Publication: On the Effect of Prior Assumptions in Bayesian Model Averaging with Applications to Growth Regression
No Thumbnail Available
Date
2009
ISSN
08837252
Published
2009
Author(s)
Editor(s)
Abstract
We consider the problem of variable selection in linear regression models. Bayesian model averaging has become an important tool in empirical settings with large numbers of potential regressors and relatively limited numbers of observations. We examine the effect of a variety of prior assumptions on the inference concerning model size, posterior inclusion probabilities of regressors and on predictive performance. We illustrate these issues in the context of cross-country growth regressions using three datasets with 41-67 potential drivers of growth and 72-93 observations. Finally, we recommend priors for use in this and related contexts.
Link to Data Set
Associated content
Other publications in this report series
Journal
Journal Volume
Journal Issue
Citations
Collections
Related items
Showing items related by metadata.
Publication On the Effect of Prior Assumptions in Bayesian Model Averaging with Applications to Growth Regression(World Bank, Washington, DC, 2007-06)This paper examines the problem of variable selection in linear regression models. Bayesian model averaging has become an important tool in empirical settings with large numbers of potential regressors and relatively limited numbers of observations. The paper analyzes the effect of a variety of prior assumptions on the inference concerning model size, posterior inclusion probabilities of regressors, and predictive performance. The analysis illustrates these issues in the context of cross-country growth regressions using three datasets with 41 to 67 potential drivers of growth and 72 to 93 observations. The results favor particular prior structures for use in this and related contexts.Publication Mixtures of g-priors for Bayesian Model Averaging with Economic Application(2011-07-01)This paper examines the issue of variable selection in linear regression modeling, where there is a potentially large amount of possible covariates and economic theory offers insufficient guidance on how to select the appropriate subset. In this context, Bayesian Model Averaging presents a formal Bayesian solution to dealing with model uncertainty. The main interest here is the effect of the prior on the results, such as posterior inclusion probabilities of regressors and predictive performance. The authors combine a Binomial-Beta prior on model size with a g-prior on the coefficients of each model. In addition, they assign a hyperprior to g, as the choice of g has been found to have a large impact on the results. For the prior on g, they examine the Zellner-Siow prior and a class of Beta shrinkage priors, which covers most choices in the recent literature. The authors propose a benchmark Beta prior, inspired by earlier findings with fixed g, and show it leads to consistent model selection. Inference is conducted through a Markov chain Monte Carlo sampler over model space and g. The authors examine the performance of the various priors in the context of simulated and real data. For the latter, they consider two important applications in economics, namely cross-country growth regression and returns to schooling. Recommendations for applied users are provided.Publication Comments on 'Jointness of Growth Determinants'(2009)We consider the measures of jointness proposed by Doppelhofer and Weeks (2009) and Strachan (2009) in the context of variable selection. Using the general criteria suggested in Ley and Steel (2007), we identify some shortcomings of these measures, which are illustrated with empirically relevant example cases. We argue that careful examination of the properties of any jointness measure is critical before using it to inform decisions, and favour the use of the measures proposed in Ley and Steel (2007).Publication Natural Disasters and Growth : Going beyond the Averages(2009-06-01)There has been a steady increase in the occurrence of natural disasters. Yet their effect on economic growth remains unclear, with some studies reporting negative, and others indicating no, or even positive effects. These seemingly contradictory findings can be reconciled by exploring the effects of natural disasters on growth separately by disaster and economic sector. This is consistent with the insights from traditional models of economic growth, where production depends on total factor productivity, the provision of intermediate outputs, and the capital-labor ratio, as well as the existence of important intersector linkages. Applying a dynamic Generalized Method of Moments panel estimator to a 1961-2005 cross-country panel, three major insights emerge. First, disasters affect economic growth - but not always negatively, and differently across disasters and economic sectors. Second, although moderate disasters can have a positive growth effect in some sectors, severe disasters do not. Third, growth in developing countries is more sensitive to natural disasters - more sectors are affected and the magnitudes are non-trivial.Publication Jointness in Bayesian Variable Selection with Applications to Growth Regression(2006-11-01)The authors present a measure of jointness to explore dependence among regressors in the context of Bayesian model selection. The jointness measure they propose equals the posterior odds ratio between those models that include a set of variables and the models that only include proper subsets. They show its application in cross-country growth regressions using two data-sets from the model-averaging growth literature.
Users also downloaded
Showing related downloaded files
No results found.