The survival function can be estimated in proc lifetest (as shown in section 5.1.19). Proc LifeTest Example: Life-Table Estimate The data in this example represent the survival rates of males with angina pectoris. Survival Analysis (Life Tables, Kaplan-Meier) using PROC LIFETEST in SAS Survival data consist of a response (time to event, failure time, or survival time) variable that measures the duration of time until a specified event occurs and possibly a set of independent variables thought to be associated with the failure time variable. For example, if I want to compare survival among males vs. females at 1, 3, and 5 years, is there an easy way to do this in proc lifetest? FIGURE 2A – PROC LIFETEST: KAPLAN MEIER CURVE KEY SYNTAX. Survival Analysis (Life Tables, Kaplan-Meier) using PROC LIFETEST in SAS Survival data consist of a response (time to event, failure time, or survival time) variable that measures the duration of time until a specified event occurs and possibly a set of independent variables thought to be associated with the failure time variable. the LIFETEST procedure for producing survival estimates. EP_UCL, a variable that contains the upper limits of the equal-precision confidence bands (if you specify the CONFBAND=EP option or the CONFBAND=ALL option in the PROC LIFETEST statement) If the estimation uses the life-table method, then the data set also contains the following: proc lifetest data=ds; time time*event(0); run; Here we denote censoring as being values where event is equal to 0. I agree it’s not particularly difficult programming to post-process the survival estimates table to get the the percentiles, but doing CIs is probably a little more tricky. As part of being semi-parametric approach, it looks like you're using the Fine-Gray model competing risks type approach, there are base assumptions that should be verified. PLOTS=SURVIVAL < more options > ; TIME. If we had a censoring indicator coded in reverse (1 = censoring), the second line might read time time*censored(1);. Lifetest uses non parametric approach and doesn't include covariates. If ‘outside’ had been a parameter, such as in, proc lifetest data=sashelp.BMT plots=survival(failure cb=hw test atrisk Secondly, to get both the survival estimates and the score test p-value, two separate models need to be fit, one stratified, and one non - stratified. For example, the PHREG procedure does not have the TIMELIST= option that allows users to output survival estimates at selected time points. PROC LIFETEST METHOD= KM . The paper discusses the rationale behind the RMST-based approach, outlines its recent development, and uses examples to illustrate real-world applications of the RMSTREG and LIFETEST procedures. Template: Stat.Lifetest.Graphics.ProductLimitFailure Path: Lifetest.SurvivalPlot -----This is the exact name of the template that PROC LIFETEST will look for to use whenever it is run. INTRODUCTION Warren F. Kuhfeld in Advanced Regression Models R&D at SAS demonstrates how to modify the survival plot from PROC LIFETEST by using procedure options and a set of macros. Subject (SUBJ) data for a small sample is presented in Table A and is sorted by time (YRS) to failure or censoring. An example of execution of this algorithm follows in Table A and Table B. Data are the number of events and number of withdrawals in each one-year time interval. PROC PHREG is more complicated but LIFETEST is a counting process. models, and you can use the RMST option in PROC LIFETEST to estimate the restricted mean survival time and make comparisons between groups. Usemethod = ltfor life-table method of computing estimates. Survival time is measured as years from the time of diagnosis. PHREG is a semi-parametric approach and can account for covariates.