On the Effect of Prior Assumptions in Bayesian Model Averaging with Applications to Growth Regression

By E. Ley, Mark F. J. Steel. 2007

551 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/810a236a64edf9d4b4236f7050debb4ed402c1a2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Determinants of Horizontal Spillovers from FDI: Evidence from a Large Meta-Analysis (2013, methodology): “Model Prior g-Prior 1.0000 1195 random BRIC Shrinkage-Stats Av= 0.9995 Notes: The “random” model prior refers to the beta-binomial prior advocated by Ley & Steel (2009): prior model probabilities are the same for all possible models; in other words, we do not a priori prefer any particular model…”
The Median Probability Model and Correlated Variables (2018, background): “Beta-binomial Prior: It is generally acknowledged (Cui and George 2008; Ley and Steel 2009; Scott and Berger 2010) that assigning equal prior probability to all models is a poor choice, since it does not adjust for the multiple testing that is effectively being done in variable selection.”
Model Averaging and Its Use in Economics (2017, methodology): “While Fernández et al. (2001a) examined the effects of choosing fixed values for g, a more systematic investigation of the interplay between g and w was conducted in Ley and Steel (2009b) and Eicher et al. (2011).”
Benchmark Priors Revisited: On Adaptive Shrinkage and the Supermodel Effect in Bayesian Model Averaging (2009, unknown): “The proposal of Ley and Steel (2009) is to impose that the model size follows a beta-binomial(a, b) distribution (Bernardo and Smith (1994)) with a = 1, so that P (k = kj) = Γ(1 + b) Γ(1) + Γ(b) + Γ(1 + b+K) ( K kj ) Γ(1+kj)Γ(b+K−kj) kj = 0, . . . , K. (A.3) The prior can be elicited by anchoring…”
Determinants of Economic Growth: A Bayesian Panel Data Approach (2009, unknown): “S = log f ( y|θ̂i,Mi ) − log f ( y|θ̂j,Mj ) − (ki − kj) 2 log (NT ) , (24)”
Natural Disasters and Human Capital Accumulation (2009, unknown): “Albala‐ Bertrand (1993a, 1993b), Tol and Leek (1999), Rasmussen (2004) or Noy (2009) are some modern examples of research aimed at measuring the short and medium‐run impacts of disasters.”
Mixtures of g-Priors in Generalized Linear Models (2015, background): “, p (Ley and Steel 2009) and encourages sparsity when pMT p/2.”
Determinants of Foreign Direct Investment (2011, unknown): “To simulate from the model space, we use the Markov Chain Monte Carlo Model Composition (MC3) algorithm of Madigan and York (1995). This approach relies on the Metropolis-Hastings algorithm, which can be used to provide random samples from any probability distribution provided it is known up to a pr”
Forecast Combination and Bayesian Model Averaging - A Prior Sensitivity Analysis (2012, methodology): “However, Ley and Steel (2009) show how to calibrate the prior over the models in terms of the expected model size.2 Following Ley and Steel (2009) we put a binomial-beta prior on the inclusion probability.”
Forecasting the European carbon market (2013, methodology): “In regression problems with many potential explanatory variables, Bayesian model averaging (BMA) has been a common response to such worries (see, among many others, Raftery, Madigan and Hoeting, 1997, Fernandez, Ley and Steel 2001a,b; Eicher, Papageorgiou and Raftery 2010 and Ley and Steel 2010). Ho”
Bank Competition and Financial Stability: Much Ado About Nothing? (2015, unknown): “Notes: The “random“ model prior refers to the beta-binomial prior used by Ley & Steel (2009): the prior model probabilities are the same for all possible model sizes.”
Mixtures of g-priors for Bayesian model averaging with economic applications (2010, unknown): “With the exception of the priors in Maruyama and George (2010) and Forte et al. (2010), the priors on model space do not depend on g and easy analytical expressions for P (Mj) exist, in the case of fixed and random prior covariate inclusion probabilities (Ley and Steel, 2009).”
Weighted‐Average Least Squares (WALS): A Survey (2016, background): “For additional references and recent developments on the choice of priors in BMA, the reader is referred to Eicher et al. (2011) and Ley and Steel (2009, 2012).”
Complete subset regressions (2013, methodology): “(15) and (16), we follow the specification suggested by Fernandez et al. (2001a,b) and Ley and Steel (2009).”
Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem (2010, methodology): “Fully Bayesian variable-selection priors have been discussed by Ley and Steel (2009), Cui and George (2008) and Carvalho and Scott (2009), among others.”