About peppapig

peppapig · ‎07-14-2016

Proc phreg model, got error message, how to solve this problem? Thanks! proc phreg data = data COVS(AGGREGATE); CLASS x2 x3 x4 x5 /ref = first; model time_event * event(0) = x1 x2 x3 x4 x5 /RL; run; ERROR: Floating Point Overflow. ERROR: Termination due to Floating Point Exception NOTE: The SAS System stopped processing this step because of errors. NOTE: PROCEDURE PHREG used (Total process time): real time 2.80 seconds cpu time 2.37 seconds

peppapig · ‎07-22-2015

Thanks so much!

peppapig · ‎07-21-2015

Thanks so much! how to understand that: estimate "trend test" group*time 3 1 -1 -3/e cl divisor=2; group * time is for" estimate of the trend in group at the first time point."? and estimate "trend test" group 3 1 -1 -3/e cl divisor=2; is for " provides an estimate averaged over all time points" ? Thank you.

peppapig · ‎07-20-2015

Hi Steve, Thanks for all your help. I really appreciate it. For the trend test, I still have some questions. For the three estimate statements below,they gave me different p values for the trend test. How to interpret these three types of estimates statements? group values = 1,2,3,4. group 3 1 -1 -3 group*time 3 1 -1 -3 in the 1st model or group*time 3 1 -1 -3 or group 3 1 -1 -3 ? Thank you so much. **************************************************************** proc sort data= data1 ; by descending group; run; proc mixed data = data1 COVTEST NOITPRINT; class haltid group(ref = "1"); model y = time group time* group/solution cl; random int /subject = id type = un; estimate "trend test" group 3 1 -1 -3 group*time 3 1 -1 -3/e cl divisor=2; run; proc mixed data = data1 COVTEST NOITPRINT; class haltid group(ref = "1"); model y = time group time* group /solution cl; random int /subject = id type = un; estimate "trend test" group*time 3 1 -1 -3/e cl divisor=2; run; proc mixed data = data1 COVTEST NOITPRINT; class haltid group(ref = "1"); model y = time group time* group /solution cl; random int /subject = id type = un; estimate "trend test" group 3 1 -1 -3/e cl divisor=2; run; ****************************************************************

peppapig · ‎07-14-2015

Thanks so much! I really appreciate your great help!

peppapig · ‎07-14-2015

Can you recommend any documents (paper, book chapter...) about how to calculate the coefficients in this estimate statement for the trend test? Thank you so much!

peppapig · ‎07-14-2015

Thanks so much! For the "3 1 -1 -3", is there any formula or rule to calculate it?

peppapig · ‎07-14-2015

Thanks so much! How to understand the "3 1 -1 3" in the estimate statement?

peppapig · ‎07-13-2015

proc mixed data= dataset ; class id group; model y= group time group*time / solution; random int time/subject=id ; estimate "trend test" group*time 3 1 -1 -3/e cl divisor = 3; run; Question: variable group = 1,2,3,4, time is continuous time variable in years. 1. how to do the trend test in proc mixed for "group"? 2. how to calculate the contrast coefficients and value of divisor for this trend analysis? Thank you .

peppapig · ‎05-14-2015

How to do plot of Hazard Ratio vs Covariate X like below plot with 95% band, and reference line? I am using proc phreg for the cox regression model using X as predictor variable, with all the other covariates adjustment x1, x2, x3... thank you.

peppapig · ‎07-07-2014

In proc glm, how to control all the class variables descending at the same time? x1, x2, x3 class variables with grouping values as 1,2,3 , using the code below, I only had x1 in descending, not x2. x3 in the output . PROC SORT DATA = abc; BY DESCENDING x1 DESCENDING x2 DESCENDING x3; RUN; PROC GLM DATA = abc ORDER = DATA ; CLASS x1 x2 x3 ; MODEL y = x1 x2 x3 /solution ss3 ; RUN;

peppapig · ‎02-10-2014

PROC GENMOD DATA = TEMP; CLASS ID ; MODEL Y (EVENT = '1') = age /dist=bin link = ? logit; REPEATED SUBJECT = ID /TYPE = exch; ESTIMATE 'age' age 30.5 / exp; RUN; This code does have output of exp(age), L'beta estimate. But I do not know what value to use for age in the ESTIMATE statement, mean age?? Thank you!!!

peppapig · ‎02-08-2014

Thanks so much. It's working for the categorical variable gender! When it comes to continuous variable, how to fit it to the estimate statement? Thank you for your great help!

peppapig · ‎02-07-2014

/*for continuous independent variable age*/ PROC GENMOD DATA = TEMP; CLASS ID age ; MODEL Y (EVENT = '1') = age /dist=bin link = logit; REPEATED SUBJECT = ID /TYPE = exch; RUN; /*for categorical independent variable gender*/ PROC GENMOD DATA = TEMP; CLASS ID gender ; MODEL Y (EVENT = '1') = gender /dist=bin link = logit; REPEATED SUBJECT = ID /TYPE = exch; RUN; Y is binary, 0 or 1. Thank you!!!

peppapig · ‎01-08-2014

Jag's code is working for me. Thanks!

Online Status	Offline
Date Last Visited	‎07-14-2016 05:14 PM

proc phreg floating point overflow

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Trend Analysis in proc mixed

Hazard ratio plot

Re: reading multiple records per obs from a csv file

proc phreg floating point overflow

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Re: Trend Analysis in proc mixed

Trend Analysis in proc mixed

Hazard ratio plot

proc glm class variables descending

How to output odds ratios for continuous variable in Proc Genmod

Re: How to output odds ratios in Proc Genmod?

How to output odds ratios in Proc Genmod?

Re: keep selected records and count