Instead of using the PROC IML to conduct the Iterative Proportional Fitting, any other methods / procedures that can be dealt with.
Wouldn't Fisher's Exact Test do what you need in PROC FREQ? At least as far as generating a probability statement about the "extremeness" of the observed proportions? Calculating the expected proportions would be more difficult, and if that is what you need, then you will probably need to explore PROC CATMOD.
Steve Denham
My situation is that the value in each cell is known, for instance, at the very beginning I got the following table:
var1 | var2 | |||
A1 | B2 | G5 | Total | |
T1 | 10 | 30 | 7 | 47 |
S2 | 2 | 5 | - | 7 |
S4 | - | 72 | 9 | 81 |
U8 | 8 | - | 17 | 25 |
Total | 20 | 107 | 33 | 160 |
and suppose the control total of var1 and var2 are:
var1 | |
T1 | 53 |
S2 | 19 |
S4 | 102 |
U8 | 50 |
Total | 224 |
var2 | |||
A1 | B2 | G5 | Total |
70 | 57 | 97 | 224 |
The target is to adjust the value of each cell of the var1 x var2 with the control total.
Don't miss out on SAS Innovate - Register now for the FREE Livestream!
Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.