Hi,
I am using proc freq to show the Somers' D and was wondering if anyone could help me with the two questions below please?
Question 1:
For C|R, would it be correct to use the code below? The row variable X is regarded as the independent variable and the column variable Y is regarded as dependent.
proc freq data=want;
tables [dependent variable i.e. Y] * [independent variable i.e. X] / measures;
run;
Question 2:
When I run the code, I get this result - can someone help me interpret it, and whether I should be reading the "Value" or "ASE"?
Hi,
I found some links about the PROC FREQ and its measures option:
http://v8doc.sas.com/sashtml//proc/zlesstmt.htm
http://v8doc.sas.com/sashtml//proc/zeq-comp.htm#z0087584
https://v8doc.sas.com/sashtml/stat/chap28/sect20.htm
https://support.sas.com/documentation/onlinedoc/stat/151/freq.pdf#page=107
https://www.statisticshowto.com/somers-d
after reading I would say:
1. yes
2. The values tends toward 0 so the model is a poor predictor . The Asymptotic Standard Error of 0.0271 means that the sample behaves as 97.29% as the overall population which means this statement is highly significant.
- Cheers -
It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.