2L – Survival Analysis with Covariates

Survival Analysis with Covariates using BMDP Statistical Software Program 2L

2L analyzes survival data for which the time-to-response is influenced by other measured variables or covariates. Two analyses are available; the Cox proportional hazards regression model which presumes failure (death) rates may be modeled as log-linear functions of covariates and the other is the accelerated failure time or “log-linear model”.

• Cox proportional hazard models with built-in risk functions
• Accelerated failure time models (exponential, Weibull, log-logistic and log-normal distribution)
• Optional stepwise variable selections based on 2 methods
• Competing risk analysis
• User-specified time-dependent covariates
• Plots of cumulative survival function, log cumulative hazard function
• Stratified Analysis
• Hypothesis tests for joint significance of subsets of regression coefficients
• Diagnostic plots (Cox-Snell residuals, standardized residuals vs. each covariate, log of survival function versus time, etc.)
• View Program BMDP Program 2L Manual Chapter