BookmarkSubscribeRSS Feed
mmyrto
Quartz | Level 8

I want to calculate sample size per group to test proportions if i think and response rate is 1% and i want to detect a difference of 0.5% with power 90%.

I run this:

 

proc power;
twosamplefreq test=pchi
groupproportions=(0.015, 0.01)
npergroup=.
power=.9;
run;

 

Is that  correct for what i want to do? I get ~10,400 per group

 

I tried doing this for response rate 3% and detect a difference of 0.5% with 90% power. Logically i thought the Nper group would be smaller since the response rate is higher but its more. Which makes me think that i am doing something wrong.

 

Thanks

3 REPLIES 3
ballardw
Super User

Did perhaps want the NULLPDIFF option to dest the proportion difference? Set to 0.05 the sample size drops to 86.

mmyrto
Quartz | Level 8

well i guess then i dont understand what the GROUPPROPORTIONS option means? 

 

mmyrto
Quartz | Level 8

and to be honest with 1% response rate sample size of 86 does not feel reasonable...

hackathon24-white-horiz.png

2025 SAS Hackathon: There is still time!

Good news: We've extended SAS Hackathon registration until Sept. 12, so you still have time to be part of our biggest event yet – our five-year anniversary!

Register Now

How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 3 replies
  • 1741 views
  • 0 likes
  • 2 in conversation