Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | William Buchanan <william@williambuchanan.net> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: runmlwin error: duplicate fixed part |
Date | Thu, 30 Aug 2012 05:20:37 -0700 |
The ## is telling Stata to create the interaction and include the individual variables. If you only want to create the interaction, you should include the variables inidigiduakly and then use # to generate the interaction only. HTH, Billy Sent from my iPhone On Aug 30, 2012, at 5:13, Susie Schaffnit <susie.schaffnit@gmail.com> wrote: > I am using the runmlwin command for a discrete-time event history analysis. My model includes several interaction terms. A few variables show up in more than one interaction. > > When I run the model I receive this error regarding my variable called SES: > "SES SES are duplicated in the fixed part" > > Oddly, SES is only one of multiple variables that is used in more than one interaction, so I am not sure why this variable is being singled out. > > Here is an example of the command I am using: > > runmlwin birthfiveyr2 cons i.yrsince##c.cohort c.prevchildren i.motherdead i.fatherdead /// > c.SES##i.liveswparents c.SES##i.partstat c.PartIn##i.yrsince i.actstat1 /// > i.aeduc1 i.yrsince##c.SES i.yrsince##i.actstat1, /// > level2 (acountry: cons) /// > level1 (yrsince:) /// > discrete (dist(binomial) link(logit) denom(cons)) /// > nogroup nopause > > > Does anyone have any idea why I am getting this error? If I run this as a simple regression it works just fine... > > Thank you! > > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/