MAXIMUM-LIKELIHOOD-ESTIMATION IN THE PROPORTIONAL ODDS MODEL

We consider maximum likelihood estimation of the parameters in the pro portional odds model with right-censored data. The estimator of the re gression coefficient is shown to be asymptotically normal with efficie nt variance. The maximum likelihood estimator of the unknown monotonic transformation of the survival time converges uniformly at a parametr ic rate to the true transformation. Estimates for the standard errors of the estimated regression coefficients are obtained by differentiati on of the profile likelihood and are shown to be consistent. A likelih ood ratio test for the regression coefficient is also considered.