Introductory Example 29 Introductory Example Regression analysis is the analysis of the relationship between one variable and an- The LIFEREG procedure fits parametric models to failure time data that can be uncensored, right censored, left censored, or interval censored. modified for left- or interval- censoring, due to the ability of PROC LIFEREG (embedded in the %AIC_SBC macro) to handle left- or interval- censored data. LIFEREG fits parametric models to failure-time data that may be right cen-sored. PROC BPHREG is an experimental upgrade to PHREG procedure that can be used to fit Bayesian Cox proportional hazards model (SAS Institute, Inc. (2007d)). INTRODUCTION The PROC LIFEREG and the PROC PHREG procedures both can do survival analysis using time-to-event data, what is the difference between the two. This paper will discuss this question by using some examples. PROC LIFEREG The LIFEREG procedure fits parametric accelerated failure time models to survival data that may be left, right, or interval censored. the GLM procedure. These types of models are commonly used in survival analysis. The models for the response variable consist of a linear effect composed of we should use PROC LIFEREG when we should use PROC PHREG, even for experienced statisticians who are using SAS. As part of this, I am using model fit statistics to decide which distribution is appropriate for my data. Re: Proc Lifereg Predicted Values Calculation Posted 11-29-2017 (1164 views) | In reply to Reeza I'm trying to manually recreate the calculations to better understand the procedure. The common statistics that you output from PROC LIFETEST are Median, 95% Confidence Intervals, 25th-75th percentiles, Minimum and Maximum, and p-values for Log-Rank and Wilcoxon. Re: OUTPUT Survival estimate from proc lifereg Posted 09-22-2014 08:08 AM (910 views) | In reply to desireatem As far as I know you can not get the survivalfunction directly from proc lifereg. Institute, Inc. (2007c)). proc lifereg data=raw outest=outest; model x*censor(1) = c1 / itprint distribution = weibull intercept=2.898 initial=0.16 scale=0.05; output out=out xbeta=xbeta; run; Examination of the resulting output in Output 73.3.4 shows that the convergence problem … *=====; * Example of an exponential regression *; *=====; options ls=75; data one; input y x cen; ***** you do not need to say [ly = log(y)] because it does log for you; ***** cannot have 0's in the responses, since log(0) is a no-no; cards; 15 2 0 13 3 1 9 1 1 19 3 1 12 2 1 ; proc lifereg data=one; model y = /dist=exponential; ***ignor censoring!! I am running some accelerated failure time models using PROC LIFEREG. 2. This particular example use Progression Free Survival data points. EXAMPLE – Basic Syntax to create any of the analyses listed above. Specifically, I am looking at the Exponential, Weibull, and Generalized Gamma distributions. Sample DataSample Data 866 AML or ALL patients866 AML or ALL patients Main Effect is Conditioning Regimen 71 (52 D d) R i 1 (71 (52 Dead) Regimp=1 (non-myelbli )loablative) 171 (93 Dead ) Regimp=2 (reduced intensity 625 (338 Dead) Regimp=4 (myeloablative) The second approach is based on the likelihood ratio test and can be used for comparing nested models, such as …