Transformation model estimation of survival under dependent truncation and 
   Lead Investigator:    Jing Qian
   Institution      :    University of Massachusetts Amherst
   E-Mail           :    qian@umass.edu
   Proposal ID      :    875


   Publications:


1  Betensky R
   Statistical methods for censored and dependently truncated data
   42552   Grant  National Institute of Health (NIH)   1R01NS094610-01A1   , 

   FUNDED



2  Chiou SH, Austin MD, Qian J, Betensky RA
   Transformation model estimation of survival under dependent truncation and independent censoring
   Journal Article  Stat Methods Med Res,28(12):3785-3798,2019,PMC6565507

   PUBLISHED





   Proposal Description:
   Truncation is a mechanism that permits observation of selected subjects from a source population subjects are included only if their event times are contained within subject specific intervals. Standard survival analysis methods for estimation of the distribution of the event time require quasi-independence (Tsai, 1990) of failure and truncation. When quasi-independence does not hold, alternative estimation procedures are required currently there is a copula model approach that makes strong modeling assumptions, and a transformation model approach (Efron and Petrosian, 1994) that does not allow for right censoring. We extend the transformation model approach to accommodate right censoring. We propose a graphical and regression diagnostic for assessment of model fit. We evaluate the proposed transformation model in simulations and apply it to the National Alzheimer?s Coordinating Centers autopsy cohort study, the Channing House data set and an AIDS incubation study. Our methods are publicly available in an R package, tranSurv (Chiou, 2016).