Statistical Procedures

Programming the statistical procedures from SAS
BookmarkSubscribeRSS Feed
psrajput
Obsidian | Level 7

Hi,

 

I need to calculate the Harell's Concordance Index or C-Index for a survival model. There are not many resources available online. Can someone help me with some simple code or macro?

 

I have the following variables: 5-6 predictor variables, attrition_score (or probability), actual_attrition (1 and 0).

 

From my research, I think I will only need attrition_score and actual_attrition and also that proc hpreg is used for the calculation. Not sure if I will need the duration of customer retention?

 

Thanks.

2 REPLIES 2
StatDave
SAS Super FREQ

If it is a survival model with a time-to-event response, use PROC PHREG. In the PROC PHREG statement, specify the CONCORDANCE(HARRELL) option. See the PHREG documentation for details. 

 

When you are looking for a particular statistic in SAS, check the list of Frequently Asked-for Statistics (FASTats) in the Important Links section of the Statistical Procedures Community page.

psrajput
Obsidian | Level 7

Thanks for the reply but the documentation doesn't help much.

- For example, it doesn't explain which method/variables are optional.
- There is a dataset used in the example but are these model predictors, the model score is not used?
- Can we use score deciles or scores in place of time? For Time*Status(0)

sas-innovate-white.png

Our biggest data and AI event of the year.

Don’t miss the livestream kicking off May 7. It’s free. It’s easy. And it’s the best seat in the house.

Join us virtually with our complimentary SAS Innovate Digital Pass. Watch live or on-demand in multiple languages, with translations available to help you get the most out of every session.

 

Register now!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 2 replies
  • 1735 views
  • 1 like
  • 2 in conversation