research	research	NOUN
ajst-23570	96	5	directions	direction	NOUN
ajst-23570	96	6	in	in	ADP
ajst-23570	96	7	view	view	NOUN
ajst-23570	96	8	of	of	ADP
ajst-23570	96	9	the	the	DET
ajst-23570	96	10	limitations	limitation	NOUN
ajst-23570	96	11	and	and	CCONJ
ajst-23570	96	12	shortcomings	shortcoming	NOUN
ajst-23570	96	13	of	of	ADP
ajst-23570	96	14	the	the	DET
ajst-23570	96	15	above	above	ADJ
ajst-23570	96	16	research	research	NOUN
ajst-23570	96	17	,	,	PUNCT
ajst-23570	96	18	the	the	DET
ajst-23570	96	19	following	follow	VERB
ajst-23570	96	20	research	research	NOUN
ajst-23570	96	21	directions	direction	NOUN
ajst-23570	96	22	and	and	CCONJ
ajst-23570	96	23	suggestions	suggestion	NOUN
ajst-23570	96	24	are	be	AUX
ajst-23570	96	25	proposed	propose	VERB
ajst-23570	96	26	:	:	PUNCT
ajst-23570	96	27	(	(	PUNCT
ajst-23570	96	28	1	1	X
ajst-23570	96	29	)	)	PUNCT
ajst-23570	96	30	further	further	ADJ
ajst-23570	96	31	research	research	NOUN
ajst-23570	96	32	on	on	ADP
ajst-23570	96	33	the	the	DET
ajst-23570	96	34	application	application	NOUN
ajst-23570	96	35	of	of	ADP
ajst-23570	96	36	bayesian	bayesian	NOUN
ajst-23570	96	37	methods	method	NOUN
ajst-23570	96	38	to	to	ADP
ajst-23570	96	39	other	other	ADJ
ajst-23570	96	40	types	type	NOUN
ajst-23570	96	41	of	of	ADP
ajst-23570	96	42	problems	problem	NOUN
ajst-23570	96	43	,	,	PUNCT
ajst-23570	96	44	such	such	ADJ
ajst-23570	96	45	as	as	ADP
ajst-23570	96	46	classification	classification	NOUN
ajst-23570	96	47	,	,	PUNCT
ajst-23570	96	48	clustering	clustering	NOUN
ajst-23570	96	49	,	,	PUNCT
ajst-23570	96	50	etc	etc	X
ajst-23570	96	51	.	.	X
ajst-23570	97	1	(	(	PUNCT
ajst-23570	97	2	2	2	X
ajst-23570	97	3	)	)	PUNCT
ajst-23570	97	4	conduct	conduct	VERB
ajst-23570	97	5	a	a	DET
ajst-23570	97	6	comparative	comparative	ADJ
ajst-23570	97	7	study	study	NOUN
ajst-23570	97	8	between	between	ADP
ajst-23570	97	9	bayesian	bayesian	NOUN
ajst-23570	97	10	method	method	NOUN
ajst-23570	97	11	and	and	CCONJ
ajst-23570	97	12	other	other	ADJ
ajst-23570	97	13	machine	machine	NOUN
ajst-23570	97	14	learning	learn	VERB
ajst-23570	97	15	algorithms	algorithm	NOUN
ajst-23570	97	16	to	to	PART
ajst-23570	97	17	determine	determine	VERB
ajst-23570	97	18	the	the	DET
ajst-23570	97	19	advantages	advantage	NOUN
ajst-23570	97	20	and	and	CCONJ
ajst-23570	97	21	disadvantages	disadvantage	NOUN
ajst-23570	97	22	of	of	ADP
ajst-23570	97	23	different	different	ADJ
ajst-23570	97	24	algorithms	algorithm	NOUN
ajst-23570	97	25	.	.	PUNCT
ajst-23570	98	1	(	(	PUNCT
ajst-23570	98	2	3	3	X
ajst-23570	98	3	)	)	PUNCT
ajst-23570	98	4	the	the	DET
ajst-23570	98	5	application	application	NOUN
ajst-23570	98	6	of	of	ADP
ajst-23570	98	7	dynamic	dynamic	ADJ
ajst-23570	98	8	bayesian	bayesian	NOUN
ajst-23570	98	9	methods	method	NOUN
ajst-23570	98	10	to	to	PART
ajst-23570	98	11	regression	regression	VERB
ajst-23570	98	12	problems	problem	NOUN
ajst-23570	98	13	is	be	AUX
ajst-23570	98	14	studied	study	VERB
ajst-23570	98	15	to	to	PART
ajst-23570	98	16	improve	improve	VERB
ajst-23570	98	17	the	the	DET
ajst-23570	98	18	adaptability	adaptability	NOUN
ajst-23570	98	19	and	and	CCONJ
ajst-23570	98	20	flexibility	flexibility	NOUN
ajst-23570	98	21	of	of	ADP
ajst-23570	98	22	the	the	DET
ajst-23570	98	23	model	model	NOUN
ajst-23570	98	24	.	.	PUNCT
ajst-23570	99	1	(	(	PUNCT
ajst-23570	99	2	4	4	X
ajst-23570	99	3	)	)	PUNCT
ajst-23570	99	4	explore	explore	VERB
ajst-23570	99	5	the	the	DET
ajst-23570	99	6	application	application	NOUN
ajst-23570	99	7	of	of	ADP
ajst-23570	99	8	bayesian	bayesian	NOUN
ajst-23570	99	9	methods	method	NOUN
ajst-23570	99	10	in	in	ADP
ajst-23570	99	11	nonlinear	nonlinear	ADJ
ajst-23570	99	12	regression	regression	NOUN
ajst-23570	99	13	problems	problem	NOUN
ajst-23570	99	14	to	to	PART
ajst-23570	99	15	improve	improve	VERB
ajst-23570	99	16	the	the	DET
ajst-23570	99	17	explanatory	explanatory	ADJ
ajst-23570	99	18	power	power	NOUN
ajst-23570	99	19	and	and	CCONJ
ajst-23570	99	20	prediction	prediction	NOUN
ajst-23570	99	21	accuracy	accuracy	NOUN
ajst-23570	99	22	of	of	ADP
ajst-23570	99	23	the	the	DET
ajst-23570	99	24	model	model	NOUN
ajst-23570	99	25	.	.	PUNCT
ajst-23570	100	1	this	this	DET
ajst-23570	100	2	study	study	NOUN
ajst-23570	100	3	provides	provide	VERB
ajst-23570	100	4	useful	useful	ADJ
ajst-23570	100	5	exploration	exploration	NOUN
ajst-23570	100	6	and	and	CCONJ
ajst-23570	100	7	enlightenment	enlightenment	NOUN
ajst-23570	100	8	for	for	ADP
ajst-23570	100	9	the	the	DET
ajst-23570	100	10	application	application	NOUN
ajst-23570	100	11	of	of	ADP
ajst-23570	100	12	bayesian	bayesian	NOUN
ajst-23570	100	13	method	method	NOUN
ajst-23570	100	14	in	in	ADP
ajst-23570	100	15	linear	linear	PROPN
ajst-23570	100	16	regression	regression	NOUN
ajst-23570	100	17	,	,	PUNCT
ajst-23570	100	18	and	and	CCONJ
ajst-23570	100	19	future	future	ADJ
ajst-23570	100	20	research	research	NOUN
ajst-23570	100	21	directions	direction	NOUN
ajst-23570	100	22	should	should	AUX
ajst-23570	100	23	focus	focus	VERB
ajst-23570	100	24	on	on	ADP
ajst-23570	100	25	expanding	expand	VERB
ajst-23570	100	26	and	and	CCONJ
ajst-23570	100	27	applying	apply	VERB
ajst-23570	100	28	scope	scope	NOUN
ajst-23570	100	29	,	,	PUNCT
ajst-23570	100	30	and	and	CCONJ
ajst-23570	100	31	improving	improve	VERB
ajst-23570	100	32	the	the	DET
ajst-23570	100	33	flexibility	flexibility	NOUN
ajst-23570	100	34	and	and	CCONJ
ajst-23570	100	35	adaptability	adaptability	NOUN
ajst-23570	100	36	of	of	ADP
ajst-23570	100	37	the	the	DET
ajst-23570	100	38	model	model	NOUN
ajst-23570	100	39	.	.	PUNCT
ajst-23570	101	1	references	reference	NOUN
ajst-23570	101	2	[	[	X
ajst-23570	101	3	1	1	NUM
ajst-23570	101	4	]	]	X
ajst-23570	101	5	zhu	zhu	PROPN
ajst-23570	101	6	,	,	PUNCT
ajst-23570	101	7	h.	h.	PROPN
ajst-23570	101	8	,	,	PUNCT
ajst-23570	101	9	han	han	PROPN
ajst-23570	101	10	,	,	PUNCT
ajst-23570	101	11	y.	y.	PROPN
ajst-23570	101	12	(	(	PUNCT
ajst-23570	101	13	2001	2001	NUM
ajst-23570	101	14	)	)	PUNCT
ajst-23570	101	15	bayesian	bayesian	NOUN
ajst-23570	101	16	statistical	statistical	ADJ
ajst-23570	101	17	inference	inference	NOUN
ajst-23570	101	18	of	of	ADP
ajst-23570	101	19	multiple	multiple	ADJ
ajst-23570	101	20	linear	linear	ADJ
ajst-23570	101	21	regression	regression	NOUN
ajst-23570	101	22	models	model	NOUN
ajst-23570	101	23	.	.	PUNCT
ajst-23570	102	1	statistics	statistic	NOUN
ajst-23570	102	2	and	and	CCONJ
ajst-23570	102	3	decision	decision	NOUN
ajst-23570	102	4	making	making	NOUN
ajst-23570	102	5	.	.	PUNCT
ajst-23570	103	1	[	[	X
ajst-23570	103	2	2	2	NUM
ajst-23570	103	3	]	]	SYM
ajst-23570	103	4	hu	hu	PROPN
ajst-23570	103	5	,	,	PUNCT
ajst-23570	103	6	z.	z.	PROPN
ajst-23570	103	7	,	,	PUNCT
ajst-23570	103	8	yang	yang	PROPN
ajst-23570	103	9	,	,	PUNCT
ajst-23570	103	10	x.	x.	NOUN
ajst-23570	103	11	(	(	PUNCT
ajst-23570	103	12	2011	2011	NUM
ajst-23570	103	13	)	)	PUNCT
ajst-23570	103	14	bayesian	bayesian	NOUN
ajst-23570	103	15	analysis	analysis	NOUN
ajst-23570	103	16	of	of	ADP
ajst-23570	103	17	linear	linear	PROPN
ajst-23570	103	18	regression	regression	NOUN
ajst-23570	103	19	model	model	NOUN
ajst-23570	103	20	under	under	ADP
ajst-23570	103	21	nmar	nmar	NOUN
ajst-23570	103	22	mechanism	mechanism	NOUN
ajst-23570	103	23	.	.	PUNCT
ajst-23570	104	1	journal	journal	PROPN
ajst-23570	104	2	of	of	ADP
ajst-23570	104	3	chuxiong	chuxiong	PROPN
ajst-23570	104	4	normal	normal	ADJ
ajst-23570	104	5	university	university	NOUN
ajst-23570	104	6	.	.	PUNCT
ajst-23570	105	1	[	[	X
ajst-23570	105	2	3	3	NUM
ajst-23570	105	3	]	]	X
ajst-23570	105	4	yao	yao	NOUN
ajst-23570	105	5	,	,	PUNCT
ajst-23570	105	6	y.	y.	PROPN
ajst-23570	105	7	(	(	PUNCT
ajst-23570	105	8	2010	2010	NUM
ajst-23570	105	9	)	)	PUNCT
ajst-23570	105	10	nonparametric	nonparametric	NOUN
ajst-23570	105	11	bayesian	bayesian	NOUN
ajst-23570	105	12	estimation	estimation	NOUN
ajst-23570	105	13	of	of	ADP
ajst-23570	105	14	linear	linear	PROPN
ajst-23570	105	15	regression	regression	NOUN
ajst-23570	105	16	models	model	NOUN
ajst-23570	105	17	with	with	ADP
ajst-23570	105	18	missing	miss	VERB
ajst-23570	105	19	variables	variable	NOUN
ajst-23570	105	20	.	.	PUNCT
ajst-23570	106	1	east	east	PROPN
ajst-23570	106	2	china	china	PROPN
ajst-23570	106	3	university	university	PROPN
ajst-23570	106	4	of	of	ADP
ajst-23570	106	5	science	science	NOUN
ajst-23570	106	6	and	and	CCONJ
ajst-23570	106	7	technology	technology	NOUN
ajst-23570	106	8	.	.	PUNCT
ajst-23570	107	1	[	[	X
ajst-23570	107	2	4	4	NUM
ajst-23570	107	3	]	]	X
ajst-23570	107	4	zhu	zhu	PROPN
ajst-23570	107	5	,	,	PUNCT
ajst-23570	107	6	h.	h.	PROPN
ajst-23570	107	7	,	,	PUNCT
ajst-23570	107	8	han	han	PROPN
ajst-23570	107	9	,	,	PUNCT
ajst-23570	107	10	y.	y.	PROPN
ajst-23570	107	11	,	,	PUNCT
ajst-23570	107	12	wu	wu	PROPN
ajst-23570	107	13	,	,	PUNCT
ajst-23570	107	14	z.	z.	PROPN
ajst-23570	107	15	(	(	PUNCT
ajst-23570	107	16	2005	2005	NUM
ajst-23570	107	17	)	)	PUNCT
ajst-23570	107	18	bayesian	bayesian	NOUN
ajst-23570	107	19	prediction	prediction	NOUN
ajst-23570	107	20	analysis	analysis	NOUN
ajst-23570	107	21	of	of	ADP
ajst-23570	107	22	multiple	multiple	ADJ
ajst-23570	107	23	linear	linear	ADJ
ajst-23570	107	24	regression	regression	NOUN
ajst-23570	107	25	model	model	NOUN
ajst-23570	107	26	.	.	PUNCT
ajst-23570	108	1	operations	operation	NOUN
ajst-23570	108	2	research	research	NOUN
ajst-23570	108	3	and	and	CCONJ
ajst-23570	108	4	management	management	NOUN
ajst-23570	108	5	.	.	PUNCT