Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Joseph Padgett <josephpadgett@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | st: gllamm missing cut points |
| Date | Fri, 8 Jun 2012 09:44:28 -0400 |
I am utilizing the gllamm command to calculate ordered logistic regression predicting satisfaction. My models are split by gender. When I run the male model gllamm returns the appropriate number of cut points (three), but when I run the female model I only get back too few cut points (two). There are responses for every category of my dependent variable (enjoy) in the female group. I'm stumped on this. If it's an error, how do I fix it? If it is not an error, how do I interpret it? ---------- gllamm enjoy, x1 x2 x3 x4 ... x30, family(binomial) link(ologit) i(respondent school) nip(20) ---------- for males I get - coeff coeff coeff ==== cut1 cut2 cut3 --------- but for females I get coeff coeff coeff ==== cut1 cut2 ---------- Everything else in the female model is there and all seems to make sense, just short one cut point... ??? * * 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/