Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Fractional response data and effect sizes


From   "[ISO-8859-1] Natália Barbosa" <natbar01@gmail.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Fractional response data and effect sizes
Date   Thu, 27 Nov 2008 12:08:45 +0000

Hi all,

I am trying to estimate the impact of country-level measures of
institutional environment and country-and industry-specific
characteristics on the intensity of innovative firms of manufacturing
industries across 10 European countries. The industries/countries are
observed in 2004.

For each industry/country I have the number of innovative firms and
the total number of observed firms along with institutional measures
and country and industry control variables as explanatory variables.
Since the dependent variable is a fraction and is bound between 0 and
1 I try three alternative procedures for checking robustness of the
findings. They are:

(1) a QMLE Poisson estimator using Stata's glm command with link(log)
exp(total number of firms) and robust
(2) the WLS estimator applied to the arcsine-root transformation of
the proportion of innovative firms
(3) the fractional logit model proposed by Papke and Wooldridge (1996)
using Stata's glm command with link(logit) family (binomial) and
robust

The key explanatory variables are the six covariates measuring the
institutional environment in each country.

A referee asks me for the effect sizes. How can I measure "effect
sizes" using STATA and the above alternative procedures?

Many thanks in advance.

Natália



*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index