Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Prakash Singh <prakashbhu@gmail.com> |
To | statalist <statalist@hsphsun2.harvard.edu> |
Subject | st: calculation of firm selection probability weight |
Date | Mon, 17 Sep 2012 23:08:55 +0530 |
Dear all Please pardon me as I feel I am asking very basic question.I have two questions to ask. First, I am working with cross country firm level survey data. in the survey data number of firm are varying country to country, industry to industry, to reduce the effect of uneven number of firms in the pooled regression data I would like to run the regression with weight, equal to the the inverse of the probability of being included in a specfic country sample. My question is how to calculate this probability of firm selection. My second question is in the context of same cross country firm level survey data I want to generate variable X using Y such that Y is divided by sum of Y at country level as well as industry level. something like gen X=Y/sum(Y) by (country industry) Thanks in advance Prakash * * 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/