@article { ISI:000366777800013, title = {Comparison of non-nested models under a general measure of distance}, journal = {Journal of Statistical Planning and Inference}, volume = {170}, year = {2016}, month = {MAR}, pages = {166-185}, publisher = {Elsevier Science BV}, type = {Article}, abstract = {As a supplement to summary statistics of information criteria, the closeness of two or more competing non-nested models can be compared under a procedure that is more general than that proposed in Vuong (1989); measures of closeness other than the Kullback-Leibler divergence are allowed. Large deviation theory is used to obtain a bound of the power of rejecting the null hypothesis that the two models are equally close to the true model. Such a bound can be expressed in terms of a constant gamma is an element of [0, 1); gamma can be computed empirically without any knowledge of the data generating mechanism. Additionally, based on the constant gamma, the procedures constructed based on different measures of distance can be compared on their abilities to conclude a difference between two models. (C) 2015 Elsevier B.V. All rights reserved.}, keywords = {Composite likelihood, Copula, Large deviation theory, Model comparison, Model misspecification}, issn = {0378-3758}, doi = {10.1016/j.jspi.2015.10.004}, author = {Ng, C. T. and Joe, Harry} } @article { ISI:000342542300004, title = {Model comparison with composite likelihood information criteria}, journal = {Bernoulli}, volume = {20}, number = {4}, year = {2014}, month = {NOV}, pages = {1738-1764}, publisher = {Int Statistical Inst}, type = {Article}, abstract = {Comparisons are made for the amount of agreement of the composite likelihood information criteria and their full likelihood counterparts when making decisions among the fits of different models; and some properties of penalty term for composite likelihood information criteria are obtained. Asymptotic theory is given for the case when a simpler model is nested within a bigger model, and the bigger model approaches the simpler model under a sequence of local alternatives. Composite likelihood can more or less frequently choose the bigger model, depending on the direction of local alternatives; in the former case, composite likelihood has more {\textquoteleft}{\textquoteleft}power{\textquoteright}{\textquoteright} to choose the bigger model. The behaviors of the information criteria are illustrated via theory and simulation examples of the Gaussian linear mixed-effects model.}, keywords = {Akaike information criterion, Bayesian information criterion, local alternatives, mixed-effects model, Model comparison}, issn = {1350-7265}, doi = {10.3150/13-BEJ539}, author = {Ng, C. T. and Joe, Harry} }