Goodness-of-Fit Tests with Censored Data.pptVIP

Goodness-of-Fit Tests with Censored Data Edsel A. Pena Statistics Department University of South Carolina Columbia, SC [E-Mail: pena@stat.sc.edu] Practical Problem A Car Tire Data Set Goodness-of-Fit Problem Generalizing Pearson Obstacles with Censored Data In Hazards View: Continuous Case Two Common Examples Counting Processes and Martingales Idea in Continuous Case Hazard Embedding and Approach Class of Statistics Asymptotics and Test A Choice of ? Generalizing Pearson Special Case: Testing Exponentiality A Polynomial-Type Choice of ? Simulated Levels Simulated Powers Back to Lung Cancer Data Back to Davis Lawrance Car Tire Data Test of Exponentiality Test of Weibull Family Simple GOF Problem: Discrete Data Embedding Idea Class of Test Statistics A Pearson-Type Choice of ? A Polynomial-Type Choice Hyde’s Test: A Special Case Adaptive Choice of Smoothing Order Simulation Results for Simple Discrete Case Concluding Remarks Framework is general enough so as to cover both continuous and discrete cases. Mixed case dealt with via hazard decomposition. Since tests are score tests, they possess local optimality properties. Enables automatic adjustment of effects due to estimation of nuisance parameters. Basic approach extends Neyman’s 1937 idea by embedding hazards instead of densities. More studies needed for adaptive procedures. When p = 1 with polynomial specification, we obtain: Resulting test coincides with Hyde’s (‘77, Btka) test. = partial likelihood of = associated observed information matrix = partial MLE of Adjusted Schwarz (‘78, Ann. Stat.) Bayesian Information Criterion * Note: Based on polynomial-type specification. Performances of Pearson type tests were not as good as for the polynomial type. * Research support from NIH and NSF. Talk at Cornell University, 3/13/02 Product-Limit Estimator and Best-Fitting Exponential Survivor Function Question: Is the underlying survivor function modeled by a family of exponential distributions? a Weibull distribution?