Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | sazas <s_azagba@live.concordia.ca> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Re: Nonlinear Panel Data |
Date | Thu, 28 Oct 2010 15:42:48 -0700 (PDT) |
jacobb wrote: > > > Without more specific information about your model it is difficult to > offer concrete advice. From what I can gather you are trying to see the > effect of the policy change on the behavior/actions of some entity (lets > say they are schools). So you have dummy variables for change in behavior > (0,1) and dummy variables for pre- and post-policy change. If no other > variables vary over time in your model then a fixed effects model won't be > appropriate. > > It might help if you can provide a little bit more information about your > model. > The dependent variable is binary indicator 0 or 1 to capture behavior and l have data available for the five waves. The list of my independent variables (regressors) include a dummy (policy effect) that takes the value of one post policy period Yit = dit(policy effect) + Zit + residual t = 1,.. 5 waves or time periods, i= cross sectional unit in this case individuals Yit is a binary indicator that represents behavior, for example do u own a car? yes =1 or 0 otherwise, do you drink alcohol? yes =1 and 0 otherwise dit is a dummy that captures the policy effect, it takes the value of zero pre policy & 1 post policy. Zit is other explanatory variables -- View this message in context: http://statalist.1588530.n2.nabble.com/Nonlinear-Panel-Data-tp5684286p5684618.html Sent from the Statalist mailing list archive at Nabble.com. * * 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/