Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Robustness test

    Hi
    I am using panel data for 130 developing countries for 18 years. I used fixed effect model with clustering at country level to see the impact of parental leave policy on Gender employment gap.Now I want to do some robustness checks but do not have idea how to do that as this is my first paper.
    Can any one suggest me including coding?
    Best
    Nuzaba
    Last edited by Nuzaba Tahreen; 10 May 2017, 15:21.

  • #2
    Nuzaba:
    the usual question is: robust with respect to what?
    Assuming you're using -xtreg, fe. you have already accounted for heteroskedasticity and/or autocorrelation via clustered standard errors.
    Kind regards,
    Carlo
    (StataNow 18.5)

    Comment


    • #3
      Hi Carlo
      The requirement of my thesis is to see some robustness checks. As I already accounted for those two disturbances now I am confused what should I test more..if I need to see some specification test then how should I do so?
      Or is there something else I should be careful about my results regarding my identification strategy?
      Sorry if I am making you confused even I am too.

      Best
      Nuzaba
      ​​​​​

      Comment


      • #4
        Nuzaba:
        I cannot be more helpful.
        I assumed that you have already ruled out issues such as endogeneity (and, especially, reversal causation).
        You should have already investigated, via -hausman- test, whether -fe- or -re- specification are good for your data.
        Perhaps you can present both the regression models with and without clustered standard errors.
        Kind regards,
        Carlo
        (StataNow 18.5)

        Comment


        • #5
          Thanks Carlo
          What ever you suggested is helpful now. But I haven't done endogeneity test or reversal causality test for my model. Can you suggest me the command for that? Here I am confused about setting my instrument.
          Best
          Nuzaba

          Comment


          • #6
            Nuzaba:
            see http://www.statalist.org/forums/foru...est-panel-data.
            For reversal causation and endogeneity at large, please consult any decent econometrics textbook.
            Kind regards,
            Carlo
            (StataNow 18.5)

            Comment


            • #7
              Originally posted by Carlo Lazzaro View Post
              Nuzaba:
              see http://www.statalist.org/forums/foru...est-panel-data.
              For reversal causation and endogeneity at large, please consult any decent econometrics textbook.
              Dear Carlo,

              I am conducting my research about CHINESE FDI IN AFRICA, my main purpose of the study is: Does Chinese FDI bring some technological spillover into African countries? thus my data consist of N=32 African countries in a period of time t=14 years. My 1st dependant variable is y1=TFP (Total Factor Productivity) change of each country, and the main independent variables are x1= Chinese FDI stock, x2= technological difference, x3=human capital, and some control variable as x4=resource rent by an African country, x5=industries output / GDP, x6= economic openness.

              after running:

              Code:
              Code:
               
                xtreg y1 x1 x2 x3 x4 x5 x6 i.year i.COUNTRY, fe
              (NB: for x1 x3 and x4, I lagged them for 1 year in this regression in order to attend my expected P value, at the same time the lagged 1 year value makes more sens in economic point of view for these three variable)

              So my question is, which kind of code should Iuse to check if any of my independant variable is or are exogenous?

              Comment


              • #8
                Rakotondrazaka:
                see Jeff Wooldridge 's lecture : https://ifs.org.uk/docs/wooldridge%20session%204.pdf
                Kind regards,
                Carlo
                (StataNow 18.5)

                Comment

                Working...
                X