Longitudinal Data Analysis with Both Monotone and Non-Monotone Missing Data

• Activity Number: 461
• Type: Contributed
• Date/Time: Wednesday, August 3, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Chi-hong Tseng*+ and Robert Elashoff
• Companies: University of California at Los Angeles and University of California at Los Angeles
• Keywords: missing data ; shared parameter model ; integrated likelihood

Abstract

A common problem in the longitudinal data analysis is the missing data problem. Two types of missing patterns are generally considered in the statistical literatures: monotone and non-monotone missingness. Non-monotone missing data are generally caused by intermittent missed visits by study participants. Monontone missing data can be from discontinued participation, loss to follow-up and mortality. Although many novel statistical approaches have been developed to handle missing data in recent years, few methods are available to provide inferences to handle both types of missing data simultaneously. In this research, a joint shared parameter model is proposed to analyze longitudinal outcome data with both monotone and non-monotone missingness. To overcome the difficulty of high dimensional integration in the estimation of the shared parameter model, we propose to use adaptive quadrature for computational efficiency since it requires fewer quadrature points to achieve the same precision. Simulation study is carried out and a real data example from the Scleroderma lung study is used to demonstrate the effectiveness of this method.