Published on :
Statistical INTERNAL_CREATION

Adjustment of Raw p-values with PROC MULTTEST

This code is also available in: Deutsch Español Français
Awaiting validation
The script begins by creating a data table named 'a' containing the raw p-values. Each observation corresponds to a statistical test identified by a 'Test' variable. Then, the PROC MULTTEST procedure is called with this table as input (option `inpvalues=a`). It calculates and displays the adjusted p-values according to three different requested methods: Holm, Hochberg, and FDR. This is a typical example of managing the multiple comparisons problem in statistics.
Data Analysis

Type : INTERNAL_CREATION


The data (raw p-values) are directly integrated into the code via a DATALINES statement, creating table 'a'.

1 Code Block
DATA STEP Data
Explanation :
This DATA STEP block creates the 'a' work table. It reads the data integrated into the code via `datalines`. Each line contains a test identifier (Test) and the associated raw p-value (Raw_P).
Copied!
1title 'Inputting Raw p-Values';
2 
3DATA a;
4 INPUT Test$ Raw_P;
5 DATALINES;
6test01 0.28282 test02 0.30688 test03 0.71022
7test04 0.77175 test05 0.78180 test06 0.88581
8test07 0.54685 test08 0.84978 test09 0.24228
9test10 0.58977 test11 0.03498 test12 0.41607
10test13 0.31631 test14 0.05254 test15 0.45061
11test16 0.75758 test17 0.12496 test18 0.49485
12test19 0.21572 test20 0.50505 test21 0.94372
13test22 0.81260 test23 0.77596 test24 0.36889
14;
15 
2 Code Block
PROC MULTTEST
Explanation :
This statistical procedure takes as input table 'a' containing the p-values. It applies several correction methods for multiple tests: Holm (holm), Hochberg (hoc), and False Discovery Rate (fdr) control. The results with adjusted p-values are displayed in the standard output.
Copied!
1PROC MULTTEST inpvalues=a holm hoc fdr;
2RUN;
This material is provided "as is" by We Are Cas. There are no warranties, expressed or implied, as to merchantability or fitness for a particular purpose regarding the materials or code contained herein. We Are Cas is not responsible for errors in this material as it now exists or will exist, nor does We Are Cas provide technical support for it.
Copyright Info : SAS SAMPLE LIBRARY. REF: SAS/STAT User's Guide, PROC MULTTEST chapter