Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Ferdinand Eibl <ferdinand.eibl@politics.ox.ac.uk> |
| To | "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu> |
| Subject | st: fixed effects with time-invariant variable and interaction term |
| Date | Tue, 30 Oct 2012 08:42:40 +0000 |
Dear Statalist, We have estimated a Lagged Dependent Variable (LDV) model with fixed effects for authoritarian regimes (with the following equation: Yit=β0 + β1Yit-1+ β2Growth+ β3Regime Type*Growth+ β4Xit+Ni+ εit). The model tries to estimate the effect of growth on social spending p.c. in different autocratic regimes. In the estimation, we used interaction terms between regime types and economic growth and omitted the different regime types from the equation as they are perfectly collinear with the regime fixed effects. As we now want to interpret our results, we were wondering how to calculate the marginal effects. More generally, we were also unsure whether, from our results table below , we could conclude that there is a significant difference between different regime types. Please note that party regime is the reference category. Any kind of recommendations and hints would be highly appreciated. Kind regards, Ferdinand STATA COMMAND xi: xtpcse welfare_pc lagwelfare_pc monarchy_growth personal_growth military_growth ln_cgdp GDPgrowthpc openc debtservice direct_tax_gdp ln_aid_pc ln_rents_pc urbanpop dependency polity deficit_gdp imf defence_pc gwf_duration i.regime, pairwise correlation(psar1) RESULTS ------------------------------------------------------------------------------ | Panel-corrected welfare_pc | Coef. Std. Err. z P>|z| [90% Conf. Interval] -------------+---------------------------------------------------------------- lagwelf~e_pc | .5927318 .1177409 5.03 0.000 .3990653 .7863982 monarchy_growthh | -196.9249 70.88603 -2.78 0.005 -313.5221 -80.32778 personal_growthh | -112.8295 58.188 -1.94 0.052 -208.5402 -17.11872 military_growth | -175.469 69.33548 -2.53 0.011 -289.5157 -61.42223 ln_cgdp | 33.54026 30.56969 1.10 0.273 -16.74241 83.82293 growth | 173.2595 65.48369 2.65 0.008 65.54841 280.9706 openc | .6272041 .1929411 3.25 0.001 .3098441 .944564 debtservice | .2663759 .6796557 0.39 0.695 -.8515582 1.38431 direct_tax~p | -5.630332 262.5316 -0.02 0.983 -437.4564 426.1958 ln_aid_pc | 3.78063 4.304718 0.88 0.380 -3.3 10.86126 ln_rents_pc | -2.575868 1.401622 -1.84 0.066 -4.881331 -.2704041 urbanpop | 3.645545 3.535471 1.03 0.302 -2.169788 9.460878 dependency | -8.524525 2.860049 -2.98 0.003 -13.22889 -3.820163 polity | -1.634748 .9341539 -1.75 0.080 -3.171294 -.0982013 deficit_gdp | -32.23502 57.8288 -0.56 0.577 -127.3549 62.88489 imf | -4.356364 3.477033 -1.25 0.210 -10.07557 1.362846 defence_pc | .8791647 .1779755 4.94 0.000 .586421 1.171908 gwf_duration | -1.545701 1.846139 -0.84 0.402 -4.58233 1.490927 * * 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/