How different is Africa? A comment on Masanjala and Papageorgiou
指出Masanjala和Papageorgiou使用贝叶斯模型平均研究非洲与非非洲国家增长差异时，结果对模型空间的先验选择不稳健，特别是未遵循强遗传性原则。
Masanjala and Papageorgiou (Rough and lonely road to prosperity: a reexamination of the sources of growth in Africa using Bayesian model averaging, Journal of Applied Econometrics 2008; 23(5): 671–682) use Bayesian model averaging to evaluate the existence of parameter heterogeneity between African and non-African countries in the framework of cross-country growth regressions. We show that their results are not robust to the use of a prior over the model space that respects the strong heredity principle put forward by Chipman (Chipman HA. 1996. Bayesian variable selection with related predictors. Canadian Journal of Statistics 24: 17–36) for models including interaction terms. Copyright © 2010 John Wiley & Sons, Ltd.