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
- /
- Perform Wilcoxon Rank Sum/Mann-Whitney rank test

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

04-29-2016 03:56 PM

i have to perform following calculations to determine 8th and 29th ordered pair values:

data are as follows:

Post change (T) 1.3390 1.3496 1.4946 1.4668 1.1911 1.2210

Prechange (R) 1.1331 1.1842 1.0824 1.3049 1.0410 1.2419

The first step in the computation of the confidence interval is to form the 36 (= 6 x 6) individual T/R ratios. This is illustrated in the following table, where the prechange lot slopes (R) are listed across the top of the table, the postchange lot slopes (T) are listed down the left margin of the table, and the individual T/R ratios are the entries in the body of the table:

please see attached: Table-1

The second step in the computation of the confidence interval is to order these 36 individual T/R ratios from lowest to highest: 0.9128 0.9357 0.9591 0.9832 1.0058 1.0261 1.0311 1.0343 . . . 1.2863 1.2945 24 1.2964 1.3190 1.3551 1.3808 1.4090 1.4357.

In the third step, the eighth and twenty-ninth ordered individual ratios are the lower and upper limits, respectively, of the 90% confidence interval for the ratio of the median in vitro release rate (slope) for T over the median in vitro release rate for R. In the example, this confidence interval is 1.0343 to 1.2863

I want to achieve this calculation and a report in SAS 9.4 TS level 1M2

Can some one from the community please help me. I really appreaciate your help.

Thanks in advance!

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

Posted in reply to DShah

04-29-2016 04:32 PM

Have you looked at PROC NPAR1WAY?

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

Posted in reply to DShah

04-29-2016 11:41 PM

Here is a way to get the values.

```
data comb;
do T= 1.3390, 1.3496, 1.4946, 1.4668, 1.1911, 1.2210;
do R= 1.1331, 1.1842, 1.0824, 1.3049, 1.0410, 1.2419;
ratio = T/R;
output;
end;
end;
run;
proc rank data=comb out=limits(where=(order in (8, 29)));
var ratio;
ranks order;
run;
proc print data=limits noobs; run;
```

It is not clear what you want in the report.

PG

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

Posted in reply to PGStats

05-02-2016 08:50 AM

Thank you!

This sounds the answer. Is there a way to get the values of T and R from the dataset?

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

Posted in reply to DShah

04-30-2016 12:25 AM

Sounds like you are doing some Statistical Programming. Suggest you post it at IML forum. It is better for IML programming.

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

Posted in reply to Ksharp

05-02-2016 08:53 AM - edited 05-02-2016 08:53 AM

Thank you. i will do that.