# Statistical Advisor, Regression for Censored Survival Times

Use SURVIVAL ANALYSIS. This chapter discusses several multiple regression models commonly used with censored or uncensored data sets with survival/failure times.

A data set is said to be 'censored' if some observations are incomplete, but not missing. For example, in industrial reliability testing, a part or product may not fail (break) within the time span covered by a study. However, we do not know how long it will function properly thereafter, and thus, that observation is 'censored.' If we had several predictor variables of a part's resilience (e.g., some characteristics of the manufacturing process of that part), the SURVIVAL ANALYSIS module would be appropriate for testing the predictive power of those independent variables.

Typical multiple regression models that are used to predict survival or failure times are the Cox proportional hazard model, the normal and log-normal regression model, and the exponential regression model. The SURVIVAL ANALYSIS module will compute maximum likelihood estimates for all of these models.