When running GENMOD with the SLICE statement I get the following error. I'm not sure why SAS is trying to make any connections. I'm wondering if the results are correct.
NOTE: Copyright (c) 2002-2010 by SAS Institute Inc., Cary, NC, USA.
NOTE: SAS (r) Proprietary Software 9.3 (TS1M0)
NOTE: This session is executing on the X64_ES08R2 platform.
2349 PROC GENMOD DATA=formodel;
2350 CLASS id ethnicity trt /PARAM=GLM;
2351 MODEL f3q7a = ethnicity trt ethnicity*trt / TYPE3 DIST=NB OFFSET=lntslv;
2352 REPEATED SUBJECT = id / TYPE=CS;
2353 *LSMEANS ethnicity /at trt=0;
2354 *LSMEANS ethnicity /at trt=1;
2355 SLICE ethnicity*trt /adjust=simulate(acc=.0002 seed=121211 report) diff
2355! EXP SLICEBY=trt;
2356 RUN;
NOTE: Class levels for some variables were not printed due to excessive size.
NOTE: Algorithm converged.
NOTE: Algorithm converged.
NOTE: Random number seed for this analysis set to 121211.
ERROR: The connect call failed. The system error is 'The connection has timed
out.'.
ERROR: Could not create connected socket pair. Failed call to connect with rc
10060.
NOTE: The most likely cause of the previous error is software firewall settings
that are too restrictive.
ERROR: Unable to load extension: (tkitcp)
ERROR: The connect call failed. The system error is 'The connection has timed
out.'.
ERROR: Could not create connected socket pair. Failed call to connect with rc
10060.
NOTE: The most likely cause of the previous error is software firewall settings
that are too restrictive.
ERROR: Unable to load extension: (tkitcp)
NOTE: PROCEDURE GENMOD used (Total process time):
real time 58.48 seconds
user cpu time 14.27 seconds
system cpu time 0.23 seconds
memory 17678.35k
OS Memory 30592.00k
Timestamp 01/30/2014 07:53:59 AM
That is a SAS vs OS problem, not a GENMOD problem. My best advice is to open a ticket with Tech Support. At the bottom of the page, in teeny-tiny print is a link to contact them.
Steve Denham
But why is it opening a connection? Perhaps SLICE is not fully implemented in my version and SAS is trying to update.
I don't know your set-up. With interactive PC or batch PC mode, I have never seen this before. Are you running EG on a server, and getting slammed by a firewall? What version of SAS do you have installed? This is the kind of thing that Tech Support, who have seen almost everything, is going to be much better at than us statisticians who hang out here all the time.
Steve Denham
I'm running PC SAS interactive on a server via remote desktop, so the firewall shouldn't be an issue. The version is 9.3 (TS1M0). All I care about is if the results in the output are reliable. Thanks for your help. I did submit a tech support form. Thanks for your help.
For that version and install, SLICE is fully functional. It's a connection problem of some sort.
Steve Denham
Available on demand!
Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.
ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.
Find more tutorials on the SAS Users YouTube channel.