Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Galin Gichev <galin@mastersofalfra.com> |
| To | statalist <statalist@hsphsun2.harvard.edu> |
| Subject | st: Interpretation of oprobit coefficients |
| Date | Thu, 12 Apr 2012 18:04:05 +0200 |
Hello! I am running ordered probit regression and I need some help with the interpretation of the coefficients. The dependent variable has 4 categories. A few of the independent var-s are level. One is ln(GDP per capita). I also have 3 categorical independent variables, converted to dummies. So my question is, how to interpret the effect on ln(GDP per capita) on y*. And how to do the same for the dummies? Here is the part of the raw and standardized coefficients that bothers me: Y* | b z P>|z| bStdX bStdY bStdXY SDofX -------------+---------------------------------------------------------------- logGDPcapita | -65.14180 -3.618 0.000 -5.3093 -59.5872 -4.8566 0.0815 CPInfl | 0.95830 3.627 0.000 0.9699 0.8766 0.8872 1.0121 SingleLivi~r | 0.12992 2.550 0.011 0.0335 0.1188 0.0306 0.2576 DivorcedSe~d | -0.19190 -3.229 0.001 -0.0456 -0.1755 -0.0417 0.2375 Widowed | -0.12437 -2.336 0.019 -0.0423 -0.1138 -0.0387 0.3401 * * 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/