I haven't used NLEstimate before, so I'm not entirely sure how to approach fixing this.
Errors:
WARNING: Apparent invocation of macro NLESTIMATE not resolved.
387 %NLEstimate(instore=house, label=RR (female/male), f=logistic(b_p1+b_p2)/logistic(b_p1))
-
180ERROR 180-322: Statement is not valid or it is used out of proper order.
My code:
proc SurveyLOGISTIC data=ep2015;
freq house_prep;
Cluster _PSU;
Stratum _STSTR;
Weight _llcpwt;
Class house_prep sex age_cat race edu income marry employ cvd asth diabete cvd physical mental / param=glm;
model house_prep(event="No")= sex age_cat race edu income marry employ cvd asth diabete cvd physical mental;
lsmeans sex / e ilink;
store out=house;
run;
%NLEstimate(instore=house, label=RR (female/male), f=logistic(b_p1+b_p2)/logistic(b_p1))
Hello @SAS93,
In Sample 58775: Estimating nonlinear combinations of model parameters it says: "NOTE: Beginning in SAS® 9.4 TS1M6, this macro is available in the SAS/STAT® Autocall library as the NLEST macro and does not need to be downloaded and defined before use."
So, if your SAS version is 9.4M6 or later (submit proc setinit; run; to find out), the name of the macro is NLEST, not NLESTIMATE. Otherwise, you need to download and submit the code of macro NLESTIMATE first before you can use it. The download link can be found in the "Downloads" tab of the web page linked above.
Available on demand!
Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.
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.