Home/Shrinkage priors for linear instrumental variable models with many instruments
Shrinkage priors for linear instrumental variable models with many instruments
Código: WPE – 342
P. Richard Hahn
This paper addresses the weak instruments problem in linear instrumental vari-able models from a Bayesian perspective. The new approach has two components. First,a novel predictor-dependent shrinkage prior is developed for the many instruments setting.The prior is constructed based on a factor model decomposition of the matrix of observedinstruments, allowing many instruments to be incorporated into the analysis in a robustway.Second, the new prior is implemented via an importance sampling scheme, which utilizesposterior Monte Carlo samples from a rst-stage Bayesian regression analysis. This modularcomputation makes sensitivity analyses straightforward.Two simulation studies are provided to demonstrate the advantages of the new method.As an empirical illustration, the new method is used to estimate a key parameter in macro-economic models: the elasticity of inter-temporal substitution. The empirical analysis pro-duces substantive conclusions in line with previous studies, but certain inconsistencies ofearlier analyses are resolved.