摘 要: | This paper investigates the generalized least squares estimation and the maximum likelihoodestimation of the parameters in a multivariate polychoric correlations model,based on data from amultidimensional contingency table.Asymptotic properties of the estimators are discussed.An iterativeprocedure based on the Gauss-Newton algorithm is implemented to produce the generalized leastsquares estimates and the standard errors estimates.It is shown that via an iteratively reweightedmethod,the algorithm produces the maximum likelihood estimates as well.Numerical results on thefinite sample behaviors of the methods are reported.
|