. International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020436 International Journal of Energy Economics and Policy ISSN: 2146-4553 available at http: www.econjournals.com International Journal of Energy Economics and Policy, 2020, 10(1), 436-455. The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan Sugra Ingilab Humbatova1, Fariz Saleh Ahmadov2, Ilgar Zulfuqar Seyfullayev3, Natig Gadim-Oglu Hajiyev4* 1Department of World Economy, Azerbaijan State University of Economics (UNEC), International Center for Graduate Education, “Economy and Management” Baku Engineering University (BEU), 2Department of Economics and Business Administration, International Center for Graduate Education, Azerbaijan State University of Economics (UNEC), Istiqlaliyyat Str. 6, Baku, AZ-1001, Azerbaijan, 3Department of Industry Economy and Management, Azerbaijan State University of Economics (UNEC), International Center for Graduate Education, “Economy and Management” Azerbaijan Technical University, 4Department “Regulation of Economy,” Azerbaijan State University of Economics (UNEC), AZ-1001, Baku, Azerbaijan. *Email: n.qadjiev2012@yandex.ru Received: 29 August 2019 Accepted: 05 November 2019 DOI: https://doi.org/10.32479/ijeep.8642 ABSTRACT Research examines the relations between GDP in Manat and Dollar and total electric energy consumption (1995-2017) for the last 22 years in the Republic of Azerbaijan. Besides, the relations between the electric energy consumption and the growth of GDP in these sectors were analysed. Autoregressive distributed lag model was used as a research methodology. Stationary tests of variables (ADF, PP, and KPSS) and Pairwise Granger Causality Tests were done. Stability of models was examined. Eviews_9 econometric software program was used to establish graphics and do calculations. Having analysed the research, there is a positive correlation not only in GDP and electric energy consumption but also electric energy consumption and GDP in different sectors of economy. We recommend to save electric energy. Keywords: Electric Energy Consumption, GDP Growth, Autoregressive Distributed Lag JEL Classifications: F15, B28, C23, Q43, O52 1. INTRODUCTION The roles that hydrocarbon resources, including oil products as energy carriers, play in the economy and in the life of people are undeniable (Muradov et al., 2019). Policy development, ensuring the growth and development of complex, open and non-linear economic systems, as well as the measurement and evaluation of its results are widely discussed topics in modern economics. It is not by chance that these topics occupy a special place in the reports of international organizations and in the diaries of scientific journals. “How are the priority directions of economic policy chosen?,” “How are the needs of economic agents studied in incentives?” “How does economic policy affect the behavior of economic agents?,” “What indicators can assess the effectiveness of regulatory measures?”, “How can one measure and evaluate economic development and growth?” These and many other issues still remain “apples of discord” for economists. Angus Deaton believes that economics can be a good tool for developing successful economic policies, but for this it needs, first of all, high-quality information. Nobel laureate, noting the fundamental importance of measurement in economics, argued that, as a means of correctly evaluating the results of economic policy, measurement could also become a source for new theoretical ideas. Currently, in countries along with microeconomic statistics, microeconomic databases are also being developed. The creation, This Journal is licensed under a Creative Commons Attribution 4.0 International License Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 437 preservation, systematization and processing of such scientific and labor-intensive microeconomic databases requires large financial resources. And the quality of macroeconomic data is reduced under the influence of the variability of monetary units of measurement. To eliminate the above deficiency, universal natural indicators are used, one of which is the electricity consumption. Some studies have found a statistically significant (Dhungel, 2010; Lu, 2017; Aslan, 2014) and a bi-directional causal relationship (Kasperowicz, 2014; Ogundipe and Apata, 2013; Motlokoa, 2016) between electricity consumption and economic growth. Other studies show us that the nature of the relationship between electricity consumption and economic growth differs depending on the type of activity. There exists bidirectional causality between electricity consumption and real output in the services sector and unidirectional causality running from real output in the industrial sector to electricity consumption. However, there is no causal relationship between electricity consumption and real output in the agricultural sector (Ibrahiem, 2018). In addition, it is believed that the living standard of the population and the economic development degree in the country also affect the relationship between electricity consumption and economic growth (Mahfoudh and Ben Amar, 2014). The results of these studies do not give us full grounds for adopting electricity consumption as an unequivocal indicator of economic growth. Preponderance of industrial states is completely dependent on energy to fuel their economies. Besides, globalization has made the world to be so interconnected and interdependent that the energy industry is the biggest contributor of the climate change which doesn’t affect a single country but have far wider implications (Vidadili et al., 2017). Each country with its own economic structure, development level and security of natural energy resources, mechanisms for regulating energy markets, climatic, geographical and demographic conditions is a unique object of research. Conducting such studies in different countries can clarify the relationships between factors that influence the nature of the relationship between electricity consumption and economic growth. On this basis, the study of the relations between these indicators in Azerbaijan was adopted as the goal of this study. We think that the results of our research are of scientific and practical importance in the following areas: 1. Research provides some empirical information about the relationship between energy consumption and economic growth in an energy-rich country; 2. Shows the behavior of energy consumption and growth in different sectors of the Azerbaijan economy; 3. The results can be used to predict the electricity demand throughout the economy, and by its branches in countries with similar conditions. 2. GENERAL CONDITIONS OF POWER SUPPLY IN AZERBAIJAN Electricity production in Azerbaijan dates back to the first years of the 20th century - from the time of the first oil boom. Subsequent industrialization processes and the possession of rich hydrocarbon resources led to an accelerated growth in demand for electricity. In the last 50 years alone, the production of electricity has almost doubled (Table 1). İt can be seen that almost 90% of the total energy produced is accounted for by thermal power plants. Despite the country’s huge potential for renewable and alternative energy sources, it was only in the last decade that solar and wind energy began to be used for production. In Azerbaijan, production facilities, transmission lines and distribution of electricity are fully owned by the state and electricity tariffs are regulated by the state. The volume of production capacity is far ahead of the volume of domestic demand for electricity. Today, Azerbaijan is an exporter of electric energy to neighboring countries. Despite the fact that all parts of Azerbaijan are fully and continuously supplied with electricity, we occupy one of the last places in the region in terms of the use of electricity per capita (Table 2). Table 1: Power generation in Azerbaijan, million kVt.h Date Years 1913 1920 1930 1940 1950 1960 1970 1980 1990 2000 2010 2017 Generation 110,8 122 503,9 1827 2924 6590 12027 15045 23152 18699 18710 24320,9 Fuel 1802 2894 4626 10893 13825 21399 17069 15003 20445,4 Hydro 24,3 29,5 1963 1022 1098 1658 1534 3446 1746,4 Own power plant of enterprises (fuel) 111,7 122,2 95,6 83,1 259,7 1899,5 Wind 0,5 22,1 Solar 37,2 Waste 170,3 Power of electricity plants, MVt 39,8 56,4 113,4 254,4 401,6 1261 2623 2882 5051 4912 6398 7941,5 www.stat.gov.az Table 2: Electric power consumption Countries kVt.h/per capita Azerbaijan 2.202 Armenia 1.962 Georgia 2.694 Turkey 2.847 Turkmenistan 2.679 Russian Federation 6.603 Kazakhstan 5.600 Ukraine 3.419 Iran 3.022 https://data.worldbank.org/indicator/EG.USE.ELEC.KH.PC Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020438 Data period Reearched countries Method(s) Results M a r i u s - C o r n e l i u et al. (2018) Annual, 1990-2014 Ten European Union (EU) member states from Central and Eastern Europe ARDL The result shows that there is no relationship between renewable energy consumption and GDP in Romania and Bulgaria. However, there is resurgence in renewable energy consumption in Hungary, Lithuania and Slovenia. To sum up, cause-effect relationship between renewable energy consumption and GDP was confirmed in both states. The confirmation is true for each studied state separately Rafał Kasperowicz (2014) First quarter of 2000 to the fourth quarter of 2012 Poland C.W.J. Granger, ADF, KPSS test Achieved results reveals that there is a relationship between electricity consumption and economic growth in Poland. Direction is divided into 2 parts. Dependency of economic growth on electricity is expressed in Poland Maria Pempetzoglou (2014) 1945-2006 Turkey Standard linear Granger causality test and the nonparametric Diks and Panchenko causality test Results confirm that there is a single-direction nonlinear causal relationshipship between income and electricity consumption. Besides, we can see the followings: 1. Single-direction linear approach to electricity consumption spent on residential, commercial and street lighting 2. Single-direction nonlinear causal relationshipship directed from electricity consumption to GDP in residential, commercial fields 3. Single-direction nonlinear causal relationshipship directed from income to electricity consumption in street lighting. to GDP in residential, commercial fields Wen-Cheng Lu (2017) 1998-2014 17 industries in Taiwan Granger causality Results confirm the double-direction Granger causal relationshipship and long-term balance between electricity consumption and GDP. So, the growth of electricity consumption by 1% causes to increase 1.72% in GDP Slim and Mohamed (2015) 1990-2010 19 African countries Solow model, Granger test There is a strong correlation between electricity consumption and rich countries. There is also a correlation relationship between the lack of using modern service of energy and the people who work for 2 dollars per day Ömer and Bayrak (2017) 1990-2012 75 net energy-importing countries CADF DOLS and FMOLS estimators Based on the results of individual and group states, there is a positive and statistically significant relationship between electricity consumption and GDP in a long term. Thus, electricity consumption causes GDP growth Uyar and Gökçe (2017) Annual, 1985-2013 Vietnam, Indonesia, South Africa, Turkey and Argentina Panel Quantile Regression The influence of GDP on oil consumption is tremendously downsizing. However, hydroelectric stations impact on electricity consumption positively and surges significantly. Coal has no any influence on economic growth Kamal (2017) 2000-2011 Five south Asian countries Granger causality, VARM Cointegration test proves the positive relationship and balance between electricity consumption and GDP in a long term. The electricity consumption coefficient is 1.3%. It reveals that the increase of electricity consumption by 1% causes the growth of GDP by 1.31%. Thus, electricity consumption has a significant influence on economic development in South Asia Aslan (2014) 1980-2008 Turkey Granger causality There is a positive and statistically significant relationship between electricity consumption and GDP in Turkey Ibrahiem (2018) 1971-2013 Egypt Johansen cointegration approach, VECM Results prove the following relationships: 1. There is a double causal relationship between electricity consumption and real product in service sector 2. There is a single-direction causal relationship from real product to electricity consumption 3. There is no causal relationship between real product and electricity consumption in agrarian sector Table 3: Summary of similar empirical studies in the literature (Contd...) Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 439 Data period Reearched countries Method(s) Results Junsheng et al. (2018) 1953-2013 China Granger causes, Toda-Yamamoto test The result confirms the positive relationship between electricity consumption and economic growth Basiru (2014) 1980-2011 18 Sub-Saharan Africa countries Panel Unit Root Test There is no any causal relationship between electricity consumption and economic growth in the studied states. It is appropriate to neutrality hypothesis. In other words, GDP and electricity consumption are neutral to each other Adeyemi and Ayomide (2013) 1980-2008 Nigeria VECM, Pairwise Granger Causality test The research result confirms the cointegartion relationship between electricity consumption and economic growth and sets the double-direction causal relationship between electricity consumption and economic growth Ranjan et al. (2017) 1990-2012 BRICS countries The Pedroni (1999-2004) Panel cointegration test, PECM There is no any strong relationship between GDP and electricity consumption. The growth of GDP is a key factor that causes the increase of electricity consumption in the studied states Muhammad and Nur-Syazwani (2018) 1971-2014 Malaysia ARDL There is a cointegration relations between real GDP and electricity consumption. Electricity consumption influences positively on economic growth in a short term Lira and Mamofokeng (2016) 1982-2013 Uganda Granger causality test The result confirms the double-direction causal relationship between electricity consumption and economic growth in a long term Ozturk et al. (2019) 1970-2012 Denmark ARDL Granger causality test The result confirms the neutrality of the relationship between electricity consumption and economic growth in Denmark Bekareva et al. (2017) 2000-2014 United States Arellano-Bond method The result confirms the positive relationship between renewable energy consumption and economic growth. Molem and Ndifor (2016) 1980-2014 Cameroon Generalised Method of Moments The result confirms that there is a relationship among electricity consumption, economic growth, population and electricity price Mukhtarov et al., 2017 1990-2015 Azerbaijan Toda-Yamamoto causality test, VAR The results of this test show that there is bidirectional causality between energy consumption and economic growth. Findings of the study Mukhtarov et al., 2018 1992-2015 Azerbaijan Gregory–Hansen test, VECM The results confirm the existence of a long-run relationship among the variables (between energy consumption, financial development, and economic growth). Find that there is a positive and statistically significant impact of financial development and economic growth on energy consumption in the long-run Table 3: (Continued) The availability and relatively low tariffs of natural gas in all regions of Azerbaijan are the main argument for explaining this paradoxical situation. 3. LITERATURE REVIEW The research of the relationships between energy consumption and economic growth has been a focal issue among scientists (Table 3). During research, a number of methods were employed. We can classify them as the following: for example, the relationships between energy consumption and economic growth has been analysed through autoregressive distributed lag (ARDL) method (Lefteris and Theologos, 2011; Ozturk and Ali, 2011; Ramazan et al., 2008; Nicholas, 2009; Fuinhas et al., 2012). However, other scientists researched the relationships between energy consumption and economic growth by Granger test (Narayan et al., 2010; Yemane, 2014; Śmiech and Monika, 2014; Appiah, 2018; Mutascu, 2016; Turgut and Resatoglu, 2016; Masako and Zijian, 2016; Muhammad et al., 2011; Richard and Jonathan, 2015; Muhammad and Hooi, 2012). 4. MATERIALS AND METHODS 4.1. ARDL Model ARDL model was used for the research. Through this model, cointegration between electric energy and GDP was estimated. To be exact, research assessed the influence of total electric energy production to GDP and the impact of electric energy consumption in different fields to GDP in Azerbaijan Republic (A.Figure 1). The relations in long and short term were researched. 4.2. Unit Root Tests It is essential to check the stationary of variables through Unit Root before the assessment of regression equations. Because, keeping stability between variables is important while assessing the Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020440 dependency between two or more variables by using regression analysis. However, probability distribution for every time series in order to be stationary must be identical. Nevertheless, stationary of variables is not always desirable. For a long term or cointegration relation and assessment, the variables must be non-stationary in most methods. It is also required that the first difference should be stationary or I(1). It must be noted that if any time series variable is stationary with real values, then it can be considered I(0). If a variable is not I(0), then its first difference is calculated and its stationary is checked. In this case, if the variable is stationary, then it is considered I(1). A variable sometimes changes because of probability distribution. In that case, the variable becomes trend- stationary. One can refer to modern econometric books regarding the stationary of changes and its effect in time series analysis (Hill et al., 2001; Heij et al., 2005; Asteriou and Hall, 2007). We can analyze them by applying three different unit root tests in order to get more reliable stationary test results: Augmented Dickey Fuller, Phillips−Perron (PP) and Kwiatkowski−Phillips−Schmidt−Shin (KPSS). The evaluation of these tests is done through E-Views 9. It must be noted that “unit root problem” or “variable is non- stationary” null hypothesis in unit root tests is checked. In KPSS test, “variable is stationary” hypothesis is taken and considered as stationary null hypothesis. If the variable is non-stationary without trend, and becomes stationary if trend is included, then the checked variable is considered “trend-stationary”. 4.3. Test Cointegration Cointegration test proves long-term relations and F−statistics is indicated to express it. Menatime, cointegration was identified by ECM model. In these models, GDP is dependent variable while electric energy consumption is an independent variable. ∆ ∆ ∆ lN lN lM lN lM t t t i n i t i i m i t i i = + + + + + − − = − − = − −∑ ∑ α δ θ ϕ ρ ε 1 1 1 1 0 1 (1) INt − GDP lMt − Electric energy consumption α − Constant factor φi, ρi, − Parameters Null hypothesis: H0: δi = qi = 0, No cointegration. Alternative hypothesis: H0: δi ≠ qi ≠ 0, Cointegration exists. Table 5: Results from bound tests Dependant variable AIC lags F‒statistic Decision Significance I (0) Bound I (1) Bound 10% 5% 2.5% 1% 10% 5% 2.5% 1% lgdpm 5.30 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 Cointegration lgdpd 9.65 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 Cointegration lepegdp 29.39 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 Cointegration ligdp 3.02 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 No cointegration lmigdp 1.37 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 No cointegration lcgdp 8.37 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 Cointegration lahfgdp 6.15 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 Cointegration ltwtgdp 1.57 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 No cointegration lcpsgdp 37.17 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 Cointegration lpi 7.77 1 4.04 4.94 5.77 6.84 4.78 5.73 6.68 7.84 Cointegration Table 4: VAR lag order selection criteria Lag LogL LR FPE AIC SC HQ Lgdpm leci 0 −18.98 NA 0.02 1.90 2.007 1.93 1 38.52 99.32* 0.0002* −2.96* −2.65* −2.88* lgdpd leci 0 −19.53 NA 0.02 1.96 2.06 1.98 1 29.13 84.05* 0.0004* −2.10* −1.81* −2.03* lepegdp lepetec 0 −31.82 NA 0.07 3.07 3.17 3.09 1 3.97 61.83* 0.004* 0.18* 0.48* 0.25* ligdp lecii 0 −49.32 NA 0.36 4.67 4.77 4.69 1 −6.49 73.99* 0.01* 1.13* 1.43* 1.22* lmigdp lecmii 0 −28.63 NA 0.06 2.77 2.88 2.81 1 12.61 71.23* 0.002* −0.60* −0.31* −0.53* lcgdp liecc 0 −53.06 NA 0.5 5.01 5.11 5.03 1 −6.957 79.65* 0.01* 1.18* 1.47* 1.25* lahfgdp lecahfi  0 −31.80 NA 0.07 3.07 3.17 3.09 1 34.76 114.96* 0.0002* −2.61* −2.32* −2.55* ltwtgdp lectwti 0 −13.16 NA 0.01 1.38 1.48 1.40 1 30.63 75.62* 0.0003* −2.23* −1.94* −2.16* lcpsgdp leccpsi 0 −43.31 NA 0.22 4.11 4.22 4.10 1 4.43 82.467* 0.003* 0.15* 0.44* 0.21* lpi lecpi 0 −32.67 NA 0.08 3.15 3.25 3.18 1 41.22 127.62* 0.0001* −3.20* −2.90* −3.13* *Indicates lag order selected by the criterion. LR: Sequential modified LR test statistic (each test at 5% level), FPE: Final prediction error, AIC: Akaike information criterion, SC: Schwarz information criterion, HQ: Hannan-quinn information criterion Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 441 F−statistics Narayan (2005) is compared with proposed limited indicators. If Fstatistic > Fcritical, then null hypothesis is rejected. It means cointegration exists. The Long Run Model lN lN lMt i n i t i i m i t i i= + + + = − − = − −∑ ∑α ϕ ρ µ 1 1 0 1 ∆ ∆ (2) Error Correction (short run) Model ∆ ∆ ∆lN lN lM ECTt i n i t i i m i t i t i= + + + + = − − = − − −∑ ∑α ϕ ρ σ ω 1 1 0 1 1 (3) 4.4. Diagnostic Test This article will use Breusch Godfrey LM test (null hypothesis: “no serial correlation”) in order to check subsequent correlation problem and use both Breusch−Pagan−Godfrey (null hypothesis: “no heteroskedasticity problem”) and Autoregressive Conditional Hederoscedasticity test (ARCH) for obtaining more reliable outcomes for heteroskedasticity problem. During ARCH test, null hypothesis “no heteroskedasticity problem” theory is checked. Nonetheless, Ramsey RESET Test and Normality Test (Jarque‒Bera) JB was checked. Null hypothesis rejection is acceptable for every five cases. Statistical data encompasses 1995-2017. Data have been taken from Statistics Committee of the Republic of Azerbaijan. 5. RESULTS AND DISCUSSIONS 5.1. Unit Root Test Let’s have a look at stationary of variables before identifying methods for evaluation. All stationary test results of variables for evaluation of both problems were given in the table. Each variable has been checked through three different unit root tests. The table shows that the majority of variables are I(1). Thus, according to ADF test, in With Intercept only case, ECI, ECMII, ECAHFI are stationary. (I(0)). Out of the variables GDPD and PI are stationary (I(2). The rest of the variables are stationary I(1). In With Intercept & Trend case ECI and ECII I(0) GDPM, GDPD, EPEGDP and PI I(2) are stationary. The rest of the variables are stationary I(1). In No Intercept & No Trend case, PI I(2) is stationary again. The rest of the variables are stationary I(1) (A.Table 1). In PP Unit Root Test, in With Intercept only case, ECII, ECAHF I(0) GDPD and PI I(2) are stationary. The rest of the variables are stationary I(1). In With Intercept & Trend case, ECMII and IECC I(0) GDPM, GDPD, ECCPSI and PI I(2) are stationary. Table 6: Long run coefficients Variable Coefficient Std. error t‒statistic Prob. lgdpm leci 11.88* 3.54 3.36 0.0202 c ‒107.09* 34.85 ‒3.07 0.0277 lgdpd leci 11.92** 2.45 4.88 0.0018 c ‒105.89** 23.86 ‒4.43 0.0030 lepegdp lepeitec 4.47** 0.57 7.77 0.0045 c ‒29.77** 4.39 ‒6.77 0.0065 lecigdp lecii ‒5.29 20.89 ‒0.25 0.8123 c 50.18 158.97 0.31 0.7680 lmigdp lecmii 11.57 18.38 0.63 0.5565 c ‒40.32 80.57 ‒0.51 0.6383 lcgdp liecc 1.31*** 0.08 16.81 0.0005 c 0.85 0.45 1.85 0.1604 lahfgdp lecahfi 82.92 1147.92 0.071 0.9444 c ‒586.69 8233.25 ‒0.07 0.9452 ltwtgdp lectwti ‒28.63 36.11 ‒0.77 0.4638 c 190.89 231.71 0.82 0.4475 lcpsgdp leccpsi 9.45 6.41 1.47 0.2364 c ‒84.12 64.53 ‒1.31 0.2834 lpi lecpi ‒20.50 13.47 ‒1.52 0.2027 c 195.45 121.45 1.61 0.1828 Table 7: Error correction (short run) model coefficients Coefficient Model 1 Model 2 Model 3 Model 4 Model 5 Model 6 Variable ∆lgdpm ∆lgdpd ∆lepetecgdp ∆lecigdp ∆lecmigdp ∆leccgdp ∆lgdpm(t-1) 0.39 ∆leci(t-1) 0.25 ect(t-1) −0.04 ∆lgdpd(t-1) 0.59** ∆leci(t-1) 0.29 ect(t-1) −0.06 ∆lepegdp(t-1) 0.44* ∆lepeitec(t-1) 0.06 ect(t-1) −0.03 ∆ligdp(t-1) 0.33 ∆lecii(t-1) 0.005 ect(t-1) −0.03 ∆lmigdp(t-1) 0.23 ∆lecmii(t-1) 0.005 ect(t-1) −0.08 ∆lcgdp(t-1) 0.23 ∆liecc(t-1) 0.23 ect(t-1) −0.16 Constant 0.09 0.05 0.08 0.12 0.17 0.12* Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020442 The rest of the variables are stationary I(1). In No Intercept & No Trend case only PI I(2) is stationary. The rest of the variables are stationary I(I) (A.Table 2). According to Kwiatkowski−Phillips−Schmidt−Shin test statistics most of the variables are I(0). All these results are available for next assessment and methods. Reliant on the enumerated test results, variable are accepted as I(1) (A.Table 3). It means that all above-mentioned methods are applicable. As mentioned above, during application process of ARDL cointegration method, one of the important issues while establishing a model is to identify optimum lag length. At this time, the most important factor is to eliminate the subsequent correlation problem in selected optimum model and keep the minimum of SBC information criteria value. 5.2. VAR Lag Order Selection Criteria In order to determine optimal lag for ARDL model, VAR Lag Order Selection Criteria was employed and we got the below-mentioned results (Table 4). Table 5 illustrates whether cointegration relations between variables exist or not. Thus, there are cointegration relations among electric energy consumption per year (ECI) and GDP in manat (GDPM) and in dollar (GDPD), electric energy consumption of electric energy production entities (EPEITEC) and their GDP (EPEGDP), electric energy consumption in construction (IECC) and its GDP (CGDP), electric energy consumption in agriculture, hunting and forestry (ECAHFI) and their GDP (AHFGDP), electric energy consumption in other, commercial and public service entities (ECCPSI) and their GDP (CPSGDP) and electric energy consumption of people (ECPI) and People’s income (PI). In other words, there are long-term relations. F‒statistics factors are above the minimum indicators of 5% according to Narayan (2005) table. However, there are no cointegration relations among electric energy consumption in industry (ECII) and its GDP (IGDP), electric energy consumption in mining (ECMII) and its GDP (MIGDP) and electric energy consumption in telecommunication, transport and warehouse (ECTWTI) and their GDP (TWTGDP). Cointeq = lN ‒ a × lM + c According to the table, electric energy consumption causes the increase of GDP (Table 6). Having a closer look at the table: Energy consumption GDP Energy consumption increases (ECI) 1% per year GDP in manat increases 11.88% Energy consumption increases (ECI) 1% per year GDP in dollar increases 11.91% Energy producing entities increases their energy consumption 1%. (EPEITEC) GDP increases 4.47% in electric energy production Energy consumption in mining industry increases 1% (ECMII) GDP increases 11.57% in mining industry Increase of energy consumption in construction (IECC) GDP increases 1.31% in construction Energy consumption in agriculture, hunting and forestry increases 1% (ECAHFI) GDP increases 82.90% in agriculture, hunting and forestry Energy consumption in other, commercial and public service increases 1% (ECCPSI) GDP increases 9.45% in commercial and public service Energy consumption in industry increases 1% (ECII) GDP decreases 5.3% in industry Energy consumption in transport, warehouse and telecommunication increases 1% (ECTWTI) GDP decreases 28.63% in transport, warehouse and telecommunication Energy consumption of people increases 1% (ECPI) People’s income decreases 20.50% In general, there are valuable from economic standpoint. Except the equations refer to relations among the energy consumption in industry (ECII) and GDP and the energy consumption in transport, warehouse and telecommunication (ECTWTI) and their GDP. The main reason for this is other factors that play key roles in the augmentation of GDP. Referring to A.Tables 4 and 5, we can mention that coefficients are 5% 1% and 0.1% significant. 5.3. Error Correction (Short Run) Model This table reveals the results of short-term and ECM model. The results are in the following: There is a positive relation between GDP and electric energy consumption in all models. GDPD coefficient is significant at the level of 1% in correlation model between GDPD and total electric energy consumption (ECI). (model 1). Besides, Table 7a: Error correction (short run) model coefficients Coefficient Model 7 Model 8 Model 9 Model 10 Variable ∆lecahfgdp (t-1) ∆lectwtgdp (t‑1) ∆leccpsgdp (t-1) ∆logpi (t-1) ∆lahfgdp(t-1) 0.003 ∆lecahfi(t-1) 0.15 ect(t-1) −0.03 ∆ltwtgdp(t-1) 0.1 ∆lectwti(t-1) −0.18 ect(t-1) −0.01 ∆lcpsgdp(t-1) 0.22 ∆leccpsi(t-1) 0.09 ect(t-1) −0.04 ∆lpi(t-1) 0.45 ∆lecpi(t-1) −0.15 ect(t-1) −0.06 Constant 0.09* 0.13 0.12* 0.08* Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 443 (EPEGDP) coefficient is significant at the level of 5% in the model between energy consumption in electric energy producing entities (EPEITEC) and their GDP (model 3). On the other hand, ect coefficient is negative (−) for all. According to the models, velocity to balance in a long term is 4% (model 1), 6% (model 2), 3% (model 3), 3% (model4), 8% (model 5), 16% (model 6), 3% (model 7), 2% (model 8), 4% (model 9), 9% (model 10) (Tables 7 and 7a). Although ect coefficients are insignificance in these models, their negativity substantiates the existence of cointegration relations proposed by Paseran and others (2001). Having positive relation in these models shows the role of electric energy and its consumption in the increase of GDP for new economic growth. Some models for ARDL models (model 1-3 and 6) are 5% 1% and 0.1% significant. Regression equations are adequate. It also passes all the diagnostic tests against serial correlation (Durbin Watson test and Breusch-Godfrey test), heteroscedasticity (White Heteroskedasticity Test), and normality of errors (Jarque-Bera test). The Ramsey RESET test also suggests that the model is well specified. All the results of these tests are shown in Table 8 and 8a. The stability of the long- run coefficient is tested by the short-run dynamics. Once the ECM model given by equations (Table 7 and 7a) has been estimated, the cumulative sum of recursive residuals (CUSUM) and the CUSUM of square (CUSUMSQ) tests are applied to assess the parameter stability (Pesaran and Pesaran (1997). A.Figure 2 plot the results for CUSUM and CUSUMSQ tests. The results indicate the absence of any instability of the coefficients because the plot of the CUSUM and CUSUMSQ statistic fall inside the critical bands of the 5% confidence interval of parameter stability However, non-stability in model 2 and model 3 was observed (A.Figure 2). Table 8: Diagnostic test results (LM version) Ramsey RESET Test (t‒statistic) Normality Test (Jarque‒Bera) JB Heteroskedasticity Test: ARCH χ2 Heteroskedasticity Test: Breusch−Pagan−Godfrey Breusch‒Godfrey Serial Correlation LM Test: χ2 R2 D_W lgdpm 0.31 0.53 0.007 10.95 7.71 0.99 2.65 0.61 0.77 0.93 0.45 0.02 lgdpd 1.33 0.51 0.81 15.77 12.88 0.99 2.29 0.29 0.77 0.37 0.11 0.002 lepegdp 0.52 0.63 0.001 14.06 11.97 0.99 3.01 0.55 0.72 0.97 0.37 0.003 ligdp 7.60 14.13 0.32 5.23 6.83 0.98 2.05 0.07 0.0008 0.57 0.95 0.03 lmigdp 1.77 0.61 0.29 10.47 11.10 0.97 2.97 0.25 0.77 0.59 0.49 0.003 lcgdp 0.18 0.12 2.49 14.35 16.09 0.99 3.15 0.71 0.95 0.11 0.35 0.0003 lahfgdp 0.03 0.12 2.61 13.70 5.51 0.99 2.63 0.85 0.95 0.11 0.13 0.06 ltwtgdp 2.95 0.53 0.0008 6.89 9.29 0.99 2.17 0.16 0.77 0.97 0.81 0.01 lcpsgdp 8.31 3.59 0.44 8.69 7.81 0.99 1.27 0.10 0.17 0.51 0.80 0.02 lpi 1.33 0.77 1.45 11.99 2.71 0.99 1.88 0.20 0.69 0.23 0.45 0.25 Table 8a: Diagnostic test results (F version) Ramsey RESET Test (F‒Statistic) Normality Test (Jarque‒Bera) JB Heteroskedasticity Test: ARCH Heteroskedasticity Test: Breusch−Pagan−Godfrey Breusch‒Godfrey Serial Correlation LM Test lgdpm F (1,4) 0.31 N/A F (1,14) 0.006 F (11,5) 0.82 F (2,3) 1.25 0.61 N/A 0.95 0.63 0.40 lgdpd F (1, 6) 1.33 N/A F (1,15) 0.77 F (10,7) 4.87 F (2,5) 6.29 0.29 N/A 0.40 0.02 0.04 lepegdp F (1, 2) 0.52 N/A F (1,14) 0.001 F (13,3) 1.10 F (2,1) 1.18 0.55 N/A 0.97 0.53 0.55 ligdp F (1, 3) 7.60 N/A F (1,14) 0.29 F (12,4) 0.14 F (2,2) 0.67 0.07 N/A 0.60 0.99 0.59 lmigdp F (1, 4) 1.77 N/A F (1,14) 0.26 F (11,5) 0.71 F (2,3) 2.82 0.25 N/A 0.61 0.69 0.20 lcgdp F (1, 2) 0.18 N/A F (1,14) 2.57 F (13,3) 1.25 F (2,1) 8.92 0.71 N/A 0.13 0.48 0.2303 lahfgdp F (1, 6) 0.03 N/A F (1,14) 2.71 F (9,7) 3.23 F (2,5) 1.18 0.85 N/A 0.12 0.06 0.38 ltwtgdp F (1, 4) 2.97 N/A F (1,14) 0.0006 F (11,5) 0.31 F (2,3) 1.81 0.16 N/A 0.9770 0.95 0.31 lcpsgdp F (1, 2) 8.31 N/A F (1,14) 0.40 F (13,3) 0.24 F (2,1) 0.42 0.10 N/A 0.53 0.97 0.71 lpi F (1, 15) 1.77 N/A F (1,18) 1.41 F (12,4) 0.77 F (2,14) 1.05 0.20 N/A 0.25 0.69 0.38 Legend: N/A‒Not Applicable Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020444 6. CONCLUSION Energy and especially electricity is one of the main factors of the development of society. From this perspective, energy and electricity consumption is essential in Azerbaijan too. We have achieved some results from the research that electricity consumption plays an important role in economic growth. Electricity is also important as an economic resource. Although the relationship between electricity consumption and GDP growth is not strong, we can mention the followings: there is a positive dependency between total electricity consumption and GDP in manat and dollar, as well as electricity consumption in electricity producing entities such as mining, construction, agriculture, hunting and forestry, commercial and public service and others and GDP in those sectors. Conversely, there is a negative dependency between electricity consumption in industry, transportation, warehouse and telecommunication and GDP. On the contrary, the opposite dependency was observed between electricity consumption of population and people’s income. The positive income was also observed between electricity consumption and GDP according to ECM model results in a short term. Having a positive relationship in models shows that electricity consumption plays an important role in GDP growth. So, the analysis has revealed that there is a weak relationships betwen either the electricity consumption and GDP in the Republic or in different sectors of economy. From this perspective, we recommend not to waste electricity consumption. REFERENCES Adeyemi, A.O., Ayomide, A. (2013), Electricity consumption and economic growth in Nigeria. Journal of Business Management and Applied Economics, 2(4), 1-14. Angus, D. (2015), Measuring and Understanding Behavior, Welfare, and Poverty. Prize Lecture. Available from: https://www.nobelprize.org/ uploads/2018/06/deaton-lecture.pdf. Appiah, M.O. (2018), Investigating the multivariate granger causality between energy consumption, economic growth and CO2 emissions in Ghana. Energy Policy, 112, 198-208. Aslan, A. (2014), Electricity consumption, labor force and GDP in Turkey: Evidence from multivariate granger causality. Journal Energy Sources, Part B: Economics, Planning, and Policy, 9(2), 174-182. Asteriou, D., Hall, S.G. (2007), Applied Econometrics; Revised Edition. London, UK: Red Globe Press. p552. Available from: https://www.data.worldbank.org/indicator/EG.USE. ELEC.KH.PC. Available from: https://www.stat.gov.az. Basiru, O.F. (2014), Energy consumption and economic growth nexus: Panel co-integration and causality tests for Sub-Saharan Africa. Journal of Energy South. Africa, 25(4), 93-100. Bekareva, S.V., Meltenisova, E.N., Gsysa, J.G.A. (2017), Evaluation of the role of renewables consumption on economic growth of the U.S. Regions International Journal of Energy Economics and Policy, 7(2), 160-171. Fuinhas, J.A., António, C., Marques, C. (2012), Energy consumption and economic growth nexus in Portugal, Italy, Greece, Spain and Turkey: An ARDL bounds test approach (1965-2009). Energy Economics, 34(2), 511-517. Heij, C., Heij, C., de Boer, P., Franses, P.H., Kloek, T., van Dijk, H.K. (2005), Econometric Methods with Applications in Business and Economics. Oxford, UK: Oxford University Press. Hill, R.C., Griffiths, W.E., Judge, G.G., Reiman, M.A. (2001), Undergraduate Econometrics. 2nd ed. New York, USA: John Wiley and Sons, Inc. Ibrahiem, D.M. (2018), Investigating the causal relationship between electricity consumption and sectoral outputs: Evidence from Egypt. Energy Transitions December, 2(1-2), 31-48. Junsheng, H., Tan, P.P., Goh, K.L. (2018), Linear and Nonlinear Causal Relationship between Energy Consumption and Economic Growth in China: New Evidence Based on Wavelet Analysis Published. Kamal, R. (2017), Dhungel linkages between electricity consumption and economic growth: Evidences from South Asian economies. HYDRO Nepal. Journal Journal of Water Energy and Environment, 20, 18-22. Kasperowicz, R. (2014), Electricity consumption and economic growth: Evidence from Poland. Journal of International Studies, 7(1), 46-57. Kwiatkowski, D., Phillips, P., Schmidt, P., Shin, Y. (1992), Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? Journal Econom, 54, 159-178. Lefteris, T., Theologos, D. (2011), Revisiting residential demand for electricity in Greece: New evidence from the ARDL approach to cointegration analysis. Empirical Economics, 41(2), 511-531. Lira, S., Mamofokeng, M. (2016), Evidence on the nexus between electricity consumption and economic growth through empirical investigation of Uganda. Review of Economic and Business Studies, 8, 149-165. Liu, Y. (2009), Exploring the relationship between urbanization and energy consumption in China using ARDL (autoregressive distributed lag) and FDM (factor decomposition model). Energy, 34(11), 1846-1854. Lu, W.C. (2017), Electricity consumption and economic growth: Evidence from 17 Taiwanese industries. Sustainability, 9(1), 50. Mackinnon, J. (1996), Numerical distribution functions for unit root and cointegration tests. Journal Appl Econom, 11, 601-618. Marius-Corneliu, M., Marin, D., Aura-Gabriela, S., Cristian, S. (2018), Renewable energy consumption and economic growth. Causality relationship in central and Eastern European countries. PLoS One, 13(10), e0202951. Masako, I., Zijian, W. (2016), The long-run causal relationship between electricity consumption and real GDP: Evidence from Japan and Germany. Journal of Policy Modeling, 38(5), 767-784. Molem, C.S., Ndifor, R.T. (2016), The effect of energy consumption on economic growth in Cameroon. Asian Economic and Financial Review, 6(9), 510-521. Muhammad, K.A.K., Nur-Syazwani, M. (2018), The impact of electricity consumption on economic growth in Malaysia: Evidence from ARDL bounds testing. Jurnal Ekonomi Malaysia, 52(1), 205-214. Muhammad, S., Chor, F.T., Muhammad, S.S. (2011), Electricity consumption and economic growth nexus in Portugal using cointegration and causality approaches. Energy Policy, 39(6), 3529-3536. Muhammad, S., Hooi, H.L. (2012), The dynamics of electricity consumption and economic growth: A revisit study of their causality in Pakistan. Energy, 39(1), 146-153. Mukhtarov, S., Mikayilov, J.I., İsmayılov, V. (2017), The relationship between energy consumption and economic growth: Evidence from Azerbaijan. International Journal of Energy Economics and Policy, 7(6), 32-38. Mukhtarov, S., Mikayilov, J.I., Mammadov, J., Mammadov, E. (2018), The impact of financial development on energy consumption: Evidence from an oil-rich economy. Energies, 11, 1536. Muradov, A.J., Hasanli, Y.H., Hajiyev, N.O. (2019), World Market Price of Oil: Impacting Factors and Forecasting. Berlin: Springer Briefs in Economics. p194. Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 445 Mutascu, M. (2016), A bootstrap panel granger causality analysis of energy consumption and economic growth in the G7 countries. Renewable and Sustainable Energy Reviews, 63, 166-171. Narayan, P.K. (2005), The saving and investment nexus for China: E v i d e n c e f r o m c o i n t e g r a t i o n t e s t s . A p p l i e d e c o n o m i c s , 37(17), 1979-1990. Available from: https://www.mafiadoc. com/the-saving-and-investment-nexus-for-china-evidence- _59fed1701723dd96f5285a02.html. Narayan, P.K., Narayan, S., Popp, S. (2010), Does electricity consumption panel Granger cause GDP? A new global evidence. Applied Energy, 87(10), 3294-3298. Nicholas, A., James, E.P. (2011), A dynamic panel study of economic development and the electricity consumption-growth nexus. Energy Economics, 33(5), 770-781. Nicholas, M.O. (2009), Energy consumption and economic growth nexus in Tanzania: An ARDL bounds testing approach. Energy Policy, 37(2), 617-622. Ömer, E., Bayrak, M. (2017), Does more energy consumption support economic growth in net energy-importing countries? Journal of Economics, Finance and Administrative Science, 22(42), 75-98. Ozturk, I., Ali, A. (2010), The causal relationship between energy consumption and GDP in Albania, Bulgaria, Hungary and Romania: Evidence from ARDL bound testing approach. Applied Energy, 87(6), 1938-1943. Ozturk, I., Ali, A. (2011), Electricity consumption and real GDP causality nexus: Evidence from ARDL bounds testing approach for 11 MENA countries. Applied Energy, 88(8), 2885-2892. Pempetzoglou, M. (2014), Electricity consumption and economic growth: A linear and nonlinear causality investigation for Turkey. International Journal of Energy Economics and Policy, 4(2), 263-273. Pesaran, M.H., Shin, Y., Smith, R.J. (2001), Bounds testing approaches to the analysis of level relationships. Journal of Applied Econometrics, 16(3), 289-326. Ramazan, S., Bradley, T.E., Ugur, S. (2008), The relationship between disaggregate energy consumption and industrial production in the United States: An ARDL approach. Energy Economics, 30(5), 2302-2313. Ranjan, A., Umer, J.B., Hasnat, T., Koçoglu, M. (2017), Renewable and non-renewable energy consumption and economic growth: Empirical evidence from panel error correction model. Jindal Journal of Business Research, 6(1),76-85. Richard, F.H., Jonathan, G.K. (2015), Electricity consumption and economic growth: A new relationship with significant consequences? The Electricity Journal, 28(9), 72-84. Slim, M., Mohamed, B.A. (2015), The importance of electricity consumption in economic growth: The example of African nations. The Journal of Energy and Development, 40(1/2), 99-110. Śmiech, S., Monika, P. (2014), Energy consumption and economic growth in the light of meeting the targets of energy policy in the EU: The bootstrap panel granger causality approach. Energy Policy, 71, 118-129. Turgut, F.T., Resatoglu, N.G. (2016), Energy consumption, electricity, and GDP causality; the case of Russia, 1990-2011. Procedia Economics and Finance, 39, 653-659. Uyar, U., Gökçe, A. (2017), The relationship between energy consumption and growth in Emerging markets by panel quantile regression: Evidence from VISTA countries. Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 27, 364-373. Vidadili, N., Suleymanov, E., Bulut, C., Mahmudlu, C. (2017), Transition to renewable energy and sustainable energy development in Azerbaijan. Renewable and Sustainable Energy Reviews, 80, 1153-1161. Wahid, M.M., Mahmudul, A.M., Noman, A.H. M., Ozturk, I. (2019), Dynamics of technological innovation, energy consumption, energy price and economic growth in Denmark. Environmental Progress and Sustainable Energy, 38(1), 22-29. Yang, C.L., Lin, H.P., Chang, C.H. (2010), Linear and nonlinear causality between sectoral electricity consumption and economic growth: Evidence from Taiwan. Energy Policy, 38(11), 6570-6573. Yemane, W.R. (2014), Electricity consumption and economic growth in transition countries: A revisit using bootstrap panel granger causality analysis. Energy Economics, 44, 325-330. Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020446 APPENDIX (Contd...) Model Variable ADF−Stat Levels of critical values Lag P-value Stationarity İntegrir I (0,1,2) 1% 5% 10% With intercept only At level form leci −3.01* −3.80 −3.02 −2.65 2 0.0507 S I (0) lepeitec −1.35 −3.77 −3.00 −2.64 0 0.5881 N/S I (1) lecii −2.83* −3.77 −3.00 −2.64 0 0.0694 S I (0) lecmii −1.71 −3.77 −3.00 −2.64 0 0.4112 N/S I (1) liecc −0.92 −3.77 −3.00 −2.64 0 0.7596 N/S I (1) lecahfi −2.76* −3.77 −3.00 −2.64 0 0.0797 S I (0) lectwti −1.12 −3.77 −3.00 −2.64 0 0.6849 N/S I (1) leccpsi −2.30 −3.77 −3.00 −2.64 0 0.1798 N/S I (1) lecpi lgdpm −0.88 −3.77 −3.01 −2.65 1 0.7739 N/S I (1) lgdpd −1.26 −3.77 −3.01 −2.65 1 0.6243 N/S I (2) lepegdp −0.37 −3.77 −3.00 −2.64 0 0.8983 N/S I (1) ligdp −1.62 −3.77 −3.00 −2.64 0 0.4557 N/S I (1) lmigdp −1.99 −3.77 −3.00 −2.64 0 0.2876 N/S I (1) lcgdp −2.39 −3.77 −3.00 −2.64 0 0.1547 N/S I (1) lahfgdp −0.13 −3.77 −3.00 −2.64 0 0.9334 N/S I (1) ltwtgdp −0.01 −3.77 −3.00 −2.64 0 0.9502 N/S I (1) lcpsgdp −0.81 −3.77 −3.00 −2.64 0 0.7961 N/S I (1) lpi −0.83 −3.77 −3.01 −2.65 1 0.7874 N/S I (1) With intercept only At first differencing dleci −3.88*** −3.77 −3.01 −2.65 0 0.0081 S I (0) dlepeitec −4.12*** −3.77 −3.01 −2.65 0 0.0048 S I (0) dlecii −3.83** −3.85 −3.04 −2.66 3 0.0105 S I (0) dlecmii −4.85*** −3.77 −3.01 −2.65 0 0.0010 S I (0) dliecc −5.06*** −3.77 −3.01 −2.65 0 0.0006 S I (0) dlecahfi −3.65** −3.77 −3.01 −2.65 0 0.0135 S I (0) dlectwti −6.60*** −3.77 −3.01 −2.65 0 0.0000 S I (0) dleccpsi −5.03*** −3.77 −3.01 −2.65 0 0.0007 S I (0) dlpi −3.29*** −3.77 −3.01 −2.65 0 0.0291 S I (0) dlgdpm −2.77* −3.77 −3.01 −2.65 0 0.0771 S I (0) dlgdpd −2.25 −3.77 −3.01 −2.65 0 0.1974 N/S I (1) ddlgdpd −4.17*** −3.80 −3.02 −2.65 0 0.0046 S I (0) dlepegdp −3.25** −3.77 −3.01 −2.65 0 0.0312 S I (0) dligdp −3.06** −3.77 −3.01 −2.65 0 0.0451 S I (0) dlmigdp −3.39** −3.77 −3.01 −2.65 0 0.0231 S I (0) dlcgdp −5.02*** −3.77 −3.01 −2.65 0 0.0007 S I (0) dlahfgdp −4.02*** −3.77 −3.01 −2.65 0 0.0059 S I (0) dltwtgdp −4.82*** −3.77 −3.01 −2.65 0 0.0010 S I (0) dlcpsgdp −3.38** −3.77 −3.01 −2.65 0 0.0236 S I (0) dlpi −2.36 −3.77 −3.01 −2.65 0 0.1642 N/S I (1) ddlpi −4.17*** −3.80 −3.02 −2.65 0 0.0021 S I (0) With intercept and trend At level form leci −3.69* −4.44 −3.63 −3.25 2 0.0466 S I (0) lepeitec −2.29 −4.44 −3.63 −3.25 0 0.4217 N/S I (1) lecii −5.26*** −4.44 −3.63 −3.25 3 0.0024 S I (0) lecmii −2.63 −4.44 −3.63 −3.25 0 0.2695 N/S I (1) liecc −2.10 −4.44 −3.63 −3.25 0 0.5152 N/S I (1) lecahfi −1.67 −4.44 −3.63 −3.25 0 0.7299 N/S I (1) lectwti −2.86 −4.44 −3.63 −3.25 0 0.1920 N/S I (1) leccpsi −2.81 −4.44 −3.63 −3.25 0 0.2063 N/S I (1) lecpi −2.45 −4.44 −3.63 −3.25 0 0.3424 N/S I (1) lgdpm −1.55 −4.47 −3.65 −3.26 1 0.7782 N/S I (2) lgdpd −1.81 −4.47 −3.65 −3.26 1 0.6591 N/S I (2) lepegdp −2.12 −4.47 −3.65 −3.26 1 0.5029 N/S I (2) ligdp −0.60 −4.44 −3.63 −3.25 0 0.9685 N/S I (2) lmigdp −0.80 −4.44 −3.63 −3.25 0 0.9501 N/S I (1) lcgdp −2.71 −4.47 −3.65 −3.26 1 0.2349 N/S I (1) lahfgdp −3.00 −4.47 −3.65 −3.26 1 0.1545 N/S I (1) ltwtgdp −2.17 −4.44 −3.63 −3.25 0 0.4776 N/S I (1) lcpsgdp −2.32 −4.47 −3.65 −3.26 1 0.4044 N/S I (1) lpi −1.92 −4.47 −3.65 −3.26 1 0.6094 N/S I (2) A.Table 1: ADF unit root test Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 447 dleci −3.76** −4.47 −3.65 −3.26 0 0.0397 S I (0) dlepeitec −4.01** −4.47 −3.65 −3.26 0 0.0251 S I (0) dlecii −3.71** −4.57 −3.69 −3.29 3 0.0477 S I (0) dlecmii −4.77*** −4.47 −3.65 −3.26 0 0.0054 S I (0) dliecc −5.35*** −4.47 −3.65 −3.26 0 0.0017 S I (0) dlecahfi −4.72*** −4.47 −3.65 −3.26 0 0.0060 S I (0) dlectwti −6.45*** −4.47 −3.65 −3.26 0 0.0002 S I (0) dleccpsi −4.87*** −4.47 −3.65 −3.26 0 0.0044 S I (0) dlpi −3.42* −4.47 −3.65 −3.26 0 0.0753 S I (0) dlgdpm −2.77 −4.47 −3.65 −3.26 0 0.2166 N/S I (1) dlgdpmd −5.30*** −4.49 −3.65 −3.26 0 0.0020 S I (0) dlgdpd −2.36 −4.47 −3.65 −3.26 2 0.3853 N/S I (1) ddlgdpd −3.85** −4.53 −3.67 −3.29 1 0.0359 S I (0) dlepegdp −3.09 −4.47 −3.65 −3.26 0 0.1331 N/S I (1) ddlepegdp −5.48*** −4.53 −3.67 −3.29 1 0.0016 S I (0) dlecigdp −3.16 −4.47 −3.65 −3.26 0 0.1185 N/S I (1) ddligdp −5.22*** −4.49 −3.65 −3.26 0 0.0024 S I (0) dlmigdp −3.60** −4.47 −3.65 −3.26 0 0.0543 S I (0) dlcgdp −4.61*** −4.47 −3.65 −3.26 0 0.0075 S I (0) dlahfgdp −3.99** −4.47 −3.65 −3.26 0 0.0258 S I (0) dltwtgdp −4.65*** −4.47 −3.65 −3.26 0 0.0068 S I (0) dlcpsgdp −3.32* −4.47 −3.65 −3.26 0 0.0905 S I (0) dlpi −2.23 −4.47 −3.65 −3.26 0 0.4457 N/S I (1) ddlpi −4.61*** −4.53 −3.67 −3.29 1 0.0085 S I (0) No Intercept & No Trend At level form leci 0.77 −2.67 −1.96 −1.61 0 0.8758 N/S I (1) lepeitec 0.71 −2.67 −1.96 −1.61 0 0.8665 N/S I (1) lecii −0.06 −2.67 −1.96 −1.61 0 0.6517 N/S I (1) lecmii 0.77 −2.67 −1.96 −1.61 0 0.8697 N/S I (1) liecc 0.36 −2.67 −1.96 −1.61 0 0.7814 N/S I (1) lecahfi −1.22 −2.67 −1.96 −1.61 0 0.1954 N/S I (1) lectwti −1.61 −2.67 −1.96 −1.61 1 0.1004 N/S I (1) leccpsi 0.12 −2.67 −1.96 −1.61 0 0.7115 N/S I (1) lecpi 0.65 −2.67 −1.96 −1.61 0 0.8499 N/S I (1) lgdpm 1.77 −2.67 −1.96 −1.61 1 0.9775 N/S I (1) lgdpd 0.77 −2.67 −1.96 −1.61 1 0.8765 N/S I (1) lepegdp 1.19 −2.67 −1.96 −1.61 0 0.9350 N/S I (1) ligdp 1.47 −2.67 −1.96 −1.61 1 0.9597 N/S I (1) lmigdp 1.45 −2.67 −1.96 −1.61 1 0.9578 N/S I (1) lcgdp 2.62 −2.67 −1.96 −1.61 0 0.9965 N/S I (1) lahfgdp 4.41 −2.67 −1.96 −1.61 0 1.0000 N/S I (1) ltwtgdp 3.69 −2.67 −1.96 −1.61 0 0.9997 N/S I (1) lcpsgdp 4.69 −2.67 −1.96 −1.61 0 1.0000 N/S I (1) lpi 1.80 −2.67 −1.96 −1.61 1 0.9789 N/S I (2) No Intercept & No Trend At First differencing dleci −3.85*** −2.67 −1.96 −1.61 0 0.0006 S I (0) dlepeitec −4.11*** −2.67 −1.96 −1.61 0 0.0003 S I (0) dlecii −3.85*** −2.69 −1.96 −1.61 3 0.0006 S I (0) dlecmii −4.85*** −2.67 −1.96 −1.61 0 0.0000 S I (0) dliecc −5.21*** −2.67 −1.96 −1.61 0 0.0000 S I (0) dlecahfi −3.69*** −2.67 −1.96 −1.61 0 0.0008 S I (0) dlectwti −6.19*** −2.67 −1.96 −1.61 0 0.0000 S I (0) dleccpsi −5.09*** −2.67 −1.96 −1.61 0 0.0000 S I (0) dlecpi −3.41*** −2.67 −1.96 −1.61 0 0.0017 S I (0) dlgdpm −1.83* −2.67 −1.96 −1.61 0 0.0640 S I (0) dlgdpd −2.05** −2.67 −1.96 −1.61 0 0.0419 S I (0) dlepegdp −3.02*** −2.67 −1.96 −1.61 0 0.0044 S I (0) dligdp −2.39*** −2.67 −1.96 −1.61 0 0.0197 S I (0) dlmigdp −2.71*** −2.67 −1.96 −1.61 0 0.0090 S I (0) dlcgdp −4.52*** −2.67 −1.96 −1.61 0 0.0001 S I (0) dlahfgdp −2.71*** −2.67 −1.96 −1.61 0 0.0093 S I (0) A.Table 1: (Continued) (Contd...) Model Variable ADF−Stat Levels of critical values Lag p-value Stationarity İntegrir I (0,1,2) 1% 5% 10% With intercept and trend At first differencing Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020448 (Contd...) dltwtgdp −2.69*** −2.67 −1.96 −1.61 0 0.0099 S I (0) dlcpsgdp −2.15** −2.67 −1.96 −1.61 0 0.0330 S I (0) dlpi −1.15 −2.67 −1.96 −1.61 0 0.2192 N/S I (1) ddlpi −4.67*** −2.69 −1.95 −1.60 0 0.0001 S I (0) ADF denotes the Augmented Dickey‒Fuller single root system respectively. The maximum lag order is 3. The optimum lag order is selected based on the Shwarz criterion automatically; ***, ** and *indicate rejection of the null hypotheses at the 1%, 5% and 10% significance levels respectively. The critical values are taken from MacKinnon (Mackinnon, 1996). Assessment period: 1995-2017. S: Stationarity; N/S: No stationarity A.Table 1: (Continued) Model Variable ADF−Stat Levels of critical values Lag p-value Stationarity İntegrir I (0,1,2) 1% 5% 10% No Intercept & No Trend At First differencing Model Variable PP−test statistic Levels of critical values Bandwidth P-value Stationarity Integrir I (0,1,2) 1% 5% 10% With Intercept only At level form leci −1.60 −3.77 −3.01 −2.64 2 0.4646 N/S I (1) lepeitec −1.31 −3.77 −3.01 −2.64 0 0.5881 N/S I (1) lecii −2.84* −3.77 −3.01 −2.64 1 0.0689 S I (0) lecmii −1.71 −3.77 −3.01 −2.64 0 0.4112 N/S I (1) liecc −0.92 −3.77 −3.01 −2.64 1 0.7622 N/S I (1) lecahfi −2.69* −3.77 −3.01 −2.64 1 0.0900 S I (0) lectwti −0.83 −3.77 −3.01 −2.64 1 0.7896 N/S I (1) leccpsi −1.41 −3.77 −3.01 −2.64 2 0.5596 N/S I (1) lecpi −2.33 −3.77 −3.01 −2.64 2 0.1705 N/S I (1) lgdpm −1.18 −3.77 −3.01 −2.64 2 0.6598 N/S I (1) lgdpd −1.56 −3.77 −3.01 −2.64 2 0.4836 N/S I (1) lepegdp −0.37 −3.77 −3.01 −2.64 0 0.8983 N/S I (1) ligdp −1.62 −3.77 −3.01 −2.64 0 0.4557 N/S I (1) lmigdp −1.89 −3.77 −3.01 −2.64 1 0.3265 N/S I (1) lcgdp −2.21 −3.77 −3.01 −2.64 1 0.2095 N/S I (1) lahfgdp −0.17 −3.77 −3.01 −2.64 1 0.9290 N/S I (1) ltwtgdp −0.02 −3.77 −3.01 −2.64 1 0.9465 N/S I (1) lcpsgdp −0.81 −3.77 −3.01 −2.64 0 0.7961 N/S I (1) lpi −0.11 −3.77 −3.01 −2.64 2 0.9356 N/S I (2) With Intercept only At First differencing dleci −3.92*** −3.78 −3.01 −2.65 2 0.0073 S I (0) dlepeitec −4.12*** −3.78 −3.01 −2.65 1 0.0048 S I (0) dlecii −6.71*** −3.78 −3.01 −2.65 1 0.0000 S I (0) dlecmii −4.99*** −3.78 −3.01 −2.65 3 0.0007 S I (0) dliecc −5.01*** −3.78 −3.01 −2.65 2 0.0007 S I (0) dlecahfi −3.65** −3.78 −3.01 −2.65 1 0.0136 S I (0) dlectwti −6.61*** −3.78 −3.01 −2.65 0 0.0000 S I (0) dleccpsi −5.78*** −3.78 −3.01 −2.65 7 0.0001 S I (0) dlecpi −3.29*** −3.78 −3.01 −2.65 2 0.0293 S I (0) dlgdpm −2.78* −3.78 −3.01 −2.65 2 0.0771 S I (0) dlgdpd −2.30 −3.78 −3.01 −2.65 1 0.1798 N/S I (1) ddlgdpd −4.17*** −3.80 −3.02 −2.65 8 0.0047 S I (0) dlepegdp −3.18** −3.78 −3.01 −2.65 2 0.0358 S I (0) dligdp −3.09** −3.78 −3.01 −2.65 1 0.0422 S I (0) dlmigdp −3.41** −3.78 −3.01 −2.65 1 0.0223 S I (0) dlcgdp −5.02*** −3.78 −3.01 −2.65 0 0.0007 S I (0) dlahfgdp −4.02*** −3.78 −3.01 −2.65 0 0.0059 S I (0) dltwtgdp −4.77*** −3.78 −3.01 −2.65 1 0.0011 S I (0) dlcpsgdp −3.31** −3.78 −3.01 −2.65 3 0.0273 S I (0) dlpi −2.36 −3.78 −3.01 −2.65 2 0.1623 N/S I (1) ddlpi −5.42*** −3.80 −3.02 −2.65 11 0.0003 S I (0) With Intercept & Trend At Level Form leci −2.15 −4.44 −3.63 −3.25 2 0.4927 N/S I (1) lepeitec −2.29 −4.44 −3.63 −3.25 0 0.4217 N/S I (1) A.Table 2: PP unit root test Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 449 lecii −3.57* −4.44 −3.63 −3.25 6 0.0565 S I (0) lecmii −2.63 −4.44 −3.63 −3.25 0 0.2695 N/S I (1) liecc −2.06 −4.44 −3.63 −3.25 1 0.5402 N/S I (1) lecahfi −1.77 −4.44 −3.63 −3.25 6 0.6807 N/S I (1) lectwti −2.99 −4.44 −3.63 −3.25 2 0.1579 N/S I (1) leccpsi −2.81 −4.44 −3.63 −3.25 2 0.2077 N/S I (1) lecpi −2.40 −4.44 −3.63 −3.25 2 0.3680 N/S I (1) lgdpm −0.99 −4.44 −3.63 −3.25 2 0.9253 N/S I (1) lgdpd −0.41 −4.44 −3.63 −3.25 2 0.9803 N/S I (1) lepegdp −2.12 −4.44 −3.63 −3.25 1 0.5081 N/S I (1) ligdp −0.83 −4.44 −3.63 −3.25 1 0.9458 N/S I (1) lmigdp −0.95 −4.44 −3.63 −3.25 1 0.9309 N/S I (1) lcgdp −3.31* −4.44 −3.63 −3.25 2 0.0913 S I (0) lahfgdp −1.71 −4.44 −3.63 −3.25 0 0.7014 N/S I (1) ltwtgdp −2.40 −4.44 −3.63 −3.25 2 0.3680 N/S I (1) lcpsgdp −1.77 −4.44 −3.63 −3.25 1 0.6712 N/S I (1) lpi −1.75 −4.44 −3.63 −3.25 2 0.6914 N/S I (2) With Intercept & Trend At First differencing dleci −3.82** −4.47 −3.65 −3.26 2 0.0362 S I (0) dlepeitec −3.99** −4.47 −3.65 −3.26 2 0.0260 S I (0) dlecii −8.77*** −4.47 −3.65 −3.26 11 0.0000 S I (0) dlecmii −4.95*** −4.47 −3.65 −3.26 3 0.0039 S I (0) dliecc −5.20*** −4.47 −3.65 −3.26 2 0.0023 S I (0) dlecahfi −4.77*** −4.47 −3.65 −3.26 3 0.0053 S I (0) dlectwti −6.45*** −4.47 −3.65 −3.26 0 0.0002 S I (0) dleccpsi −5.81*** −4.47 −3.65 −3.26 8 0.0007 S I (0) dlpi −3.45*** −4.47 −3.65 −3.26 2 0.0705 S I (0) dlgdpm −2.82 −4.47 −3.65 −3.26 1 0.2072 N/S I (1) ddlgdpm −6.29*** −4.49 −3.65 −3.26 7 0.0003 S I (0) dlgdpd −2.37 −4.47 −3.65 −3.26 2 0.3823 N/S I (1) ddlgdpd −3.84** −4.49 −3.65 −3.26 9 0.0356 S I (0) dlepegdp −3.01 −4.47 −3.65 −3.26 2 0.1543 N/S I (1) ddlepegdp −8.98*** −4.49 −3.65 −3.26 19 0.0000 S I (0) dligdp −3.08 −4.47 −3.65 −3.26 3 0.1370 N/S I (1) ddligdp −7.92*** −4.47 −3.65 −3.26 10 0.0000 S I (0) dlmigdp −3.45* −4.47 −3.65 −3.26 3 0.0706 S I (0) dlcgdp −4.61** −4.47 −3.65 −3.26 0 0.0075 S I (0) dlahfgdp −3.99** −4.47 −3.65 −3.26 0 0.0258 S I (0) dltwtgdp −4.63*** −4.47 −3.65 −3.26 1 0.0071 S I (0) dlcpsgdp −3.25 −4.47 −3.65 −3.26 2 0.1017 N/S I (1) ddlcpsgdp −4.60*** −4.49 −3.65 −3.26 17 0.0000 S I (0) dlpi −2.22 −4.47 −3.65 −3.26 2 0.4540 N/S I (1) ddlpi −7.34 −4.49 −3.65 −3.26 16 0.0000 S I (0) No Intercept & No Trend At Level Form leci 0.69 −2.67 −1.96 −1.61 2 0.8575 N/S I (1) lepeitec 0.71 −2.67 −1.96 −1.61 1 0.8624 N/S I (1) lecii 0.11 −2.67 −1.96 −1.61 13 0.7087 N/S I (1) lecmii 1.22 −2.67 −1.96 −1.61 4 0.9381 N/S I (1) liecc 0.39 −2.67 −1.96 −1.61 1 0.7903 N/S I (1) lecahfi −1.06 −2.67 −1.96 −1.61 2 0.2505 N/S I (1) lectwti −1.18 −2.67 −1.96 −1.61 1 0.2069 N/S I (1) leccpsi 0.25 −2.67 −1.96 −1.61 7 0.7484 N/S I (1) lecpi 0.49 −2.67 −1.96 −1.61 2 0.8138 N/S I (1) lgdpm 3.63 −2.67 −1.96 −1.61 2 0.9997 N/S I (1) lgdpd 1.77 −2.67 −1.96 −1.61 2 0.9774 N/S I (1) lepegdp 1.18 −2.67 −1.96 −1.61 0 0.9355 N/S I (1) ligdp 2.38 −2.67 −1.96 −1.61 2 0.9938 N/S I (1) lmigdp 2.31 −2.67 −1.96 −1.61 1 0.9928 N/S I (1) lcgdp 2.29 −2.67 −1.96 −1.61 1 0.9926 N/S I (1) lahfgdp 4.17 −2.67 −1.96 −1.61 1 0.9999 N/S I (1) A.Table 2: (Continued) (Contd...) Model Variable PP−test statistic Levels of critical values Bandwidth p-value Stationarity Integrir I (0,1,2) 1% 5% 10% With Intercept & Trend At level form Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020450 ltwtgdp 3.48 −2.67 −1.96 −1.61 1 0.9995 N/S I (1) lcpsgdp 4.66 −2.67 −1.96 −1.61 0 1.0000 N/S I (1) lpi 4.55 −2.67 −1.96 −1.61 2 1.0000 N/S I (2) No Intercept & No Trend At First differencing dleci −3.89*** −2.67 −1.96 −1.61 2 0.0005 S I (0) dlepeitec −4.11*** −2.67 −1.96 −1.61 1 0.0003 S I (0) dlecii −6.88*** −2.67 −1.96 −1.61 2 0.0000 S I (0) dlecmii −4.86*** −2.67 −1.96 −1.61 2 0.0000 S I (0) dliecc −5.12*** −2.67 −1.96 −1.61 2 0.0000 S I (0) dlecahfi −3.68*** −2.67 −1.96 −1.61 1 0.0008 S I (0) dlectwti −6.18*** −2.67 −1.96 −1.61 1 0.0000 S I (0) dleccpsi −5.42*** −2.67 −1.96 −1.61 6 0.0000 S I (0) dlecpi −3.40*** −2.67 −1.96 −1.61 2 0.0017 S I (0) dlgdpm −1.77* −2.67 −1.96 −1.61 2 0.0793 S I (0) dlgdpd −2.00** −2.67 −1.96 −1.61 2 0.0456 S I (0) dlepegdp −2.99*** −2.67 −1.96 −1.61 3 0.0048 S I (0) dligdp −2.33** −2.67 −1.96 −1.61 2 0.0223 S I (0) dlmigdp −2.71*** −2.67 −1.96 −1.61 1 0.0093 S I (0) dlcgdp −4.38*** −2.67 −1.96 −1.61 1 0.0001 S I (0) dlahfgdp −2.71*** −2.67 −1.96 −1.61 1 0.0093 S I (0) dltwtgdp −2.77*** −2.67 −1.96 −1.61 2 0.0083 S I (0) dlcpsgdp −2.05** −2.67 −1.96 −1.61 3 0.0408 S I (0) dlpi −1.08 −2.67 −1.96 −1.61 6 0.2451 N/S I (1) ddlpi −5.65*** −2.69 −1.96 −1.61 11 0.0000 S I (0) PP Phillips‒Perron is single root system. The optimum lag order in PP test is selected based on the Newey‒West criterion automatically; ***, ** and *indicate rejection of the null hypotheses at the 1%, 5% and 10% significance levels respectively. The critical values are taken from MacKinnon (Mackinnon, 1996). Assessment period: 1995-2017. S: Stationarity, N/S: No Stationarity A.Table 2: (Continued) (Contd...) Model Variable PP−test statistic Levels of critical values Bandwidth p-value Stationarity Integrir I (0,1,2) 1% 5% 10% No Intercept & No Trend At level form Model Variable Kwiatkowski−Phillips− Schmidt−Shin test statistic Levels of Critical Values Bandwidth Stationarity Integrir I (0,1,2) 1% 5% 10% With Intercept only At level form leci 0.38* 0.71 0.47 0.35 3 S I (0) lepeitec 0.49** 0.71 0.47 0.35 3 S I (0) lecii 0.32 0.71 0.47 0.35 2 N/S lecmii 0.53** 0.71 0.47 0.35 2 S I (0) liecc 0.47** 0.71 0.47 0.35 3 S I (0) lecahfi 0.26 0.71 0.47 0.35 3 N/S lectwti 0.57** 0.71 0.47 0.35 3 S I (0) leccpsi 0.45* 0.71 0.47 0.35 3 S I (0) lecpi 0.12 0.71 0.47 0.35 3 N/S lgdpm 0.65** 0.71 0.47 0.35 3 S I (0) lgdpd 0.61** 0.71 0.47 0.35 3 S I (0) lepegdp 0.57** 0.71 0.47 0.35 3 S I (0) ligdp 0.63** 0.71 0.47 0.35 3 S I (0) lmigdp 0.63** 0.71 0.47 0.35 3 S I (0) lcgdp 0.69** 0.71 0.47 0.35 3 S I (0) lahfgdp 0.66** 0.71 0.47 0.35 3 S I (0) ltwtgdp 0.66** 0.71 0.47 0.35 3 S I (0) lcpsgdp 0.67** 0.71 0.47 0.35 3 S I (0) lpi 0.66** 0.71 0.47 0.35 3 S I (0) With Intercept only At First differencing dleci 0.06 0.71 0.47 0.35 2 N/S dlepeitec 0.05 0.71 0.47 0.35 1 N/S dlecii 0.36* 0.71 0.47 0.35 13 S I (0) dlecmii 0.15 0.71 0.47 0.35 3 N/S dliecc 0.15 0.71 0.47 0.35 1 N/S A.Table 3: KPSS unit root test Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 451 dlecahfi 0.57 0.71 0.47 0.35 2 N/S dlectwti 0.11 0.71 0.47 0.35 1 N/S dleccpsi 0.23 0.71 0.47 0.35 7 N/S dlecpi 0.31 0.71 0.47 0.35 2 N/S dlgdpm 0.20 0.71 0.47 0.35 2 N/S dlgdpd 0.29 0.71 0.47 0.35 2 N/S dlepegdp 0.19 0.71 0.47 0.35 0 N/S dligdp 0.26 0.71 0.47 0.35 1 N/S dlmigdp 0.41 0.71 0.47 0.35 0 N/S dlcgdp 0.22 0.71 0.47 0.35 1 N/S dlahfgdp 0.10 0.71 0.47 0.35 1 N/S dltwtgdp 0.13 0.71 0.47 0.35 1 N/S dlcpsgdp 0.12 0.71 0.47 0.35 0 N/S dlpi 0.17 0.71 0.47 0.35 2 N/S With Intercept & Trend At Level Form leci 0.08 0.21 0.15 0.12 2 N/S lepeitec 0.07 0.21 0.15 0.12 2 N/S lecii 0.13 0.21 0.15 0.12 0 N/S lecmii 0.09 0.21 0.15 0.12 1 N/S liecc 0.47 0.21 0.15 0.12 3 N/S lecahfi 0.18 0.21 0.15 0.12 3 N/S lectwti 0.08 0.21 0.15 0.12 2 N/S leccpsi 0.15 0.21 0.15 0.12 2 N/S lecpi 0.13 0.21 0.15 0.12 3 N/S lgdpm 0.12 0.21 0.15 0.12 3 N/S lgdpd 0.12 0.21 0.15 0.12 3 N/S lepegdp 0.12 0.21 0.15 0.12 3 N/S ligdp 0.15 0.21 0.15 0.12 3 N/S lmigdp 0.16 0.21 0.15 0.12 3 N/S lcgdp 0.09 0.21 0.15 0.12 2 N/S lahfgdp 0.09 0.21 0.15 0.12 3 N/S ltwtgdp 0.09 0.21 0.15 0.12 3 N/S lcpsgdp 0.09 0.21 0.15 0.12 2 N/S lpi 0.09 0.21 0.15 0.12 3 N/S With Intercept & Trend At First differencing dleci 0.06 0.21 0.15 0.12 2 N/S dlepeitec 0.05 0.21 0.15 0.12 1 N/S dlecii 0.50 0.21 0.15 0.12 21 N/S dlecmii 0.12 0.21 0.15 0.12 3 N/S dliecc 0.12 0.21 0.15 0.12 1 N/S dlecahfi 0.13 0.21 0.15 0.12 3 N/S dlectwti 0.05 0.21 0.15 0.12 0 N/S dleccpsi 0.18 0.21 0.15 0.12 10 N/S dlecpi 0.13 0.21 0.15 0.12 2 N/S dlgdpm 0.12 0.21 0.15 0.12 2 N/S dlgdpd 0.15 0.21 0.15 0.12 2 N/S dlepegdp 0.15 0.21 0.15 0.12 0 N/S dligdp 0.12 0.21 0.15 0.12 0 N/S dlmigdp 0.09 0.21 0.15 0.12 3 N/S dlcgdp 0.08 0.21 0.15 0.12 0 N/S dlahfgdp 0.09 0.21 0.15 0.12 2 N/S dltwtgdp 0.13 0.21 0.15 0.12 1 N/S dlcpsgdp 0.10 0.21 0.15 0.12 0 N/S dlpi 0.16 0.21 0.15 0.12 2 N/S KPSS denotes Kwiatkowski‒Phillips‒Schmidt‒Shin (Kwiatkowski et al.,1992) single root system. The optimum lag order in KPSS test is selected based on the Newey‒West criterion automatically; ***, ** and *indicate rejection ofthe null hypotheses at the 1%, 5% and 10% significance levels respectively. The critical values are taken from Kwiatkowski‒Phillips‒ Schmidt‒Shin. Assessment period: 1995-2017. S: Stationarity, N/S: No Stationarity A.Table 3: (Continued) Model Variable Kwiatkowski−Phillips− Schmidt−Shin test statistic Levels of Critical Values Bandwidth Stationarity Integrir I (0,1,2) 1% 5% 10% With Intercept only At First differencing Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020452 A.Table 4: Coefficients ARDL model Coefficient Model 1 Model 2 Model 3 Model 4 Model 5 Model 6 Variable ∆lgdpm ∆lgdpd ∆lepegdp ∆ligdp ∆lmigdp ∆lcgdp ∆lgdpm(t−1) 0.44 lgdpm(t−1) −0.03 ∆leci(t−1) 0.06 leci(t−1) −0.03 ∆lgdpd(t−1) 0.61* lgdpd(t−1) −0.03 ∆leci(t−1) 0.18 leci(t−1) 0.09 ∆lepegdp(t−1) 0.32 lepegdp(t−1) −0.25 ∆lepeitec(t−1) −0.38 lepeitec(t−1) −0.25 ∆ligdp(t−1) 0.25 ligdp(t−1) 0.03 ∆lecci(t−1) −0.38* lecci(t−1) 0.03 ∆lmigdp(t−1) 0.22 lmigdp(t−1) −0.03 ∆lecmii(t−1) −0.22 lecmii(t−1) 0.09 ∆lcgdp(t−1) 0.33* lcgdp(t−1) 0.02 ∆liecc(t−1) 0.08 liecc(t−1) −0.03 Constant −2.22 −0.57 1.85 2.61* 0.083 0.05 A.Table 5: Coefficients ARDL model Coefficient Model 7 Model 8 Model 9 Model 10 Variable ∆lahfgdp ∆ltw tgdp ∆lcpsgdp ∆lpi ∆lahfgdp(t−1) −0.001 lahfgdp(t−1) 0.01 ∆lecahfi(t−1) 0.07 lecahfi(t−1) −0.13 ∆ltwtgdp(t−1) 0.11 ltwtgdp(t−1) 0.03 ∆lectwti(t−1) −0.39 lectwti(t−1) 0.44 ∆lcpsgdp(t−1) 0.23 lcpsgdp(t−1) 0.02 ∆leccpsi(t−1) 0.08 leccpsi(t−1) −0.06 ∆lpi(t−1) 0.43* lpi(t−1) −0.01 ∆lecpi(t−1) −0.20 lecpi(t−1) 0.07 Constant 0.90 −2.92 0.39 −0.49 Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 453 A.Figure 1: Dynamic Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020454 A.Figure 2: Plot of cumulative sum of recursive residuals Humbatova, et al.: The Relationship between Electricity Consumption and Economic Growth: Evidence from Azerbaijan International Journal of Energy Economics and Policy | Vol 10 • Issue 1 • 2020 455 A. Abbreviations ECI Electric energy consumption, total million kVt.h EPEITEC Internal consumption of electric energy producing entities million kVt.h ECII Elcertic energy consumption in industry million kVt.h ECMII Electric energy consumption in mining million kVt.h IECC Electric energy consumption in construction million kVt.h ECAHFI Electric energy consumption in agriculture, hunting and forestry million kVt.h ECTWTI Electric energy consumption in transport, warehouse and telecommunication million kVt.h ECCPSI Electric energy consumption in other, commercial and public service million kVt.h ECPI Electric energy consumption by people and in household million kVt.h GDPM GDP in manat mln. manat GDPD GDP in dollar mln. dollar EPETECGDP GDP in electric energy producing entities mln. manat ECIGDP GDP in industry mln. manat ECMIGDP GDP in mining industry mln. manat ECCGDP GDP in construction mln. manat ECAHFGDP GDP in agriculture, hunting and forestry mln. manat ECTWTGDP GDP in transport, warehouse and telecommunication mln. manat ECCPSGDP GDP in other, commercial and public service mln. manat PI People’s income mln. manat