Software for Efficient Estimation of the Cox Model With Interval-Censored Data

Software for Ef cient Estimation of the Cox Model With Interval Censored Data Project Summary Interval censored data arise frequently in clinical and epidemiological studies because the time to the development of an asymptomatic diseasee gtumor occurrenceHIV infectioncannot be observed exactly but rather is known to lie in a time interval between two consecutive clinical examinationsRecent theoretical and computational advances have made it possible tot the well known Cox proportional hazards model with potentially time dependent covariates to interval censored data through ef cient nonparametric maximum likelihood estimationThe broadlong term objective of this SBIR proposal is to create a suite of commandsalong with a companion textin the widely used commercial software package Stata for performing cutting edge nonparametric maximum likelihood estimation of the Cox proportional hazards model with time dependent covariates and interval censored event timesThe goal of the Phase I project is to establish the scienti c merit and technical feasibility of the proposed research and development effortwith two speci c aimsto develop and implement numerical methods for performing nonparametric maximum likelihood estimation of the Cox proportional hazards model for a single disease with unrelated subjects under interval censoringandto certify the correctness of the estimation results of the new command by comparing them to results from published papers and limited research codeThe Phase II project then will use the procedures developed in Phase I to build a suite of commands for semiparametric regression analysis of interval censored data that is reliablerobustuser friendlyand optimized for speed and memory ef ciencyThe code also will be expanded substantially to allow non proportional hazards and to deal with multiple diseases and clustered data under interval censoringIn additiona companion text will be written to not only document the software itselfbut also serve as a substantive reference for researchers new to theeldThe software program produced by this SBIR project will be an integral part of the Stata package and thus will be marketed by StataCorpThis powerful new tool will enable biomedical investigators to analyze interval censored data in a statistically ef cient and unbiased mannerAs suchthe tool will facilitate the search for effective intervention and prevention strategies for many common diseasese gcancerHIV AIDSdiabeteshypertensionthereby leading to improvements in public health Project Narrative The broadlong term objective of this SBIR project is to develop a suite of commands in the widely used commercial software package Stata in order to perform statistical analysis of times to occurrence of asymptomatic diseases that can only be detected through periodic clinical examinationsThis powerful tool will enable clinical and epidemiological investigators to analyze an important type of biomedical data in a statistically ef cient and unbiased manner and thereby facilitate the discovery of effective intervention and prevention strategies for many diseases of utmost public health signi cancesuch as cancerHIV AIDSdiabetesand hypertension