Obsidian | Level 7

## Power calculation in cohort study

Hi! I am performing a prospective cohort study in an existing cohort study. The sample of participants I can use from this existing cohort is 190. I am using a Cox model to analyze the data and to get a Hazard ratio. But now I want to know what the power of the study is. How can I calculate it? I can't find it on the internet...

So I am doing a prospective survival analysis (in an existing cohort) of 190 participants, the exposure is divided either into three categories and continuous and the outcome is yes/no.

After that, I also want to calculate the power of the study when it is stratified for some covariates.

I am using SAS, so maybe there is an option in SAS for this?

I hope some of you can help me. Thanks in advance!

1 ACCEPTED SOLUTION

Accepted Solutions
Super User

## Re: Power calculation in cohort study

I would probably simulate it then.

You would run a whole bunch of simulations and determine the cutoff points.  I actually coded this about 5 years ago for a clinical trial protocol and to determine the number of obs and when we could terminate early 🙂

I recall using a text book, I'll dig up the name and reference tonight, if someone else hasn't already answered this.

You can also look up Rick Wicklin's book on simulating data with SAS.

5 REPLIES 5
Super User

## Re: Power calculation in cohort study

PROC POWER.

It looks like survival analysis.

Here's an example to get you started.

http://documentation.sas.com/?docsetId=statug&docsetTarget=statug_power_examples06.htm&docsetVersion...

@hovliza wrote:

Hi! I am performing a prospective cohort study in an existing cohort study. The sample of participants I can use from this existing cohort is 190. I am using a Cox model to analyze the data and to get a Hazard ratio. But now I want to know what the power of the study is. How can I calculate it? I can't find it on the internet...

So I am doing a prospective survival analysis (in an existing cohort) of 190 participants, the exposure is divided either into three categories and continuous and the outcome is yes/no.

After that, I also want to calculate the power of the study when it is stratified for some covariates.

I am using SAS, so maybe there is an option in SAS for this?

I hope some of you can help me. Thanks in advance!

Obsidian | Level 7

## Re: Power calculation in cohort study

Thanks for answering. When I do this:

``````PROC POWER;
coxreg
hazardratio = 1.4
stddev = 1.2
ntotal = 190
eventprob = 0.25
power = .
;
run;``````

SAS says about the 'coxreg';  180-322: Statement is not valid or it is used out of proper order. This nearly the same as in the example, what can I do? I am using SAS 9.4.. I think that is the problem? What else can I do?

Super User

## Re: Power calculation in cohort study

What version of SAS/STAT do you have? If you're not sure, you can use the following code to check.

It's possible that it's an earlier version and you don't have this feature yet 😞

``proc product_status;run;``
Obsidian | Level 7

## Re: Power calculation in cohort study

I am using SAS 9.4 so I think it is not possible? What could I do to calculate the power of my survival analysis? Because Ive three groups and in PROC POWER; twosamplesurvival you only have two groups right?
Super User

## Re: Power calculation in cohort study

I would probably simulate it then.

You would run a whole bunch of simulations and determine the cutoff points.  I actually coded this about 5 years ago for a clinical trial protocol and to determine the number of obs and when we could terminate early 🙂

I recall using a text book, I'll dig up the name and reference tonight, if someone else hasn't already answered this.

You can also look up Rick Wicklin's book on simulating data with SAS.

Discussion stats
• 5 replies
• 3083 views
• 0 likes
• 2 in conversation