Conseguences of soil crude oil pollution on some wood properties of olive trees Mathematics | 169 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 An Efficient Single Stage Shrinkage Estimator for the Scale parameter of Inverted Gamma Distribution Abbas Najim Salman Intesar Obeid Hassoun Dept. of Mathematics / College of Education for Pure Science (Ibn-Al- Haitham)/ University of Baghdad Maymona Mohammed Ameen University of Fallujah Received in : 28/June/2016 Accepted in: 23/November/2016 Abstract The present paper agrees with estimation of scale parameter θ of the Inverted Gamma (IG) Distribution when the shape parameter α is known (α=1), bypreliminarytestsinglestage shrinkage estimators using suitable shrinkage weight factor and region. The expressions for the Bias, Mean Squared Error [MSE] for the proposed estimators are derived. Comparisons between the considered estimator with the usual estimator (MLE) and with the existing estimator are performed .The results are presented in attached tables. Keywords: Inverted Gamma Distribution, Maximum Likelihood Estimator (MLE), Shrinkage EstimatorPretest Region, Bias, Mean Squared Error and Relative Efficiency. Mathematics | 170 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 Introduction “In Reliability studies the models which are used in life testing include the Exponential, Gamma, Lognormal and Inverted Gammadistributions. If the failure is mainly due to aging or wearing out process, then its reasonable in many applicationsto choose one of the above mentioned distribution.In a sense, this distribution is unnecessary,it has the same distribution as the reciprocal of a gamma distribution .However, a catalogue of results for the inverse gamma distribution prevents having to repeatedly apply the transformation theorem in applications”;[1],[2],[3],[4]. “TheInverted Gamma distribution is prospective to use in life experiments”; [5], it has probability density function (p.d.f) with two parameters α and θ as below : ( ) ( ) ------------------------(1) Here α and θ arerespectively the shape and scale parameters. In conventional notation, wewrite X~IG (α , θ). This paper deals with the problem for estimation the unknown scale parameter (θ) of IG distribution with known shape parameter (α) when a prior estimate (θo) regarding the actual value (θ) is available using preliminary test single stage shrinkage estimator. It is Well-known that, the prior knowledge regarding due reasons introduced by Thompson [9] as well as the classical estimator of ( ) and using shrinkage weight function [ψ(θ ^ )] ;0 ψ (θ ^ ) 1 results what it isknown as "shrinkage estimator”, which though perhaps biased has smaller mean squared error (MSE) than that of . Thus "Thompson – Type" shrinkage estimator will be = ψ (θ ^ ) + (1- ψ(θ ^ )) θO;-------------(2) Now , to test the prior knowledge of weather close to actual value and to be comfortable to use this priorknowledge,the preliminary test single stage shrinkage estimator (SSSE) will be used for this mission when using the test estimator of level of significant ( ) for testing the hypotheses θO HO: θ=θOVS.HA : θ If HO correct, thenthe estimator which is defined in (2) will be used. Conversely , if HOrejected,thendifferentshrinkage weight functionsΨ2 ( );0 ( ) will be used and then using the followingshrinkage estimator Ψ2(θ ^ ) +(1-Ψ2(θ ^ )) θ0 ----------------------------------------(3) Consequently, thecommon form of preliminary test single stage shrinkage estimator(SSSE) will be ={ ( ) ( ( )) ( ) ( ( )) -------------(4) Mathematics | 171 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 ( ) ( ) =1,2 isa shrinkage weight function specifying the belief of θ^and (1- Ψ(θ^)) specifying the belief θoand Ψ1(θ ^ ) may be a function of θ ^ or may be a constant (ad hoc basis ),while (R) is a pretest region for acceptance of the prior knowledge with level of significance ( ) . Numerousauthors have been studied the estimator(4)for estimating parameters,see for example[6],[7]and[8]. The purpose of this paper is to employ the preliminary test single stage (SSSE) defined by (4) for estimating the scale parameter (θ) of two parameters Inverted Gamma (IG) distribution when the shape parameter (α) is known. The expressions of Bias, Mean Squared Error (MSE) and Relative Efficiency (R.Eff(.)) were derived for the proposed estimator. Numerical resultsand conclusions due mentioned expressions including some constantswereachieved and put in annexed tables. Comparisons between the proposed estimators with the classical estimator and with existing estimator are performed. Maximum Likelihood Estimator of θ Let x1, x2,---, xn be a randomsample of size n form IG (1,θ), then the natural logarithm of the Likelihood function L(1,θ) can be written as: ( ) ∑ ∑ ------------------------------(5) ∑ -----------------------------(6) Let ,then the maximum Likelihood estimator of θ is ∑ ---------------------------------(7) The distribution of is G(nα ,θ/n) ( ) ( ) ( ) ( ) = = ( ) And, ( ) ( ) Preliminary Test Single Shrinkage Estimator (PTSSSE). Using the form (4), we proposed the preliminary test single stage shrinkage estimator for estimator the scale parameter θ of Inverted Gamma distribution when a prior knowledge θo available about θ with known shape α =1 as below:- { ( ) -----(8) i.e. we put ψ1( ) ( ) in equation (4)and R is the pretest region Mathematics | 172 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 ]----------------------------------(9) For simplicity , assume R =[a,b] , a b i.e. a= , b= -------------------------(10) Where and are respectively the lower and upper 100( /2) percentile point of chi-square distribution with (2n) degree of freedom. The expression for the bias of the estimator is as follow:- Bias ( ) = E ( ) - θ =∫ ( ) ( ) ∫ ( ) ( ) ( ) Where is the complement region of R in real space and f(θ ^ ) isa (P D F) of ( ) which has the following forms. ( ) ( ) ( )( ) ------------------(11) We conclude ,( ) * ( ) ( )+ ( )( )---------(12) ( , ) =∫ ( ) = = ----------(13) The bias ratio B(.) of the estimator ( ) is defined below ( ) (( ) -----------(14) And the expression for mean square error (MSE) of is given asbelow: Mathematics | 173 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 ( ) ,( ) * ( ) ( ) ( ) + ( )( ) * ( ) ( ) + * ( ) + ( ) ( ) -------------------------------------------(15) In this paper we use the shrinkage weight factor (k) as the same as of Thompson – type as below ( ) ( ) ( ) And by simple calculation ( ) ( ) -----------------------------------(16) The Relative Efficiency of estimator w.r.t the classical estimator is defined as below:- ( ) ( ) ( ) -------(17) See for example [6],[7],[8]and[9]. Conclusions and Numerical Results The computations of Relative Efficiency[R.Ef f(.)] and Bias Ratio [B(.)] for the equation( 14 ) and (17 ) were used for the estimator .Thesecomputations (using Math. CAD program) were performed for =0.01, 0.05, 0.1,ζ =0.25(0.25)2 and n = 4, 6, 8, 10, 12. These computation are given in attached tables No.(1)and(2) for some samples of these constants.The observation mentioned in the tables leads to the following results. 1.Bias Ratio [B(.)] of increases whenζ increase. 2. The R.E f f of are adversely proportional with value of especially when ζ = 1(θ o =θ) this yields =0.01 has higher R. efficiency for all n. 3. Bias ratio of increases when increases especially when ζ= 1. 4. The Relative Efficiency [R.E ff(.)]decreases when n increases for all and ζ. 5. Relative Efficiency has the highest value at ζ =1 (θ o =θ) and decreases otherwise. 6. The proportional estimator is better than the classical estimator in the sense of Mean Squared Error. References 1.Chhikara,R.and Folks,(1977),The Inverse Gaussian Distribution As A life Model,Techno metrics 19,461-468. 2. Sinha,S.and Kale,B,(1980),"Life Testing and Reliability Estimation. John Wiley & sons. 3.Von Alren,W.(ed).(1964),"Reliability Engineering by ARINC. Prentice Hall,Inc.,New Jersey. 4.Sherif,Y.S. and Smith ,M.L.(1980), "First Passage Time Distribution of Brownian motion as a reliability model. IEEE Transaction of Reliability,29,5,425-426. 5.Lin,C;Duran,B,and Lewis,(1989),"Inverted Gamma as a Life Distribution Microelectronics and Reliability 29,(4),619-626. Mathematics | 174 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 6.Al- Joboori, A.N.,(2002),"On Shrunken Estimators for the Parameters of Simple Linear Regression Model. Ibn –Al-HaithamJ. for pure and Applied Science, 15,(4A).60-67. 7.Al-Joboori, A. N.,(2010)."Pre – Test Single and Double Stage Shrunken Estimator for the Mean of Normal Distribution with Known Variance ",Baghdad Journal for Science .7.4 .1432-1442. 8.Al-Joboori, A. N; Khalaf, B. A. and Hamza, S, (2010),"Estimate the Scale Parameter of Exponential Distribution Via Modified Tow Stage Shrinkage Technique " ,Journal College of Education. 6,62-75. 9.Thompson,J.R., (1968a),"Some Shrinkage Techniques for Estimating the Mean ",J. Amer. Statist. Assoc,63,113-122. 10.V.Wilkorsky,(2001),"Computing the distribution of a linear Combination of Inverted Gamma Variables" Kybernetika ,37(1),79-90. 11.Huda, A. Rasheed and Akbal, J. Sultan ,(2015),"Bayesion Estimate of the Scale Parameter for Inverse Gamma Distribution under Linex Loss Function ", International Journal of Advanced Research ,3, 2,369 -375. 12.Dey,S.,(2007),"Inverted Exponential Distribution as a life distribution Model from a Bayesian View Point Data", Science Journal, 6,107-113. Table (1) Showed Bias Ratio [B(.)]of Δ n B(-) ζ 0.75 0.50 0.25 1 1.25 1.50 1.75 2 0.01 4 B(-) -0.75 -0.5 -0.25 -1.966415E-9 0.25 0.5 0.75 1 6 B(-) -0.75 -0.5 -0.25 -1.670148E-10 0.25 0.5 0.75 0.9999999 8 B(-) -0.7499999 -0.5 -0.25 -6.020044E-12 0.25 0.5 0.7499999 0.9999999 10 B(-) -0.7499999 -0.5 -0.25 -1.193395E-13 0.25 0.4999999 0.7499999 0.9999999 12 B(-) -0.7499999 -0.4999999 -0.25 -1.490223E-15 0.25 0.4999999 0.7499999 0.9999999 0.05 4 B(-) -0.7499813 -0.4999878 -0.2499944 -1.2290094E-6 0.2499919 0.4999849 0.749978 0.9999711 6 B(-) -0.7499719 -0.4999813 -0.2499907 -1.0438422E-7 0.2499904 0.4999808 0.7499712 0.9999615 8 B(-) -0.7499625 -0.499975 -0.2499875 -3.7625274E-9 0.2499875 0.499975 0.7499624 0.9999499 10 B(-) -0.7499531 -0.4999688 -0.2499844 -7.458721E-11 0.2499844 0.4999687 0.7499531 0.9999375 12 B(-) -0.7499437 -0.4999625 -0.2499813 -9.313892E-13 0.2499812 0.4999625 0.7499437 0.999925 0.1 4 B(-) -0.7497014 -0.4998049 -0.2499109 -1.966415E-5 0.2498698 0.4997585 0.7496477 0.9995381 6 B(-) -0.74955 -0.4997002 -0.2498506 -1.6701475E-6 0.2498464 0.4996933 0.7495389 0.9993833 8 B(-) -0.7494 -0.4996 -0.2498 -6.0200438E-8 0.2497998 0.4995995 0.749399 0.999198 10 B(-) -0.74925 -0.4995 -0.24975 -1.1933954E-9 0.24975 0.4995 0.7492499 0.9989999 12 B(-) -0.7491 -0.4994 -0.2497 -1.490223E-11 0.2497 0.4994 0.7491 0.9988 Mathematics | 175 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 Table (2) Showed Relative Efficiency [R.Eff (.)] of . Δ n R.Eff(-) ζ 0.75 0.50 0.25 1 1.25 1.50 1.75 2 0.01 4 R.Eff(-) 0.4444445 1.0000001 4.0000003 5.4235342E+14 4.0000004 1.0000001 0.4444445 0.25 6 R.Eff(-) 0.2962963 0.6666667 2.666667 2.7386475E+14 2.666667 0.6666667 0.2962963 0.1666667 8 R.Eff(-) 0.2222223 0.5000001 2.0000003 1.5616604E+14 2.0000003 0.5000001 0.2222223 0.125 10 R.Eff(-) 0.1777778 0.4000001 1.6000003 9.9998908E+13 1.6000003 0.4000001 0.1777778 0.1 12 R.Eff(-) 0.1481482 0.3333334 1.3333337 6.9444435E+13 1.3333337 0.3333334 0.1481482 0.0833334 0.05 4 R.Eff(-) 0.4444667 1.0000497 4.0001857 1.3884247E+9 4.0002792 1.0000666 0.4444739 0.2500166 6 R.Eff(-) 0.2963185 0.6667167 2.6668661 7.0109376E+8 2.6668729 0.6667184 0.2963195 0.1666799 8 R.Eff(-) 0.2222444 0.50005 2.0002 3.9978506E+8 2.0002002 0.5000501 0.2222445 0.1250126 10 R.Eff(-) 0.1778 0.40005 1.6002 2.5599721E+8 1.6002 0.40005 0.1778 0.1000125 12 R.Eff(-) 0.1481704 0.3333833 1.3335333 1.7777775E+8 1.3335333 0.3333833 0.1481704 0.0833458 0.1 4 R.Eff(-) 0.4448011 1.0007958 4.0029708 5.4235342E+6 4.0044671 1.0010656 0.4449165 0.2502665 6 R.Eff(-) 0.2966521 0.6674671 2.6698578 2.7386475E+6 2.6699666 0.6674953 0.2966682 0.1668785 8 R.Eff(-) 0.2225782 0.5008008 2.0032011 1.5616604E+6 2.0032051 0.5008023 0.2225793 0.1252013 10 R.Eff(-) 0.1781338 0.400801 1.6032022 9.9998908E+5 1.6032023 0.4008011 0.1781339 0.1002003 12 R.Eff(-) 0.1485043 0.3341346 1.3365365 6.9444435E+5 1.3365365 0.3341346 0.1485043 0.0835337 Mathematics | 176 2012( عام 1( العدد ) 30مجلة إبن الهيثم للعلوم الصرفة و التطبيقية المجلد ) Ibn Al-Haitham J. for Pure & Appl. Sci. Vol.30 (1) 2017 مقدر التخلص ذي المرحله الواحده الكفؤ لمعلمة قياش توزيع معكوش َكاما عباش وجم سلمان اوتصار عبيد حسون جايعت بغذاد /(ابٍ انهيثى )كهيت انخشبيت نهعهىو انصشفت /قسى انشياضياث ميمووه محمد اميه جايعت انفهىجت 8102 /تشريه الثاوي/82قبل في: 8102/حسيران / 82استلم في: الخالصة نخىصيع يعكىط َكايا ري انًعهًخيٍ عُذيا حكىٌ θيخعايم هزا انبحث يع حقذيش يعهًتانقياط ( SSSEبطشيقت يقذس االخخباس األوني انًخقهص ري انًشحهت انىاحذة ) 1يعهىيت وحساوي يعهًت انشكم ( MSEورنك باسخعًال عايم وصٌ ويجال يُاسب.أشخقج يعادالث انخحيض, يخىسطًشبعاث انخطأ ) انًقذس انًقخشح . ( ويع انًقذساث انًىجىدة انخي MLEوأجشيج يقاسَاث بيٍ انًقذس انًقخشح يع انًقذس انكالسيكي ) جضث وحى عشض هزة انُخائج في انجذاول انًشفقت.اَ حىصيع يعكىط َكايا , يقذساأليكاٌ االعظى , يقذس االخخباس انًخقهص , انخحيض , يخىسط يشبع انخطأ : الكلمات المفتاحية وانكفأة انُسبيت