A Bayesian specification test

• Main Authors: LI, Yong, ZENG, Tao, Jun YU
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2015
• Subjects: EM algorithm; Specification test; Latent variable models; Markov chain; Monte Carlo; Dynamic factor; DSGE; Stochastic volatility; Econometrics
• Online Access: https://ink.library.smu.edu.sg/soe_research/1798; https://ink.library.smu.edu.sg/context/soe_research/article/2797/viewcontent/P_ID_50755_BaynesiaSpecificationTest27_2015May26.pdf
• Institution: Singapore Management University

A Bayesian test statistic is proposed to assess the model specification after the model is estimated by Bayesian MCMC methods. The proposed approach does not require an alternative model to be specified and is applicable to a variety of models, including latent variable models, structural dynamic choice models, and dynamics stochastic general equilibrium (DSGE) models, for which frequentist methods are difficult to use. The properties of the test statistic are established and its implementation is discussed. The test is easy to use and the test statistic can be calculated from MCMC outputs even when there are latent variables. The method is illustrated using a dynamic factor model, a DSGE model and a stochastic volatility model.