Calcite | Level 5

## How to calculate Incident rate ("event incident rate per 100 person-years") and 95%CI.

I want to calculate the Incident rate ("event incident rate per 100 person-years") and its corresponding 95% confidence intervals (CI), but I have no clue where to start to do.

2 REPLIES 2
Diamond | Level 26

## Re: How to calculate Incident rate ("event incident rate per 100 person-years") and 95%CI

Can you show us a portion of your data? The preferred method of providing data is https://blogs.sas.com/content/sastraining/2016/03/11/jedi-sas-tricks-data-to-data-step-macro/

--
Paige Miller
Super User

## Re: How to calculate Incident rate ("event incident rate per 100 person-years") and 95%CI

The last time I did this was about 15 years ago, and I did it 'by hand' in a DATA step.  So I read through the data, and counted number of incidents, and added up the number of person-years, then at the end I did some math for the confidence interval.  That's definitely an option.  If your data are well structured, it's pretty straight forward.

I would start by heading to lexjansen.com and searching the papers indexed there for "incidence".

I found a few with macros, but also saw that SAS/STAT 12.1 introduced PROC STDRATE, which looks like it will do it:

https://lexjansen.com/nesug/nesug12/sa/sa19.pdf

https://support.sas.com/resources/papers/proceedings13/423-2013.pdf

The Boston Area SAS Users Group is hosting free webinars!
Next up: Bart Jablonski and I present 53 (+3) ways to do a table lookup on Wednesday Sep 18.
Register now at https://www.basug.org/events.
Discussion stats
• 2 replies
• 1991 views
• 1 like
• 3 in conversation