Recurrent Event Processes with Shape and Size Parameters

• Activity Number: 672
• Type: Invited
• Date/Time: Thursday, August 13, 2015 : 10:30 AM to 12:20 PM
• Sponsor: ENAR
• Author(s): Mei-Cheng Wang* and Chiung-Yu Huang
• Companies: The Johns Hopkins University and The Johns Hopkins University
• Keywords: recurrent event process ; size ; shape ; point process ; rate function

Abstract

This talk discusses a unified framework to characterise the rate function of a recurrent event process through shape and size parameters. The shape and size parameters are introduced and used to characterise the association between a random variable X and the rate function ?(.). Association measures between X and ?(.) are defined via shape- and size-based coefficients. The rate-independence is studied through tests of shape- and size-independence, where the test statistics can be used separately or in combination. These tests can be used when X is a covariable which is possibly correlated with the recurrent event process through ?(.), or in one sample setting, X is the censoring time at which the observation of N(.) is terminated. The proposed tests are shape- and size-based, so when a null hypothesis is rejected the test results can serve to distinguish the source of violation. A class of shape- and size-based regression models are developed as an extension of the proportional rate models. While still enjoying the feature being semiparametric, the new class of models possesses the advantage to model the size and shape components simultaneously and have desirable interpretation.