Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Bloomberg Jenny <jennybloomberg2@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Regression with categorical ordinal Y and nonlinear complex function of X's |
Date | Sun, 16 Mar 2014 23:15:39 +0000 |
Hello, I have a question about how to conduct a nonlinear regression like the following: The dependent variable is a categorical ordinal variable (like 1-5 that are ordered), while the right hand side of the regression function is given by a non-polynomial function of explanatory variables, such as of logarithm or of exponential, in addition to linear terms. In such a case, what kind of stata commands would be useful to conduct a regression analysis and test the goodness-of-fit? I think if the right hand side was given by a simple linear functions (or possibly with a simple interaction term of linear terms), I could use the standard -ologit-. Also, even with such a complex function as exp and log plus linear terms in the right hand side, I think I could use -nl- command if the dependent variable was a continuous variable. However, I have no idea what I can/should I do if these two kinds of features, categorical ordinal Y and nonlinear complex function of X's, appear at the same time. Any suggestions will be greatly appreciated! Best, Jenny * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/