turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- Analytics
- /
- Stat Procs
- /
- Confidence interval for ratio of means, parallel d...

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-11-2010 03:11 PM

I am looking for a way to use Proc GLM to calculate the confidence interval for the ratio of means with treatment and center as factors for testing bioequivalence. I found the following reference:

http://www.lexjansen.com/pharmasug/2008/sp/sp04.pdf

but this calls for a crossover design. For the type of products we test here, we run a parallel design with clinical endpoints.

Any suggestions?

http://www.lexjansen.com/pharmasug/2008/sp/sp04.pdf

but this calls for a crossover design. For the type of products we test here, we run a parallel design with clinical endpoints.

Any suggestions?

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-12-2010 07:12 AM

What about taking the log of the response variable? The difference between the treatment means is the log of the ratio, and confidence bounds around the ratio can be calculated from the confidence interval on the difference by exponentiating the results.

Steve Denham

Steve Denham

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-13-2010 03:36 PM

The response variable is % change from baseline and can be negative and positive. Of course we can't take the log of a negative number.

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-14-2010 07:17 AM

OK. Percent change from baseline is the same as an analysis of covariance, with the regression coefficient for the pretreatment value fixed at negative one (that's pretty loose, but it's a fair analogy). How about a log transform of all values before calculating the change from baseline? Then you are looking at the ratio change from baseline. Or, you could use the log of the pretreatment value as a covariate, and look at the difference in group least squares means, giving the ratio after adjusting all subjects to an equivalent pretreatment value.

Would that approach be workable?

Steve Denham

Would that approach be workable?

Steve Denham

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-14-2010 09:54 AM

Good suggestions, thanks!

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-14-2010 11:47 AM

Now what to do when the response is equal to 0? I considered adding a constant to the response variable, but then the results are dependent on the constant I choose. The baseline response is always > 0, but the post-baseline response can be equal to 0.

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-15-2010 07:26 AM

Zeros. My first reaction is to start swearing, but since that doesn't solve the problem, I went googling for nonparametric methods. The EU recommends a nonparametric approach in many cases. There were also some bootstrapping methods returned in the search. I have to admit that I am out of my comfort realm with these; I just know that they have been used.

Good luck,

Steve Denham

Good luck,

Steve Denham

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

10-15-2010 07:49 AM

I just looked up the EMEA guidance, and it now specifies that non-parametric analyses should NOT be used, so my previous posting should be crumpled and tossed in the nearest waste receptacle. It seems I was ten years out of date, and I apologize.

That leaves bootstrapping and Bayesian methods, so far as I can determine.

I really do hope you have some luck.

Steve Denham

That leaves bootstrapping and Bayesian methods, so far as I can determine.

I really do hope you have some luck.

Steve Denham