- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content
Posted 03-13-2020 12:28 PM
(1269 views)
Using SAS 9.4
I am running the following code:
proc univariate data= have normal plots;
class graft;
var age_sx bmi_sx ;
run;
proc npar1way data= have wilcoxon;
class graft;
var age_sx ;
OUTPUT OUT= KW_PVALS (KEEP=_VAR_ P_KW);
RUN;
PROC PRINT DATA = KW_PVALS;
run;
ai would like to present the 95% CI along with the p-value. Is there a good method for producing that from the code I already have? Thank you
4 REPLIES 4
- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content
Did you check the options on the OUTPUT statement? That' would be the start, especially since you're only keeping a single value you're dropping the rest which likely has what you want.
- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content
Confidence interval of what? In which data set?
- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content
I need to confidence interval of the median as my data is not normally distributed. CIbasic in the proc univariate would work except that statements assumes the normality of the data
- Mark as New
- Bookmark
- Subscribe
- Mute
- RSS Feed
- Permalink
- Report Inappropriate Content
You don't usually calculate parametric statistics on a non-parametric measure such as the median. Usually with the median you report the quartiles as well, Q25 and Q75.