Pseudo-likelihood inference for clustered binary data |
| |
Authors: | Helena Geys Geert Molenberghs Louise M Ryan |
| |
Institution: | Harvard School of Public Health , Limburgs Universitair Centrum , Boston, MA, 02115, U.S.A |
| |
Abstract: | The maximum likelihood procedure to estimate paraneters of a model has scveral attractive properties including the existence of the covariance matrix which yield asymptotic covariances: for a sample size N the asymptotics are in general of order 1/N. Here we give an asymptotic for the skewness of the distribution of the maximum likelihood estimator of a parameter; this is of order 1/ n2 and this expression is new. Applications relate to the parameters of (i) the Poisson, binomial, and normal density. (ii) the gamna density and (iii) the Beta debsity. Other application are being considered. The expression for the asymptotic skowness at one phase of the study tured out to be unusually complicated involving the asymptotic expressions for variance and bias. When these were identified a much simpler compact expression appeared which we now describe. The work is a much improved treatment of the subject described in Shenton and Bowman (Mariunm likelihood estimation in small samples, Griffin. 1977). |
| |
Keywords: | Clustered Data Developmental Toxicity Exponential Family Likelihood Normalizing Constant |
|
|