(Luận văn) the impact of food safety standard on coffee export, the case in vietnam during 2005 2014

UNIVERSITY OF ECONOMICS ERASMUS UNVERSITY ROTTERDAM HO CHI MINH CITY VIETNAM INSTITUTE OF SOCIAL STUDIES THE NETHERLANDS t to ng hi ep VIETNAM – THE NETHERLANDS w n PROGRAMME FOR M.A IN DEVELOPMENT ECONOMICS lo ad ju y th yi pl n ua al THE IMPACT OF FOOD SAFETY STANDARD ON COFFEE EXPORT THE CASE IN VIETNAM DURING 2005-2014 n va ll fu oi m at nh z z BY vb ht TRUONG TAN TAI k jm om l.c gm a Lu MASTER OF ARTS IN DEVELOPMENT ECONOMICS n n va y te re HO CHI MINH CITY, OCTOBER -2016 ABSTRACT The objective of this study is to scrutinize the impact of FSS on the quantity of t to Vietnam’s coffee export Meanwhile, the regulated number of pesticides or average maximum ng residue levels is usually applied as a measurement of Food Safety Standard of a country The hi ep data covers 56 countries from 2005 to 2014 due to the data availability from Agrobase- Logigram’s Homologa database providing coffee FSS The Fixed effect estimator is w employed in the panel gravity model Furthermore, Driscoll – Kraay Standard Errors for n lo Fixed effect estimator is used for robustness checks ad Significantly, the primary findings determine that the regulated number of pesticides y th has a negative impact while average maximum residue levels have a positive effect on the ju yi export of Vietnamese coffee Furthermore, GDP per capita of importing countries, domestic pl consumption, and TWO member dummy variable demonstrate a contribution to Vietnamese al ua coffee export Meanwhile, the real exchange rate depreciation and price*distance variable n indicate a negative influence on the quantity of Vietnam’s coffee export Last but not least va n important, there are not any significant evidences proving the effect of trade openness and fu ll tariff on Vietnamese coffee export in the study m oi Keywords: Food safety standard, Vietnam’s coffee export, panel gravity model at nh z z ht vb k jm om l.c gm n a Lu n va y te re i ACKNOWDGEMENT t to Firstly, I would highly appreciate my advisor Dr Nguyen Huu Dung for his valuable ng advice, consideration, and agreeable methodology during the time for conducting this thesis hi ep If there are not such valuable things, I am unable to complete my thesis in time Secondly, I am grateful to Dr Truong Dang Thuy providing me with precious w instructions and encouragement Besides that, I also express my appreciation to dedicated n lo professors and staffs in the Vietnam – Netherlands Programme who always support me during ad the time at VNP y th ju Thirdly, I wish to express my thankfulness to my classmates and my friendly group in yi Class 20 The kind assistance, useful discussion, and wonderful memories together from them pl will be imprinted in my heart ua al Finally, I have no word to manifest my deep gratefulness to my loved family They n this thesis n va have to sacrifice the best things for me to have this opportunity to study at VNP and complete ll fu oi m at nh z z ht vb k jm om l.c gm n a Lu n va y te re ii ABBREVIATIONS The Centre d’Études Prospectives et d’Informations Internationales EEC CEPII t to European Economic Community ng hi ep EU The European Union FSS Food safety standards FTA Free Trade Agreement w Maximum Residue Levels of Pesticides n MRLs lo Ordinary least squares y th SPS ad OLS Sanitary and Phytosanitary ju Technical Barriers to Trade TRAINS The UNCTAD Trade Analysis Information System yi TBT pl al World Trade Organization n va WTO n ua UN Comtrade The United Nations Commodity Trade Statistics Database ll fu oi m at nh z z ht vb k jm om l.c gm n a Lu n va y te re iii CONTENTS ABSTRACT i t to ACKNOWDGEMENT ii ng ABBREVIATIONS iii hi ep CONTENTS iv LIST OF TABLES vii w n LIST OF FIGURES viii lo Problem statement ju y th 1.1 ad CHAPTER 1: INTRODUCTION Research objectives 1.3 Research questions 1.4 Scope and limitations of the study 1.5 The structure of the study yi 1.2 pl n ua al n va ll fu CHAPTER 2: LITERATURE REVIEW The definitions oi m 2.1 Pesticides 2.1.2 A maximum residue level or limit (MRL) at nh 2.1.1 z z Some contributions to gravity model theory 2.3 Empirical research ht vb 2.2 k jm Gravity model estimation using MRLs 2.3.2 Gravity model estimation using the regulated numbers of pesticides 10 l.c gm 2.3.1 om 2.3.3 Gravity model estimation either using MRL or the regulated numbers of pesticides 11 a Lu Distance and GDP per capita in gravity model 12 2.3.5 Extended control variables in gravity model 13 Advantages 18 iv y 3.1 te re CHAPTER 3: SITUATION OF VIETNAMESE COFFEE DURING 2005 - 2014 18 n Literature review summary 16 va 2.4 n 2.3.4 3.2 Disadvantages 19 3.3 The top contribution rankings for the importing Vietnamese coffee countries 20 t to CHAPTER 4: ECONOMETRIC MODEL AND DATA 23 ng 4.1 Specification of the model 23 hi ep 4.1.1 Gravity model 23 4.1.2 Extended variables in gravity model 24 w n Data 25 lo 4.2 Data source 25 4.2.2 y th ad 4.2.1 4.2.3 Descriptive statistical analysis 27 ju yi pl al Econometric models 28 n ua 4.3 Data description 25 Pooled OLS 28 4.3.2 Fixed Effect Estimation 29 4.3.3 Random Effect estimation 30 4.3.4 Driscoll and Kraay estimation 30 n va 4.3.1 ll fu oi m at nh 4.4 Choosing between OLS, Fixed Effect, and Random Effect estimation 31 z F Test for pooled OLS or Fixed Effect estimation 31 4.4.2 Breusch and Pagan Lagrangian Multiplier Test for Random Effect or OLS 31 4.4.3 The Hausman test 31 ht vb k jm gm Post-estimation tests 32 l.c 4.5 z 4.4.1 Multicollinearity 32 4.5.2 Heteroskedasticity 32 4.5.3 Serial correlation 32 om 4.5.1 n a Lu Estimating the intuitive gravity model 34 5.3 Empirical results 35 v y 5.2 te re Correlation matrix of all variables in the model 33 n 5.1 va CHARTER 5: EMPIRICAL RESULTS 33 5.3.1 The empirical results in the gravity model using the regulated number of pesticides variable 35 t to 5.3.2 The empirical results in the model using average maximum residue levels variable 39 ng hi CHAPTER 6: CONCLUSIONS AND POLICY IMPLICATIONS 42 ep 6.1 Conclusions 42 Main findings 42 w 6.2 n ad Limitations and future research 44 y th 6.4 Policy implications 43 lo 6.3 ju REFERENCES 45 yi pl APPENDICES 49 n ua al n va ll fu oi m at nh z z ht vb k jm om l.c gm n a Lu n va y te re vi LIST OF TABLES Table 3.1 Top 10 importing countries (selected data on share export quantity during t to 2005-2014) 20 ng Table 4.1: Descriptive statistical analysis 28 hi ep Table 5.1: The empirical results using the regulated number of pesticides variable 36 Table 5.2: The empirical results using average maximum residue levels variable 39 w n lo ad ju y th yi pl n ua al n va ll fu oi m at nh z z ht vb k jm om l.c gm n a Lu n va y te re vii LIST OF FIGURES Figure 1.1: Vietnam’s coffee export value in the period of 2004-2014 t to Figure 2.1 : Analytical Framework for Vietnam’s Coffee Export and its influencing factors 17 ng hi Figure 3.1: Distribution of Vietnam’s coffee to the major importing countries in the period of ep 2005-2014 21 Figure 3.2 : The top ten rankings for the major importing Vietnamese coffee countries w n annually 22 lo ad Figure 5.1: The correlation matrix of variables 33 y th Figure 5.2: The relationship between Pdistance and Vietnamese coffee export 34 ju yi Figure 5.3: The relationship between GDP per capita of importing countries and Vietnamese pl coffee export 35 n ua al n va ll fu oi m at nh z z ht vb k jm om l.c gm n a Lu n va y te re viii CHAPTER 1: INTRODUCTION 1.1 Problem statement t to ng It is undeniable that Vietnam is an agricultural country although the government is hi still moving towards industrialization and modernization in the future Meanwhile, ep agricultural products in general and coffee commodity in particular play a crucial position in export turnover of Vietnam To describe this matter, it may consider the total exports of w n Vietnam in the period of 2004-2014 which has been increasing significantly recent years lo ad ju y th yi pl n ua al n va ll fu oi m at nh z Figure 1.1: Vietnam’s coffee export value in the period of 2004-2014 z ht vb The Vietnamese economy has been entering a new development stage after joining jm WTO since 2007 wherein coffee export sector also adjusts to a great turning point The value k of coffee export reached more than USD 2.1 billion in 2008 Subsequently, it dropped in the gm two following years with the value export of nearly USD 1.76 and 1.90 billion respectively om l.c Nevertheless, there are also some years witnessing the decline in coffee export from Vietnam Specifically, demand from these countries and regions were also dropped slightly in 2010 and a Lu 2011 due to the change in food safety regulations However, it resumes good performance n period from 2011 to 2014 Furthermore, Vietnamese coffee is noticeably exported to many va countries around the world n countries, tariff is on the way to be lowered gradually Predictably, it will not be the important barrier in the coming time In practice, Henson and Loader (2001) identify that it appears to y as a result of WTO, FTA joining or agreements on bilateral and multilateral treaties among te re At the same period times, the tariff barriers in the world incline to drop Specifically, REFERENCES t to Anderson, J E (1979) A theoretical foundation for the gravity equation The American ng Economic Review, 69(1), 106-116 hi ep Anderson, J E., & Van Wincoop, E (2003) Gravity with gravitas: a solution to the border puzzle the american economic review, 93(1), 170-192 w n Antonie, M D., Cristescu, A., & Cataniciu, N (2010, June) A panel data analysis of the lo ad connection between employee remuneration, productivity and minimum wage in y th Romania In Proceedings of the 11th WSEAS Int Conf MCBE (pp 134-139) ju Aristotelous, K (2008) What is the effect of EMU on Greece’s exports to the yi Eurozone South-Eastern Europe Journal of Economics, 6(1), 39-51 pl ua al Atici, C (2013) Food Safety Regulations and Export Responses of Developing Countries: n The Case of Turkey’s Fig and Hazelnut Exports FAO commodity and trade policy n va research ll fu Baier, S L., & Bergstrand, J H (2009) Bonus vetus OLS: A simple method for nh International Economics,77(1), 77-85 oi m approximating international trade-cost effects using the gravity equation Journal of at Bekele, K (2011) Does Real Exchange Rate Matter for Ethiopia’s Exports? A Gravity Model z z Analysis (Doctoral dissertation, Addis Ababa University) vb ht Bergstrand, J H (1989) The generalized gravity equation, monopolistic competition, and the gm 143-153 k jm factor-proportions theory in international trade The review of economics and statistics, l.c Breusch, T S., & Pagan, A R (1980) The Lagrange multiplier test and its applications to om model specification in econometrics The Review of Economic Studies, 47(1), 239-253 from a panel gravity model The World Bank Economic Review,19(1), 99-120 n a Lu Brun, J F., Carrère, C., Guillaumont, P., & De Melo, J (2005) Has distance died? Evidence y te re economics thesis n Netherlands Programme for M.A in Development Economics, Master development va Bui, M K (2015) The impact of food safety standard on rice export from Vietnam Vietnam - Chen, C., Yang, J., & Findlay, C (2008) Measuring the effect of food safety standards on China’s agricultural exports Review of World Economics, 144(1), 83-106 45 Chen, M X., Otsuki, T., & Wilson, J S (2006) Do standards matter for export success? World Bank Policy Research Working Paper, (3809) t to Deardorff, A (1998) Determinants of bilateral trade: does gravity work in a neoclassical ng world? In The regionalization of the world economy (pp 7-32) University of Chicago hi Press ep Dong, Y., & Zhu, Y (2015) Impact of SPS Measures Imposed by Developed Countries on w China’s Tea Export-A Perspective of Differences in Standards Applied Economics and n lo Finance, 2(4), 160-169 ad Driscoll, J C., & Kraay, A C (1998) Consistent covariance matrix estimation with spatially y th dependent panel data Review of economics and statistics, 80(4), 549-560 ju yi Drogué, S., & DeMaria, F (2012) Pesticide residues and trade, the apple of discord? Food pl Policy,37(6), 641-649 al n va 1741-1779 n ua Eaton, J., & Kortum, S (2002) Technology, geography, and trade Econometrica, 70(5), Fang, W., & Miller, S M (2007) Exchange rate depreciation and exports: the case of fu ll Singapore revisited Applied Economics, 39(3), 273-277 m oi Ferro, E., Wilson, J S., & Otsuki, T (2013) The effect of product standards on agricultural nh exports from developing countries World Bank Policy Research Working Paper, (6518) at z Gujarati, D (2011) Econometrics by example Palgrave Macmillan z jm A Gravity model approach Modern Economy, 1(03), 134 ht vb Hatab, A A., Romstad, E., & Huo, X (2010) Determinants of Egyptian agricultural exports: k Helpman, E., & Krugman, P R (1985) Market structure and foreign trade: Increasing gm returns, imperfect competition, and the international economy MIT press l.c Henson, S., & Loader, R (2001) Barriers to agricultural exports from developing countries: om the role of sanitary and phytosanitary requirements World development, 29(1), 85-102 a Lu Jayasinghe, S., Beghin, J C., & Moschini, G (2010) Determinants of world demand for US n n 999-1010 va corn seeds: the role of trade costs American Journal of Agricultural Economics, 92(4), y te re Jongwanich, J (2009) The impact of food safety standards on processed food exports from developing countries Food Policy, 34(5), 447-457 Keith, T Z (2014) Multiple regression and beyond: An introduction to multiple regression and structural equation modeling Routledge 46 Kim, S J., & Reinert, K A (2009) Standards and Institutional Capacity: An examination of trade in food and agricultural products The International Trade Journal, 23(1), 54-77 t to Khan, I U., & Kalirajan, K (2011) The impact of trade costs on exports: An empirical ng modeling.Economic Modelling, 28(3), 1341-1347 hi ep Lee, H., & Park, I (2007) In search of optimised regional trade agreements and applications to East Asia The World Economy, 30(5), 783-806 w Linnemann, H (1966) An econometric study of international trade flows (No 42) North- n lo Holland Pub Co ad Ling, J I A N G (2013) Measurement of the Impacts of the Technical Barriers to Trade on y th Vegetable Export of China—An Empirical Study Based on the Gravity ju yi Model International Business and Management, 7(2), 20-25 pl Liu, X (2009) GATT/WTO promotes trade strongly: Sample selection and model al n ua specification Review of international Economics, 17(3), 428-446 n va Mangelsdorf, A., Portugal-Perez, A., & Wilson, J S (2012) Food standards and exports: evidence for China World Trade Review, 11(03), 507-526 ll fu m Mehmood, B., & Mustafa, H (2014) Empirical inspection of broadband-growth nexus: A oi fixed effects with Driscoll and Kraay standard errors approach Pakistan Journal of at nh Commerce and Social Sciences, 8(1), 01-10 z Moenius, J (2006, May) The good, the bad and the ambiguous: standards and trade in z ht vb agricultural products In IATRC Summer Symposium (Vol 5, pp 28-30) jm NOWAK‐LEHMANN, F E L I C I T A S., Herzer, D., MARTINEZ‐ZARZOSO, I N k M A C U L A D A., & Vollmer, S (2007) The Impact of a Customs Union between gm Turkey and the EU on Turkey's Exports to the EU JCMS: Journal of Common Market om l.c Studies, 45(3), 719-743 Otsuki, T., Wilson, J S., & Sewadeh, M (2001) Saving two in a billion: quantifying the trade a Lu effect of European food safety standards on African exports Food policy, 26(5), 495-514 (1963) A tentative model for the volume of trade between n countries Weltwirtschaftliches Archiv, 93-100 va P n Pöyhönen, y te re Rose, A K (2005) Does the WTO make trade more stable? Open economies review, 16(1), 7-22 47 Sarker, R., & Jayasinghe, S (2007) Regional trade agreements and trade in agri‐food products: evidence for the European Union from gravity modeling using disaggregated data Agricultural Economics, 37(1), 93-104 t to ng Shepherd, B (2013) The gravity model of international trade: A user guide ARTNeT Books hi and Research Reports ep Subramanian, A., & Wei, S J (2007) The WTO promotes trade, strongly but w unevenly Journal of international Economics, 72(1), 151-175 n lo Tinbergen, J (1962) Shaping the world economy; suggestions for an international economic ad policy Books (Jan Tinbergen) y th Thorbecke, W., & Zhang, H (2009) THE EFFECT OF EXCHANGE RATE CHANGES ON ju yi CHINA'S LABOUR‐INTENSIVE MANUFACTURING EXPORTS Pacific Economic pl Review, 14(3), 398-409 al n ua Wei, G., Huang, J., & Yang, J (2012) The impacts of food safety standards on China's tea n va exports China Economic Review, 23(2), 253-264 Wilson, J S., & Otsuki, T (2001) Global trade and food safety: winners and losers in a fu ll fragmented system (Vol 2689) World Bank Publications m oi Wilson, J S., & Otsuki, T (2004) To spray or not to spray: pesticides, banana exports, and at nh food safety Food policy, 29(2), 131-146 z Wilson, J S., Otsuki, T., & Majumdsar, B (2003) Balancing food safety and risk: drug z jm Economic Development, 12(4), 377-402 ht vb residue limits affect international trade in beef? Journal of International Trade & k Wooldridge, J M (2012) Introductory econometrics: A modern approach Nelson Education gm World Health Organization (2010) International code of conduct on the distribution and use om l.c of pesticides: Guidelines for the Registration of Pesticides Xiong, B., & Beghin, J (2011) Does European aflatoxin regulation hurt groundnut exporters n a Lu from Africa? European Review of Agricultural Economics, jbr062 n va y te re 48 APPENDICES Pooled OLS regression t to  Pooled OLS regression having ln_regnum ng hi Source SS df MS ep Number of obs F(8, 176) Prob > F R-squared Adj R-squared Root MSE w Model Residual n 176 112.774981 3.37411228 1496.04361 184 8.13067181 lo 902.199852 593.843761 ad Total = = = = = = 185 33.42 0.0000 0.6031 0.5850 1.8369 ju y th Coef Std Err yi ln_netweight t P>|t| [95% Conf Interval] pl al n n ll fu oi m -5.67 0.03 0.27 4.87 2.27 -4.21 3.38 5.61 4.09 at nh 0.000 0.976 0.786 0.000 0.024 0.000 0.001 0.000 0.000 -1.784763 -.3493333 -.1357127 3990549 0218915 -.0247881 0192331 1.707908 5.475073 z 2333771 1796989 0797282 1377388 072918 004011 0137057 4699936 2.589798 va -1.324185 0053087 0216337 6708872 1657977 -.0168723 0462819 2.635457 10.58613 ua ln_pdistance ln_gdpperc ln_regnum ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons -.8636077 3599507 17898 9427194 309704 -.0089566 0733306 3.563005 15.69718 z ht vb VIF n y te re 1.79 va Mean VIF n 0.388821 0.424582 0.544775 0.555142 0.628795 0.646813 0.649619 0.895954 a Lu 2.57 2.36 1.84 1.80 1.59 1.55 1.54 1.12 om ln_gdpperc ln_dconsum ln_rexrate simptax tradeopn ln_regnum ln_pdistance wtomemb l.c 1/VIF VIF gm Variable k jm  49  Pooled OLS regression having ln_avermrl Source SS df MS t to ng hi 913.472 582.571613 114.184 176 3.31006598 Total 1496.04361 184 8.13067181 ep Model Residual Number of obs F(8, 176) Prob > F R-squared Adj R-squared Root MSE = = = = = = 185 34.50 0.0000 0.6106 0.5929 1.8194 w n lo ad ln_netweight Coef Std Err t P>|t| [95% Conf Interval] ju y th pl n ua al n ll fu 0.000 0.815 0.064 0.000 0.048 0.000 0.003 0.000 0.000 oi m -5.81 -0.23 1.87 5.04 2.00 -4.64 2.97 5.98 4.55 -1.801069 -.3714492 -.0118029 4124953 0015971 -.0273413 0135074 1.861481 6.550335 -.8879701 2925216 4198211 9441137 2897056 -.0110129 06705 3.696954 16.58729 at nh 2313359 1682187 109353 1346869 072993 0041369 0135651 4650218 2.542888 va -1.34452 -.0394638 2040091 6783045 1456513 -.0191771 0402787 2.779218 11.56881 yi ln_pdistance ln_gdpperc ln_avermrl ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons z z vb VIF ht  1/VIF ln_gdpperc ln_dconsum ln_rexrate simptax tradeopn ln_pdistance ln_avermrl wtomemb 2.30 2.30 1.87 1.80 1.72 1.54 1.41 1.11 0.435281 0.435612 0.533337 0.555952 0.579883 0.648583 0.710805 0.897842 Mean VIF 1.76 k VIF jm Variable om l.c gm n a Lu n va y te re 50 Random Effect regression  Random Effect regression having ln_regnum t to ng hi ep Random-effects GLS regression Group variable: id Number of obs Number of groups R-sq: Obs per group: w within = 0.3226 between = 0.4284 overall = 0.4753 185 44 = avg = max = 4.2 = = 98.89 0.0000 n = = lo ad corr(u_i, X) Wald chi2(8) Prob > chi2 = (assumed) ju y th Coef Std Err yi ln_netweight pl n ua ll fu P>|z| -6.56 2.55 -1.69 3.91 -0.80 -1.17 0.80 3.79 3.23 [95% Conf Interval] 0.000 0.011 0.090 0.000 0.427 0.241 0.421 0.000 0.001 oi m -2.065022 1735955 -.2811548 3235022 -.3324256 -.0211585 -.0182637 520653 3.913039 -1.114752 1.320514 0205502 9753574 140549 0053246 0436983 1.6384 16.02638 at nh z z (fraction of variance due to u_i) ht vb 1.4777486 78617393 77940355 n sigma_u sigma_e rho 2424205 2925865 076967 1662927 120659 006756 0158069 2851447 3.090195 va -1.589887 7470546 -.1303023 6494298 -.0959383 -.0079169 0127173 1.079526 9.969709 al ln_pdistance ln_gdpperc ln_regnum ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons z jm Breusch and Pagan Lagrangian multiplier test for choosing Pooled OLS or k  gm Random Effect regression ln_netweight[id,t] = Xb + u[id] + e[id,t] om l.c Breusch and Pagan Lagrangian multiplier test for random effects 2.851433 7861739 1.477749 y te re Test: 8.130672 6180695 2.183741 n ln_netw~t e u sd = sqrt(Var) va Var n a Lu Estimated results: Var(u) = chibar2(01) = Prob > chibar2 = 122.02 0.0000 51  Random Effect regression having ln_avermrl Random-effects GLS regression Group variable: id Number of obs Number of groups R-sq: Obs per group: 185 44 = avg = max = 4.2 = = 106.06 0.0000 t to = = ng hi within = 0.3496 between = 0.4216 overall = 0.4838 ep w n lo corr(u_i, X) Wald chi2(8) Prob > chi2 = (assumed) ad y th ln_netweight Coef Std Err z P>|z| [95% Conf Interval] ju yi n ua al ll fu -7.02 1.85 2.75 4.03 -1.02 -1.80 0.63 3.70 4.27 0.000 0.064 0.006 0.000 0.310 0.072 0.527 0.000 0.000 -2.110548 -.0320715 0808471 3406462 -.3532786 -.0237769 -.020789 4864006 6.773475 -1.189639 1.107164 4836195 98435 1121002 000999 0405746 1.581453 18.26921 oi m 1.4697237 78145674 77960051 n sigma_u sigma_e rho 2349301 2906266 10275 1642132 1187213 0063205 0156543 2793552 2.932639 va -1.650093 5375461 2822333 6624981 -.1205892 -.0113889 0098928 1.033927 12.52134 pl ln_pdistance ln_gdpperc ln_avermrl ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons at nh z z (fraction of variance due to u_i) ht vb Breusch and Pagan Lagrangian multiplier test for choosing Pooled OLS or jm  k Random Effect regression gm om ln_netweight[id,t] = Xb + u[id] + e[id,t] l.c Breusch and Pagan Lagrangian multiplier test for random effects 2.851433 7814567 1.469724 n y te re Test: 8.130672 6106746 2.160088 va ln_netw~t e u sd = sqrt(Var) n Var a Lu Estimated results: Var(u) = chibar2(01) = Prob > chibar2 = 115.77 0.0000 52 Fixed Effect regression  Fixed Effect regression having ln_regnum t to ng Fixed-effects (within) regression Group variable: id Number of obs Number of groups R-sq: Obs per group: 185 44 = avg = max = 4.2 = = 15.99 0.0000 hi = = ep w n within = 0.4902 between = 0.0733 overall = 0.1257 lo ad y th F(8,133) Prob > F = -0.9097 ju corr(u_i, Xb) yi pl al Coef ln_pdistance ln_gdpperc ln_regnum ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons -1.84824 6.337632 -.207028 4501706 -.8969454 0169904 -.0031183 6279477 -33.65924 sigma_u sigma_e rho 6.5898192 78617393 98596693 Std Err t P>|t| [95% Conf Interval] n ua ln_netweight n va ll fu oi m -7.85 4.24 -2.57 2.29 -4.51 1.29 -0.20 2.38 -2.56 0.000 0.000 0.011 0.024 0.000 0.201 0.843 0.019 0.011 at nh z z -2.313871 3.384004 -.3661769 0609344 -1.290582 -.009149 -.0342794 1056561 -59.61822 -1.38261 9.29126 -.0478791 8394068 -.5033092 0431298 0280428 1.150239 -7.700265 ht vb 2354093 1.493269 0804611 1967866 1990111 0132153 0157541 2640555 13.12411 k jm F test that all u_i=0: F(43, 133) = 19.25 om l.c gm (fraction of variance due to u_i) Prob > F = 0.0000 n a Lu n va y te re 53  Fixed Effect regression having ln_avermrl t to ng hi Fixed-effects (within) regression Group variable: id Number of obs = Number of groups = R-sq: Obs per group: ep w within = 0.4963 between = 0.0909 overall = 0.1522 185 44 4.2 = = 16.38 0.0000 n = avg = max = lo ad F(8,133) Prob > F ju y th corr(u_i, Xb) = -0.9116 yi n ua al [95% Conf Interval] at nh 0.000 0.000 0.005 0.008 0.000 0.640 0.734 0.041 0.022 z -2.388215 3.078887 0878343 1413412 -1.303193 -.0169236 -.0364361 0216535 -56.48438 z -1.468279 9.005115 4717991 9249825 -.5284106 0274571 025738 1.044105 -4.399237 ht vb -8.29 4.03 2.88 2.69 -4.68 0.47 -0.34 2.06 -2.31 P>|t| oi m 6.4850048 78145674 98568708 ll sigma_u sigma_e rho 2325466 1.498065 0970608 1980932 1958537 0112188 0157167 2584609 13.16637 t fu -1.928247 6.042001 2798167 5331619 -.9158016 0052668 -.0053491 5328793 -30.44181 Std Err n pl ln_pdistance ln_gdpperc ln_avermrl ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons Coef va ln_netweight k jm F test that all u_i=0: F(43, 133) = 19.09 om l.c gm (fraction of variance due to u_i) Prob > F = 0.0000 n a Lu n va y te re 54 Hausman Test  Hausman Test for choosing Fixed Effect or Random Effect for ln_regnum t to Coefficients (b) (B) fixed_ln_r~m random_ln_~m ng (b-B) Difference sqrt(diag(V_b-V_B)) S.E hi ep ln_pdistance ln_gdpperc ln_regnum ln_dconsum ln_rexrate tradeopn simptax wtomemb w n lo ad -1.589887 7470546 -.1303023 6494298 -.0959383 -.0079169 0127173 1.079526 -.2583535 5.590577 -.0767257 -.1992592 -.8010072 0249073 -.0158356 -.4515787 1.464324 0234536 1052222 1582619 0113579 ju y th -1.84824 6.337632 -.207028 4501706 -.8969454 0169904 -.0031183 6279477 yi b = consistent under Ho and Ha; obtained from xtreg B = inconsistent under Ha, efficient under Ho; obtained from xtreg pl difference in coefficients not systematic n ua Ho: al Test: n va chi2(8) = (b-B)'[(V_b-V_B)^(-1)](b-B) = 38.05 Prob>chi2 = 0.0000 (V_b-V_B is not positive definite) ll fu oi m Hausman Test for choosing Fixed Effect or Random Effect for ln_ avermrl sqrt(diag(V_b-V_B)) S.E ht k gm 1.469604 1107923 1557688 0092689 0013998 om l.c a Lu -.2781535 5.504455 -.0024166 -.1293363 -.7952125 0166557 -.0152419 -.5010473 jm -1.650093 5375461 2822333 6624981 -.1205892 -.0113889 0098928 1.033927 vb -1.928247 6.042001 2798167 5331619 -.9158016 0052668 -.0053491 5328793 (b-B) Difference z ln_pdistance ln_gdpperc ln_avermrl ln_dconsum ln_rexrate tradeopn simptax wtomemb z Coefficients (b) (B) fixed_ln_a~l random_ln_~l at nh  n b = consistent under Ho and Ha; obtained from xtreg B = inconsistent under Ha, efficient under Ho; obtained from xtreg n va Ho: difference in coefficients not systematic y te re Test: chi2(8) = (b-B)'[(V_b-V_B)^(-1)](b-B) = 14.37 Prob>chi2 = 0.0726 (V_b-V_B is not positive definite) 55 Heteroskedasticity and autocorrelation test  Modified Wald test testing heteroskedasticity for ln_regnum t to Modified Wald test for groupwise heteroskedasticity in fixed effect regression model ng hi ep H0: sigma(i)^2 = sigma^2 for all i w chi2 (44) = Prob>chi2 = n 1.1e+05 0.0000 lo ad ju y th yi pl Wooldridge test testing autocorrelation for ln_regnum ua al  n Wooldridge test for autocorrelation in panel data H0: no first-order autocorrelation F( 1, 29) = 12.918 Prob > F = 0.0012 n va ll fu oi m at nh z z ht vb k jm om l.c gm n a Lu n va y te re 56  Modified Wald test testing heteroskedasticity for ln_avermrl t to Modified Wald test for groupwise heteroskedasticity in fixed effect regression model ng hi ep H0: sigma(i)^2 = sigma^2 for all i chi2 (44) = Prob>chi2 = w 4.9e+29 0.0000 n lo ad ju y th Wooldridge test testing autocorrelation for ln_avermrl yi  pl n ua al Wooldridge test for autocorrelation in panel data H0: no first-order autocorrelation F( 1, 29) = 12.958 Prob > F = 0.0012 n va ll fu oi m at nh z z ht vb k jm om l.c gm n a Lu n va y te re 57 Driscoll-Kraay Standard Errors for Fixed Effects Regression  Driscoll-Kraay Standard Errors for Fixed Effects Regression having ln_regnum t to ng hi ep Regression with Driscoll-Kraay standard errors Method: Fixed-effects regression Group variable (i): id maximum lag: w Number Number F( 8, Prob > within of obs of groups 43) F R-squared = = = = = 185 44 9512.52 0.0000 0.4902 n lo ad ju y th t yi ln_netweight Drisc/Kraay Coef Std Err P>|t| [95% Conf Interval] pl n ua n ll fu oi m at 0.000 0.000 0.000 0.014 0.019 0.037 0.603 0.003 0.018 z -2.426946 3.476145 -.3070172 0973874 -1.640639 0010617 -.0151181 2199325 -61.33137 z -1.269535 9.199119 -.1070387 8029537 -.1532521 0329191 0088815 1.035963 -5.987113 ht vb -6.44 4.47 -4.18 2.57 -2.43 2.15 -0.52 3.10 -2.45 nh 2869578 1.418901 0495808 1749316 3687689 0078984 0059502 202319 13.72154 va -1.84824 6.337632 -.207028 4501706 -.8969454 0169904 -.0031183 6279477 -33.65924 al ln_pdistance ln_gdpperc ln_regnum ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons k jm om l.c gm n a Lu n va y te re 58  Driscoll-Kraay Standard Errors for Fixed Effects Regression having ln_avermrl t to ng hi ep Regression with Driscoll-Kraay standard errors Method: Fixed-effects regression Group variable (i): id maximum lag: Number Number F( 8, Prob > within of obs of groups 43) F R-squared = = = = = 185 44 461.56 0.0000 0.4963 w n lo ad Drisc/Kraay Coef Std Err t P>|t| [95% Conf Interval] ju y th ln_netweight yi n ua al n ll fu oi m at 0.000 0.000 0.000 0.005 0.009 0.607 0.477 0.011 0.044 z -2.501717 2.910581 1882429 1691642 -1.592549 -.015215 -.0203744 1305977 -60.07072 z -6.78 3.89 6.16 2.95 -2.73 0.52 -0.72 2.67 -2.07 nh 2843618 1.55275 0454079 1804924 3355731 0101561 0074505 199476 14.69183 va -1.928247 6.042001 2798167 5331619 -.9158016 0052668 -.0053491 5328793 -30.44181 pl ln_pdistance ln_gdpperc ln_avermrl ln_dconsum ln_rexrate tradeopn simptax wtomemb _cons -1.354777 9.173421 3713906 8971595 -.2390539 0257486 0096763 9351609 -.8129 ht vb k jm om l.c gm n a Lu n va y te re 59