E cient Estimation for the Proportional Hazards Model with Case Interval Censoring

Maximum likelihood estimation for the proportional hazards model with interval censored data is considered The estimators are computed by pro le likelihood methods using Groeneboom s iterative convexminorant algorithm Under appropriate regularity conditions the maximum likelihood estimator for the regression parameter is shown to be asymptotically normal and e cient Two approaches for estimation of the variance covariance matrix for the estimated regression parameter are proposed one uses the inverse of the observed information matrix another uses the curvature of the pro le likelihood function An example is given to illustrate the proposed methods