Likelihood Ratio Based Model Selection Test for Spatial Data
主讲人: Tuo Liu, The Ohio State University

 CV: Upload/File/2016/12/20161213063805577.pdf

主持人: Xuexin Wang

Abstract: This paper generalizes the likelihood-ratio based test for model selection in Vuong(1989) to models with spatial near-epoch dependent (NED) data. We measure the distance from a model to a data generating process by Kullback-Leibler Information Criterion, and test the null hypothesis that two models are equally close to the data generating process. We make no assumption on the model specification of the truth, and allow for the cases where both, either or neither of the two competing models is mis-specified. As a prerequisite of the test, we first show that the quasi-maximum likelihood estimators (QMLE) of possibly mis-specified spatial models are consistent estimators of their pseudo-true values, and are asymptotically normal under regularity conditions. In particular, we study spatial autoregressive models with spatial autoregressive errors (SARAR) and matrix exponential spatial specification (MESS) models. We then construct a Vuong's style model selection test for essential non-nested competing models with spatially dependent data. A spatial heteroskedastic and autoregressive consistent estimator of asymptotic variance of the test statistic, which is necessary to implement the test, is constructed. Monte Carlo experiments are designed to investigate finite sample performance of QMLEs for SARAR and MESS models, as well as empirical sizes and powers of the proposed test.

时间: 2016-12-21(Wednesday)16:40-18:00
地点: 经济楼N401
主办单位: SOE&WISE
类型: 其他