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
- /
- SAS Programming
- /
- General Programming
- /
- How to get the median difference and 95% credible ...

Topic Options

- 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
- RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

10-03-2013 10:30 AM

Hi,

I have a continuous measurement for two treatment groups and standard deviation is quite large compared to the mean difference due to small sample size in these subgroups. How can I get median difference and 95% credible interval using non-parametric method?

Thanks,

Shellee

Accepted Solutions

Solution

10-03-2013
11:30 AM

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

Posted in reply to Shellee

10-03-2013 11:30 AM

confidence interval of Hodges-Lehmann's median ??

All Replies

Solution

10-03-2013
11:30 AM

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

Posted in reply to Shellee

10-03-2013 11:30 AM

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

Posted in reply to damdisasterman

10-03-2013 03:06 PM

Thank you so much, damdisasterman.

My SAS version is 9.1, so I use the macro for the median and credible interval from the paper you refer to me.

Thanks,

Shellee

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

Posted in reply to Shellee

10-03-2013 02:43 PM

SAS calls this estimate of location shift.

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

Posted in reply to data_null__

10-03-2013 03:07 PM

Thank you very much for response to my question.

Thanks,

Shellee

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

Posted in reply to Shellee

10-04-2013 03:06 AM

Hi Shellee,

the following code might be useful:

proc nparway data = filename wilcoxon;

class group;

var PD;

output out=wilcoxon_test;

run;

You must stack the two treatment variables and classify with the variable group which has two values. You can also do the test via enterprise guide.

Sven

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

Posted in reply to Hypoman

10-04-2013 09:00 AM

Thank you so much for your response to my question, Sven.

Thanks,

Shellee