IMPACT OF PUBLIC INVESTMENT ON ECONOMIC GROWTH IN VIETNAM A DISSERTATION PAPER Presented to the Faculty of the Graduate Program of the College of Arts and Sciences Central Philippine University, Phili[.]
IMPACT OF PUBLIC INVESTMENT ON ECONOMIC GROWTH IN VIETNAM A DISSERTATION PAPER Presented to the Faculty of the Graduate Program of the College of Arts and Sciences Central Philippine University, Philippines In Collaboration with Thai Nguyen University, Vietnam In Partial Fulfillment Of the Requirements for the Degree DOCTOR IN PUBLIC ADMINISTRATION NGUYEN PHUC AI NOVEMBER, 2020 Tai ngay!!! Ban co the xoa dong chu nay!!! i ACKNOWLEDGEMENT The author wishes to convey the gratitude to the following persons who wholeheartedly devoted and helped make this piece of work a reality: To the leadership of Central Philippine University and leadership of Thai Nguyen University for their enthusiasm to support executive for the participants who completed the study program; To Assoc Prof Nguyen Khanh Doanh for his advices, guidance, supervision, suggestions, and precious time in enthusiastically reading and checking the manuscript, providing the author useful materials; To Doctor Reynaldo Nene Dusaran, his incomparable contribution and support to the development of Doctor of Public Administration program in Thai Nguyen University as well as his invaluable thoughts, insightful suggestions, useful guidance throughout the thesis work To the leadership of International Cooperation Center for Training and Study Abroad and their staff for their enthusiasm to support executive for the participants who completed the study program; To the faculties and researchers of Thai Nguyen University of Economics and Business Administration for their active involvement and cooperation which made the conduct of the study possible Finally, I specialy would like to give inmost thanks to my family and friends for their love and support in one way or another, and to all who have contributed to making this study a success Thai Nguyen, November 2020 Nguyen Phuc Ai ii LỜI CẢM ƠN Tác giả xin gửi lời tri ân đến người tận tình giúp đỡ để tác giả hồn thành luận án này: Trân trọng cảm ơn Ban lãnh đạo trường Đại học Central Philippine Ban lãnh đạo Đại học Thái Nguyên nhiệt tình hỗ trợ điều hành cho học viên hồn thành chương trình học Trân trọng cảm ơn PGS GS Nguyễn Khánh Doanh tận tình bảo, hướng dẫn, giám sát, góp ý dành thời gian quý báu việc nhiệt tình đọc kiểm tra thảo, cung cấp cho tác giả tư liệu hữu ích; Xin cảm ơn tiến sĩ Reynaldo Nene Dusaran đóng góp, hỗ trợ khơng nhỏ ông việc xây dựng chương trình Tiến sĩ Quản lý hành cơng Đại học Thái Ngun suy nghĩ, góp ý sâu sắc, dẫn hữu ích ơng suốt q trình tơi thực luận án; Cảm ơn Ban lãnh đạo Trung tâm Hợp tác Quốc tế Đào tạo Du học cán nhiệt tình hỗ trợ giúp học viên hồn thành chương trình học Xin cảm ơn khoa, cán nghiên cứu Trường Đại học Kinh tế Quản trị Kinh doanh Thái Nguyên tham gia hợp tác tích cực họ giúp cho việc tiến hành nghiên cứu trở nên khả thi Cuối cùng, xin cảm ơn gia đình bạn bè tơi dành tình cảm ủng hộ cho tơi nhiều cách khác nhau, cảm ơn tất người góp phần làm cho nghiên cứu thành cơng Thái Nguyên, tháng 11 năm 2020 Nguyễn Phúc Ái iii COMMITMENT I assure you that the data and reseach findings in this disertation are honest and have not been used for publication in any other reseach I would like to assure you that all helps for the implementation of the disertation has been thanked and the information cited in the disertation is clearly indicated Thai Nguyen, November 2020 Author of disertation Nguyen Phuc Ai iv LỜI CAM ĐOAN Tôi xin cam đoan: Số liệu kết nghiên cứu luận án trung thực chưa sử dụng để công bố cho nghiên cứu khác Tôi cam đoan tất trợ giúp cho việc thực luận án cảm ơn thơng tin trích dẫn luận án rõ nguồn gốc Thái Nguyên, tháng 11 năm 2020 Tác giả luận án Nguyễn Phúc Ái v TABLE OF CONTENTS ACKNOWLEDGEMENT i LỜI CẢM ƠN ii COMMITMENT iii LỜI CAM ĐOAN iv TABLE OF CONTENTS v LIST OF TABLES viii LIST OF FIGURES ix LIST OF ABBREVIATIONS x ABSTRACT xi CHAPTER 1: INTRODUCTION 1.1 Background and Rationale of the Study 1.1.1 Background of the study 1.1.2 Statement of the Problem 1.2 Objectives of the Study 1.2.1 General Objective 1.3 The Theoretical Framework 1.4 Conceptual Framework 1.5 Operational Definition of Variables and other term 1.6 Significance of the Study 1.7 Scope and Limitations 1.7.1 Scope of the Study 1.7.2 Limitations of the Study CHAPTER 2: REVIEW OF RELATED LITERATURE AND STUDIES 10 2.1 An Overview of economic growth theory and public investment 10 2.1.1 Overview of economic growth theory 10 2.1.2 Public investment theory 38 2.1.3 The role of public investment 40 2.2 Approaches to estimate relationships in macro economic variables 41 2.2.1 The Engle-Granger Two-Step Modeling Method (EGM) 41 2.2.2 The Engle-Yoo Three-Step Modeling Method (EYM) 42 2.2.3 The Saikkonen Method 43 2.2.4 The Johansen Maximum Likelihood (ML) Vector Autoregressive (VAR) Method 43 2.2.5 The ARDL bound test method 45 vi 2.3 Review of related studies 45 2.3.1 International studies on the relationship between economic growth and public investment 45 2.3.2 Study on the relationship between economic growth and public investment in Vietnam 52 Chapter Summary 56 CHAPTER 3: RESEARCH METHODOLOGY 57 3.1 Research Design 57 3.2 Population, Sample Size and Sampling Technique 58 3.3 Research Instruments 58 3.4 Ethical Considerations 58 3.5 Data Gathering Procedure 58 Chapter Summary 65 CHAPTER 4: DATA PRESENTATION, ANALYSYS AND INTERPRETATION 66 4.1 Economic overview and public investment trend 66 4.1.1 Vietnam economic overview in the period of 1986-2015 66 4.1.2 Import and Export of Vietnam 67 4.1.3 Investment and public investment trend 69 4.1.4 Vietnamese public investment System and Issues 72 4.2 Empirical Results 76 4.2.1 Descriptive Statistics 76 4.2.2 Unit root test 77 4.2.3 Empirical results of the impact of Public Investment on Economic growth 78 4.3 Discussions 84 Chapter Summary 87 CHAPTER 5: SUMMARY, CONCLUSIONS AND POLICY RECOMMENDATIONS 88 5.1 Summary 88 5.2 Conclusions 88 5.3 Policy recommendations 89 5.3.1 Economic restructuring 89 5.3.2 Public investment restructuring 89 5.3.3 Reduce the proportion of public investment in society's total investment, improve the efficiency of public investment 90 5.3.4 Changing the role of public investment in the economy 91 5.3.5 Strict control of public investment 92 vii 5.3.6 Improve the quality capital and effectively use capital for public investment activities 94 5.3.7 Improve the efficiency of the implementation of the National Target Program (NTP) and others 96 5.3.8 Prioritize public investment for infrastructure projects 97 5.3.9 Strengthen public investment in agriculture and rural development 98 5.3.10 Promote reformation of SOE sector 99 Chapter summary 100 REFERENCES 101 APPENDICES 107 viii LIST OF TABLES Table 4.1 Statistics of Variables 77 Table 4.2 Unit root test 78 Table 4.3 Bound test results 79 Table 4.4 Estimation of ARDL model 79 Table 4.5 Estimation of long -run variables 80 Table 4.6 Estimation of ECM variables 81 Table 4.7 Serial correlation test 82 ix LIST OF FIGURES Figure 1.1 Conceptual Framework Figure 2.1 The classical theory of growth 10 Figure 2.2 Fix proportion Production function 17 Figure 2.3 Equilibrium output change with investment 17 Figure 2.4 Production function with some factor substitution 19 Figure 2.5 Production function 22 Figure 2.6 Output, consumption and investment 24 Figure 2.7 Depreciation 24 Figure 2.8 Investment, depreciation and steady state 25 Figure 2.9 Steady state consumption 27 Figure 2.10 The saving rate and the golden rule 28 Figure 2.11 The saving rate is reduced 29 Figure 2.12 The saving rate is increased 29 Figure 2.13 Effects of depreciation and population growth 31 Figure 2.14 Effect of population growth 32 Figure 2.15 Steady - state with technical progress 33 Figure 4.1 GDP growth rate 67 Figure 4.2 Total import and export 68 Figure 4.3 Trade deficit 69 Figure 4.4 Capital/GDP ratio 69 Figure 4.5 Investment at constant 2010 prices by types of ownership 70 Figure 4.6 Structure of Investment by types of ownership (%) 71 Figure 4.7 Change of GDP and Investment 75 Figure 4.8 Description of variables 77 Figure 4.8 Cusum test 83 Figure 4.9 Cusum of square test 83 Figure 4.10 TFP growth rate for 2006-2015 period 85 105 62 Pham, T Anh., (2008), “Chi tieu chinh phu va tang truong kinh te: khao sat ly luan tong quan”, Center of Economic and Political Research CEPR, University of Economics, Hanoi National University, NC - 02/2008 63 Pesaran, M H., and Y Shin (1995) Long-run Structural Modelling Cambridge, Department of Applied Economics, University of Cambridge (DAE Working Paper No 9419.) 64 Pesaran, M H., and B Pesaran (1997) Working with Microfit 4.0: An Interactive Approach Oxford: Oxford University Press 65 Pesaran, M H., Yongcheol Shin, and Richard J Smith (1999) Bounds Testing Approaches to the Analysis of Long Run Relationships February (Working Paper) 66 Pesaran, M H., Yongcheol Shin, and Richard J Smith (2001) Bounds Testing Approaches to the Analysis of Level Relationships Journal of Applied Econometrics 16, 289-326 67 Phillips, P.C.B and B.E Hansen (1990) “Statistical Inference in Instrumental Variables Regression with I(1) Processes”, Review of Economic Studies, 57, 99-125 68 Phillips, P.C.B and M Loretan (1991) “Estimating Long-run Economic Equilibria”, Review of Economic Studies, 58, 407-36 69 Ramirez, MD and Nazmi, N (2003) ―Public Investment and Economic Growth in Latin America: An Empirical Test‖ Review of Development Economics, 7(1), 115-126 70 Romer, P (1986) “Increasing returns and long-run growth”, Journal of Political Economy, Vol.94, No.5, pp.1002-1037 71 Romer (1987) “Crazy explanations for the productivity slowdown”, S Fischer (ed.),NBER Macroeconomics Annual 2, MIT Press, Cambridge, MA 72 Romer (1990) “Endogenous technological change”, Journal of Political Economy, Vol.98, No.5 Part 2, pp.S71-S102 73 Rebelo, S, “Long-Run Policy Analysis and Long-Run Growth” The Journal of Political Economy, Vol 99, No (Jun., 1991), pp 500-521 74 Saikkonen, P (1991) “Asymptotically Efficient Estimation of Cointegration Regressions”, Econometric Theory, 7, 1-21 75 Syed Adnan Haider, Ali Shah Bukhari, Liaqat Ali, Mahpara Saddaqat (2007), “Public Investment and Economic Growth in the Three Little Dragons: Evidence from Heterogeneous Dynamic Panel Data” International Journal of Business and Information Volume 2, Number 1, June 2007 76 Solow, RM (1956) “A contribution to the theory of economic growth”, Quarterly Journal of Economics, Vol.70, No.1, pp.65-94 106 77 Solow (1957) “Technical change and the aggregate production function”, Review of Economics & Statistics, Vol.39, No.3, pp.312-320 78 Swaby, R (2007) Public Investment and Growth in Jamaica Fiscal and Economic Programme Monitoring Dept Bank of Jamaica 2007 79 To Trung Thanh,(2011), “Public investment ―crowds out‖ private investment? A look from experimental model of VECM‖ , Magazine of Finance-Tạp chí tài chính, Vol.6 (560) 2011 80 Tran Ngoc Anh Thu and Le Hoang Phong (2014), ―Impact of public investment on economic growth in Vietnam: An experimental look of ARDL model‖ , Development and Integration-Tạp chí Kinh tế Hội nhập, Vol.19, 3-10 81 Vedder, R.K and L.E Gallaway (1998) Government Size and Economic Growth Paper Prepared for the Joint Economic Committee of Us Congress Pp.1-15 82 Yakita, A., 2001 Taxation in an overlapping generations model with human capital International Tax and Public Finance 8, 775-792 83 World Bank (2012-2018), World Bank Data https://www.worldbank.org/ 107 APPENDICES APPENDIX DATA GDPIndex (%) 2.79 3.58 5.14 7.36 5.1 5.96 8.65 8.07 8.84 9.54 9.34 8.15 5.76 4.77 6.79 6.19 6.32 6.9 7.54 7.55 6.98 7.13 5.66 5.4 6.42 6.24 5.25 5.42 5.98 6.68 PublicInvest/GDP (%) 6.68 4.56 5.21 7.69 7.4 6.67 7.68 13.24 11.65 13.3 15.77 17.08 18.01 19.24 20.24 21.19 21.42 20.63 19.55 17.68 17.44 15.88 12.93 15.89 14.66 12.29 12.53 12.33 12.36 12.39 PrivateInvest/GDP (%) 3.34 4.08 4.31 6.91 8.46 8.48 9.77 9.27 9.52 8.74 8.01 7.81 7.7 7.89 7.83 9.45 12.13 15.34 14.51 14.51 16.42 13.43 13.27 13.88 12.81 11.86 11.51 11.9 12.63 LaborIndex (%) 2.53 2.491327657 2.450202429 2.388441901 1.918516689 1.856651423 1.688487039 1.291900058 1.939735845 1.721208601 1.606239043 0.322409238 2.068457314 1.45651818 1.188580614 0.646451784 1.776654333 0.814923619 1.231036985 0.755442605 0.833097745 0.938041936 1.097242014 0.684154228 1.41795773 2.1660652 1.829251647 1.458440271 1.307142259 1.048094059 FDI share (%) 0.00015188 0.028271245 0.0302079 0.064671903 2.781322895 3.902796789 4.803347845 7.027592369 11.93948244 8.585966076 9.713080725 8.270096541 6.141214415 4.92266363 3.858491949 3.683622274 3.689268314 3.394427339 3.257519609 3.390403646 3.616000904 8.654717714 9.663039055 7.168823838 6.9006118 5.481797332 5.370298997 5.19792941 4.940800273 6.106361156 108 APPENDIX RESUTLS Null Hypothesis: LGDP has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) Augmented Dickey-Fuller test statistic Test critical values: 1% level 5% level 10% level t-Statistic Prob.* -3.843738 -4.394309 -3.612199 -3.243079 0.0316 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(LGDP) Method: Least Squares Date: 07/15/18 Time: 14:28 Sample (adjusted): 30 Included observations: 24 after adjustments Variable Coefficient Std Error t-Statistic Prob LGDP(-1) D(LGDP(-1)) D(LGDP(-2)) D(LGDP(-3)) D(LGDP(-4)) D(LGDP(-5)) C @TREND("1") -0.976769 0.536957 0.242173 0.414782 0.136616 0.121736 2.026105 -0.009413 0.254120 0.199122 0.231645 0.165026 0.163400 0.139861 0.533494 0.004956 -3.843738 2.696623 1.045448 2.513441 0.836082 0.870406 3.797799 -1.899370 0.0014 0.0159 0.3114 0.0230 0.4154 0.3970 0.0016 0.0757 R-squared Adjusted R-squared S.E of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic) 0.597980 0.422096 0.125526 0.252108 20.61689 3.399858 0.020208 Mean dependent var S.D dependent var Akaike info criterion Schwarz criterion Hannan-Quinn criter Durbin-Watson stat 0.004752 0.165122 -1.051408 -0.658723 -0.947229 2.057092 Null Hypothesis: LPUB has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) Augmented Dickey-Fuller test statistic t-Statistic Prob.* -1.136913 0.9034 109 Test critical values: 1% level -4.339330 5% level -3.587527 10% level -3.229230 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(LPUB) Method: Least Squares Date: 07/15/18 Time: 14:28 Sample (adjusted): 30 Included observations: 27 after adjustments Variable Coefficient Std Error t-Statistic Prob LPUB(-1) -0.088247 0.077620 -1.136913 0.2678 D(LPUB(-1)) -0.288151 0.175843 -1.638689 0.1155 D(LPUB(-2)) -0.396331 0.149299 -2.654616 0.0145 C 0.470964 0.175681 2.680793 0.0137 @TREND("1") -0.011823 0.004379 -2.699896 0.0131 R-squared 0.489043 Mean dependent var 0.032086 Adjusted R-squared 0.396141 S.D dependent var 0.161739 S.E of regression 0.125685 Akaike info criterion -1.144501 Sum squared resid 0.347528 Schwarz criterion -0.904531 Log likelihood 20.45076 Hannan-Quinn criter -1.073145 F-statistic 5.264105 Durbin-Watson stat 1.908518 Prob(F-statistic) 0.003954 Null Hypothesis: D(LPUB) has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) t-Statistic Prob.* 110 Augmented Dickey-Fuller test statistic -6.979422 Test critical values: 1% level -4.323979 5% level -3.580623 10% level -3.225334 0.0000 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(LPUB,2) Method: Least Squares Date: 07/15/18 Time: 14:29 Sample (adjusted): 30 Included observations: 28 after adjustments Variable Coefficient Std Error t-Statistic Prob D(LPUB(-1)) -1.138487 0.163121 -6.979422 0.0000 C 0.185436 0.062268 2.978005 0.0064 @TREND("1") -0.009464 0.003535 -2.677382 0.0129 R-squared 0.665188 Mean dependent var 0.013722 Adjusted R-squared 0.638403 S.D dependent var 0.243420 S.E of regression 0.146376 Akaike info criterion -0.904322 Sum squared resid 0.535647 Schwarz criterion -0.761586 Log likelihood 15.66050 Hannan-Quinn criter -0.860686 F-statistic 24.83436 Durbin-Watson stat 2.319292 Prob(F-statistic) 0.000001 Null Hypothesis: LPRI has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -2.308617 0.4150 Test critical values: -4.356068 1% level 111 5% level -3.595026 10% level -3.233456 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(LPRI) Method: Least Squares Date: 07/15/18 Time: 14:30 Sample (adjusted): 30 Included observations: 26 after adjustments Variable Coefficient Std Error t-Statistic Prob LPRI(-1) -0.261905 0.113447 -2.308617 0.0318 D(LPRI(-1)) 0.131029 0.119354 1.097824 0.2853 D(LPRI(-2)) -0.014244 0.118788 -0.119909 0.9058 D(LPRI(-3)) 0.292668 0.118870 2.462083 0.0230 C 0.634298 0.281487 2.253378 0.0356 @TREND("1") 0.006923 0.004600 1.505067 0.1479 R-squared 0.423136 Mean dependent var 0.029501 Adjusted R-squared 0.278920 S.D dependent var 0.117171 S.E of regression 0.099497 Akaike info criterion -1.578204 Sum squared resid 0.197993 Schwarz criterion -1.287874 Log likelihood 26.51665 Hannan-Quinn criter -1.494599 F-statistic 2.934045 Durbin-Watson stat 1.621839 Prob(F-statistic) 0.038107 Null Hypothesis: D(LPRI) has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -4.893494 0.0027 Test critical values: -4.323979 1% level 112 5% level -3.580623 10% level -3.225334 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(LPRI,2) Method: Least Squares Date: 07/15/18 Time: 14:30 Sample (adjusted): 30 Included observations: 28 after adjustments Variable Coefficient Std Error t-Statistic Prob D(LPRI(-1)) -0.994149 0.203157 -4.893494 0.0000 C 0.190277 0.083082 2.290242 0.0307 @TREND("1") -0.008611 0.004517 -1.906475 0.0681 R-squared 0.490229 Mean dependent var -0.004242 Adjusted R-squared 0.449448 S.D dependent var 0.232874 S.E of regression 0.172791 Akaike info criterion -0.572513 Sum squared resid 0.746417 Schwarz criterion -0.429776 Log likelihood 11.01518 Hannan-Quinn criter -0.528877 F-statistic 12.02083 Durbin-Watson stat 1.948229 Prob(F-statistic) 0.000220 Null Hypothesis: LPRI1 has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -3.350722 0.0804 Test critical values: 1% level -4.356068 5% level -3.595026 10% level -3.233456 113 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(LPRI1) Method: Least Squares Date: 07/15/18 Time: 14:32 Sample (adjusted): 30 Included observations: 26 after adjustments Variable Coefficient Std Error t-Statistic Prob LPRI1(-1) -0.405710 0.121081 -3.350722 0.0032 D(LPRI1(-1)) 0.337518 0.136114 2.479672 0.0222 D(LPRI1(-2)) 0.119902 0.149219 0.803526 0.4311 D(LPRI1(-3)) 0.398569 0.147744 2.697699 0.0138 C 0.709527 0.219261 3.235992 0.0041 @TREND("1") 0.013723 0.004696 2.922317 0.0084 R-squared 0.489342 Mean dependent var 0.023196 Adjusted R-squared 0.361678 S.D dependent var 0.107971 S.E of regression 0.086264 Akaike info criterion -1.863639 Sum squared resid 0.148829 Schwarz criterion -1.573309 Log likelihood 30.22731 Hannan-Quinn criter -1.780034 F-statistic 3.833037 Durbin-Watson stat 1.958105 Prob(F-statistic) 0.013446 Null Hypothesis: D(LPRI1) has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -3.984728 0.0213 Test critical values: 1% level -4.323979 5% level -3.580623 10% level -3.225334 114 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(LPRI1,2) Method: Least Squares Date: 07/15/18 Time: 14:32 Sample (adjusted): 30 Included observations: 28 after adjustments Variable Coefficient Std Error t-Statistic Prob D(LPRI1(-1)) -0.780422 0.195853 -3.984728 0.0005 C 0.086321 0.059935 1.440257 0.1622 @TREND("1") -0.003608 0.003273 -1.102582 0.2807 R-squared 0.391309 Mean dependent var -0.005021 Adjusted R-squared 0.342613 S.D dependent var 0.159660 S.E of regression 0.129452 Akaike info criterion -1.150061 Sum squared resid 0.418944 Schwarz criterion -1.007325 Log likelihood 19.10085 Hannan-Quinn criter -1.106425 F-statistic 8.035859 Durbin-Watson stat 1.971230 Prob(F-statistic) 0.002018 Null Hypothesis: LFDI has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -6.329638 0.0001 Test critical values: 1% level -4.309824 5% level -3.574244 10% level -3.221728 *MacKinnon (1996) one-sided p-values 115 Augmented Dickey-Fuller Test Equation Dependent Variable: D(LFDI) Method: Least Squares Date: 07/15/18 Time: 14:31 Sample (adjusted): 30 Included observations: 29 after adjustments Variable Coefficient Std Error t-Statistic Prob LFDI(-1) -0.411952 0.065083 -6.329638 0.0000 C 0.670233 0.283896 2.360844 0.0260 @TREND("1") 0.001999 0.018594 0.107489 0.9152 R-squared 0.688322 Mean dependent var 0.365578 Adjusted R-squared 0.664347 S.D dependent var 1.196503 S.E of regression 0.693201 Akaike info criterion 2.202705 Sum squared resid 12.49373 Schwarz criterion 2.344149 Log likelihood -28.93922 Hannan-Quinn criter 2.247003 F-statistic 28.70969 Durbin-Watson stat 2.080248 Prob(F-statistic) 0.000000 Null Hypothesis: LLABOR has a unit root Exogenous: Constant, Linear Trend Lag Length: (Automatic - based on SIC, maxlag=7) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -4.721910 0.0038 Test critical values: 1% level -4.309824 5% level -3.574244 10% level -3.221728 *MacKinnon (1996) one-sided p-values 116 Augmented Dickey-Fuller Test Equation Dependent Variable: D(LLABOR) Method: Least Squares Date: 07/15/18 Time: 14:33 Sample (adjusted): 30 Included observations: 29 after adjustments Variable Coefficient Std Error t-Statistic Prob LLABOR(-1) -0.914890 0.193754 -4.721910 0.0001 C 0.537554 0.216036 2.488259 0.0196 @TREND("1") -0.018555 0.011055 -1.678332 0.1053 R-squared 0.462430 Mean dependent var -0.030388 Adjusted R-squared 0.421078 S.D dependent var 0.598155 S.E of regression 0.455117 Akaike info criterion 1.361174 Sum squared resid 5.385425 Schwarz criterion 1.502618 Log likelihood -16.73702 Hannan-Quinn criter 1.405473 F-statistic 11.18290 Durbin-Watson stat 2.047884 Prob(F-statistic) 0.000313 Dependent Variable: LGDP Method: ARDL Date: 07/15/18 Time: 20:48 Sample (adjusted): 30 Included observations: 28 after adjustments Maximum dependent lags: (Automatic selection) Model selection method: Akaike info criterion (AIC) Dynamic regressors (2 lags, automatic): LFDI LLABOR LPRI1 LPUB Fixed regressors: C @TREND Number of models evalulated: 162 Selected Model: ARDL(2, 1, 2, 2, 1) Variable Coefficient Std Error t-Statistic Prob.* LGDP(-1) LGDP(-2) 0.660306 -0.363666 0.186455 0.189660 3.541371 -1.917466 0.0033 0.0758 117 LFDI -0.127902 0.052962 -2.414963 0.0300 LFDI(-1) LLABOR LLABOR(-1) LLABOR(-2) LPRI1 LPRI1(-1) LPRI1(-2) LPUB LPUB(-1) 0.159070 0.022519 0.116379 0.144121 0.803868 -0.709807 0.377854 -0.210866 0.276074 0.050409 0.063379 0.066468 0.062833 0.240514 0.340540 0.286647 0.223461 0.211047 3.155586 0.355313 1.750898 2.293704 3.342290 -2.084355 1.318186 -0.943636 1.308118 0.0070 0.7277 0.1018 0.0378 0.0048 0.0559 0.2086 0.3614 0.2119 C @TREND 0.320210 -0.021934 0.581655 0.007424 0.550516 -2.954447 0.5906 0.0105 R-squared Adjusted R-squared 0.807992 0.629699 Mean dependent var S.D dependent var 1.892227 0.192143 S.E of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic) 0.116924 0.191397 30.06828 4.531816 0.004159 Akaike info criterion Schwarz criterion Hannan-Quinn criter Durbin-Watson stat -1.147734 -0.481632 -0.944100 2.070571 *Note: p-values and any subsequent tests not account for model selection ARDL Long Run Form and Bounds Test Dependent Variable: D(LGDP) Selected Model: ARDL(2, 1, 2, 2, 1) Case 5: Unrestricted Constant and Unrestricted Trend Date: 07/15/18 Time: 20:59 Sample: 30 Included observations: 28 Conditional Error Correction Regression Variable Coefficient Std Error t-Statistic Prob C @TREND LGDP(-1)* LFDI(-1) LLABOR(-1) LPRI1(-1) LPUB(-1) D(LGDP(-1)) D(LFDI) D(LLABOR) D(LLABOR(-1)) D(LPRI1) 0.320210 -0.021934 -0.703360 0.031168 0.283019 0.471915 0.065208 0.363666 -0.127902 0.022519 -0.144121 0.803868 0.581655 0.007424 0.216369 0.040844 0.136644 0.186338 0.137414 0.189660 0.052962 0.063379 0.062833 0.240514 0.550516 -2.954447 -3.250751 0.763113 2.071216 2.532584 0.474539 1.917466 -2.414963 0.355313 -2.293704 3.342290 0.5906 0.0105 0.0058 0.4581 0.0573 0.0239 0.6424 0.0758 0.0300 0.7277 0.0378 0.0048 118 D(LPRI1(-1)) D(LPUB) -0.377854 -0.210866 0.286647 0.223461 -1.318186 -0.943636 0.2086 0.3614 * p-value incompatible with t-Bounds distribution Levels Equation Case 5: Unrestricted Constant and Unrestricted Trend Variable Coefficient Std Error t-Statistic Prob LFDI LLABOR LPRI1 LPUB 0.044313 0.402382 0.670944 0.092710 0.053876 0.233078 0.277843 0.186307 0.822501 1.726379 2.414835 0.497618 0.4246 0.1063 0.0300 0.6265 EC = LGDP - (0.0443*LFDI + 0.4024*LLABOR + 0.6709*LPRI1 + 0.0927 *LPUB ) F-Bounds Test Null Hypothesis: No levels relationship Test Statistic Value Signif I(0) I(1) F-statistic k 6.412719 10% 5% 2.5% 1% Asymptotic: n=1000 3.03 3.47 3.89 4.4 4.06 4.57 5.07 5.72 Actual Sample Size 28 10% 5% 1% Finite Sample: n=35 3.374 4.512 4.036 5.304 5.604 7.172 10% 5% 1% Finite Sample: n=30 3.43 4.624 4.154 5.54 5.856 7.578 t-Bounds Test Null Hypothesis: No levels relationship Test Statistic Value Signif I(0) I(1) t-statistic -4.750751 10% 5% 2.5% 1% -3.13 -3.41 -3.65 -3.96 -4.04 -4.36 -4.62 -4.96 Dependent Variable: LGDP Method: Least Squares Date: 07/15/18 Time: 23:04 Sample (adjusted): 30 Included observations: 28 after adjustments Variable Coefficient Std Error t-Statistic Prob 119 C LGDP(-2) LFDI(-1) LLABOR(-2) LPRI1(-2) LPUB(-1) @TREND 1.216670 -0.272390 0.034897 0.135406 0.493063 0.177871 -0.029877 R-squared Adjusted R-squared S.E of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic) 0.773533 0.623114 0.158082 0.524791 15.94716 3.148090 0.023156 0.514105 0.213331 0.041258 0.078169 0.216756 0.126865 0.009101 2.366578 -1.276841 0.845835 1.732213 2.274733 1.402051 -3.282920 Mean dependent var S.D dependent var Akaike info criterion Schwarz criterion Hannan-Quinn criter Durbin-Watson stat 0.0276 0.2156 0.4072 0.0979 0.0335 0.0755 0.0035 1.892227 0.192143 -0.639083 -0.306032 -0.537266 1.413062 Dependent Variable: D(LGDP) Method: Least Squares Date: 07/15/18 Time: 23:45 Sample (adjusted): 30 Included observations: 27 after adjustments Variable Coefficient Std Error t-Statistic Prob C D(LGDP(-1)) D(LFDI(-1)) D(LLABOR(-1)) D(LPRI1(-1)) D(LPUB(-1)) ECM(-1) -0.005861 0.239228 0.025612 -0.036898 -0.047312 -0.029733 -0.885495 0.035819 0.210507 0.053665 0.056971 0.333580 0.218972 0.283862 -0.163621 1.136438 0.477248 -0.647661 -0.141832 -0.135786 -3.119459 0.8717 0.2692 0.6384 0.5246 0.8886 0.8933 0.0054 R-squared Adjusted R-squared S.E of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic) 0.357723 0.165040 0.171214 0.586287 13.39072 1.856537 0.138757 Mean dependent var S.D dependent var Akaike info criterion Schwarz criterion Hannan-Quinn criter Durbin-Watson stat 0.009706 0.187373 -0.473387 -0.137429 -0.373489 2.005365