Empirical Economics

, Volume 54, Issue 4, pp 1517–1547 | Cite as

Of needles and haystacks: revisiting growth determinants by robust Bayesian variable selection

  • Kuo-Jung Lee
  • Yi-Chi Chen


This paper proposes a Bayesian variable selection technique that is robust to model uncertainty and heteroscedasticity of unknown forms in cross-country growth regressions. In particular, we adopt a spike-and-slab prior for the regression coefficients to sidestep the potential complications of highly collinear covariates in the variable selection problems. We find a number of important growth determinants that are distinct from the previous works in the ranking and sign of estimated coefficients, partly because of the presence of highly correlated covariates. Importantly, we find that our results from variable selection are not qualitatively changed when various degrees of freedom for t-errors are considered. The implications of this work highlight the caution needed in empirical growth research when using g-priors under collinearity.


Determinants of economic growth Robust variable selection Heteroscedasticity Outliers Bayesian methods Correlated covariates 

JEL Classification

C11 C21 C52 


  1. Barbieri MM, Berger JO (2004) Optimal predictive model selection. Ann Stat 32:870–897Google Scholar
  2. Barro RJ (1991) Economic growth in a cross-section of countries. Q J Econ 106:407–443CrossRefGoogle Scholar
  3. Brock WA, Durlauf SN (2001) Growth empirics and reality. World Bank Econ Rev 15:229–272CrossRefGoogle Scholar
  4. Brooks S, Gelman A, Jones GL, Meng X (2011) Handbook of Markov chain Monte Carlo. Chapman & Hall/CRC, Boca RatonCrossRefGoogle Scholar
  5. Ciccone A, Jarociński M (2010) Determinants of economic growth: will data tell? Am Econ J Macroecon 2:222–246CrossRefGoogle Scholar
  6. Clyde M, George EI (2004) Model uncertainty. Stat Sci 19:81–94CrossRefGoogle Scholar
  7. Doppelhofer G (2008) Model averaging. In: Durlauf SN, Blume LE (eds) The new palgrave dictionary of economics. Palgrave Macmillan, BasingstokeGoogle Scholar
  8. Doppelhofer G, Weeks M (2009) Jointness of growth determinants (with discussion). J Appl Econ 24:209–244CrossRefGoogle Scholar
  9. Doppelhofer G, Weeks M (2011) Robust growth determinants. NHH discussion paper. doi: 10.2139/ssrn.1762697. Accessed 16 Nov 2016
  10. Durlauf SN, Johnson PA, Temple JRW (2005) Growth econometrics. In: Aghion P, Durlauf SN (eds) Handbook of economic growth. Elsevier, North HollandGoogle Scholar
  11. Durlauf SN, Quah DT (1999) The new empirics of economic growth. In: Taylor JB, Woodford M (eds) Handbook of macroeconomics. Elsevier, North HollandGoogle Scholar
  12. Eicher TS, Papageorgiou C, Raftery AE (2011) Default priors and predictive performance in Bayesian model averaging, with application to growth determinants. J Appl Econ 26:30–55CrossRefGoogle Scholar
  13. Fernández C, Ley E, Steel MFJ (2001) Model uncertainty in cross-country growth regressions. J Appl Econ 16:563–576CrossRefGoogle Scholar
  14. Flegal JM, Haran M, Jones GL (2008) Markov chain Monte Carlo: can we trust the third significant figure? Stat Sci 23:250–260CrossRefGoogle Scholar
  15. Gelfand AE, Smith AFM (1990) Sampling-based approaches to calculating marginal densities. J Am Stat Assoc 85:398–409CrossRefGoogle Scholar
  16. George EI, McCulloch RE (1993) Variable selection via Gibbs sampling. J Am Stat Assoc 88:881–889CrossRefGoogle Scholar
  17. George EI, McCulloch RE (1997) Approaches for Bayesian variable selection. Stat Sin 7:339–374Google Scholar
  18. Geweke J (1993) Bayesian treatment of the independent Student-\(t\) linear model. J Appl Econ 8:S19–S40CrossRefGoogle Scholar
  19. Ghosh J, Ghattas AE (2015) Bayesian variable selection under collinearity. Am Stat 69:165–173CrossRefGoogle Scholar
  20. Ho T-K (2015) Looking for a needle in a haystack: Revisiting the cross-country causes of the 2008–2009 crisis by Bayesian model averaging. Economica 82:813–840CrossRefGoogle Scholar
  21. Hoeting J, Raftery AE, Madigan D (1996) A method for simultaneous variable selection and outlier identification in linear regression. Comput Stat Data Anal 22:251–270CrossRefGoogle Scholar
  22. Hoeting JA, Madigan D, Raftery AE, Volinsky CT (1999) Bayesian model averaging: a tutorial. Stat Sci 14:382–417CrossRefGoogle Scholar
  23. Khalili A (2011) An overview of the new feature selection methods in finite mixture of regression models. J Iran Stat Soc 10:201–235Google Scholar
  24. Korobilis D (2013) Bayesian forecasting with highly correlated predictors. Econ Lett 118:148–150CrossRefGoogle Scholar
  25. Krishna A, Bondell HD, Ghosh SK (2009) Bayesian variable selection using an adaptive powered correlation prior. J Stat Plan Infer 139:2665–2674CrossRefGoogle Scholar
  26. Levine R, Renelt D (1992) A sensitivity analysis of cross-country growth regressions. Am Econ Rev 82:942–963Google Scholar
  27. Ley E, Steel MFJ (2009) On the effect of prior assumptions in Bayesian model averaging with applications to growth regressions. J Appl Econ 24:651–674CrossRefGoogle Scholar
  28. Liang F, Paulo R, Molina G, Clyde MA, Berger JO (2008) Mixtures of \(g\) priors for Bayesian variable selection. J Am Stat Assoc 103:410–423CrossRefGoogle Scholar
  29. Moral-Benito E (2015) Model averaging in economics: an overview. J Econ Surv 29:46–75CrossRefGoogle Scholar
  30. O’Hara RB, Sillanpää MJ (2009) A review of Bayesian variable selection methods: What, how and which. Bayesian Anal 4:85–118CrossRefGoogle Scholar
  31. Raftery AE (1995) Bayesian model selection in social research. Sociol Methodol 25:111–163CrossRefGoogle Scholar
  32. Raftery AE, Madigan D, Hoeting JA (1997) Bayesian model averaging for linear regression model. J Am Stat Assoc 92:179–191CrossRefGoogle Scholar
  33. Rossi PE, Allenby GM, McCulloch R (2005) Bayesian statistics and marketing. Wiley, HobokenCrossRefGoogle Scholar
  34. Sala-i-Martin X, Doppelhofer G, Miller RI (2004) Determinants of long-term growth: a Bayesian averaging of classical estimates (BACE) approach. Am Econ Rev 94:813–835CrossRefGoogle Scholar
  35. Sala-i-Martin XX (1997) I just ran two million regressions. Am Econ Rev 87:178–183Google Scholar
  36. Sturm J-E, de Haan J (2005) Determinants of long-term growth: new results applying robust estimation and extreme bounds analysis. Empir Econ 30:597–617CrossRefGoogle Scholar
  37. Temple JRW (1998) Robustness tests of the augmented Solow model. J Appl Econ 13:361–375CrossRefGoogle Scholar
  38. Temple JRW (2000) Growth regressions and what the textbooks don’t tell you. Bull Econ Res 52:181–205CrossRefGoogle Scholar
  39. Turnovsky SJ, Fisher WH (1995) The composition of government expenditure and its consequences for macroeconomic performance. J Econ Dyn Control 19:747–786CrossRefGoogle Scholar
  40. Zellner A (1986) On assessing prior distributions and Bayesian regression analysis with \(g\)-prior distributions. In: Goel PK, Zellner A (eds) Bayesian inference and decision techniques: essays in honor of Bruno de Finetti. North-Holland/Elsevier, Amsterdam, pp 233–243Google Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  1. 1.Department of StatisticsNational Cheng Kung UniversityTainanTaiwan
  2. 2.Department of EconomicsNational Cheng Kung UniversityTainanTaiwan

Personalised recommendations