Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: panel data analysis advice


From   Robert Paul <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: panel data analysis advice
Date   Mon, 10 Mar 2014 14:09:49 -0700 (PDT)

Dear Statalist,


I have demographic and treatment information for patients chronic disease (N=60,000). I got permission to link a subset of my data to income data (18.5%). For this subset I have 20 years panel data.
The data in long format looks 
Id     year  income age …
1      1990  100   45
1      1991  110   45
1      1992   125   45
1      1993  132   45
.
.
.
 
My aim is 
a-  to estimate the effect of demographic, treatment, and being chronic disease patient, on patient’s income; and
b-  to evaluate differences in income between patients and the general population (when linked to control population)
 
to address these issues I plan  
 
a-  to run a Fixed and Random effects model , to start with  then run  Hausman test …
 
b-  I will also get a control group for my data - (from general population without chronic disease -matched by demographic vars)  --- for this I plan to use Hausman-Taylor that utilizes the vars as instruments and provide  parameter estimate for time-invariant variable (major variable of interest – chronic disease patient or not)
 

 
Dependent variable – log equivalized income
RHS vars – age at end of follow-up,  age^2, age at diagnosis,  treatment type
    1. Run  xtreg logincome age age_square age at diagnosis treatment type dummies . .  , fe
    2. xtreg logincome age age_square age at diagnosis treatment type dummies . . . .  , re
    3. xtreg logincome age age_square age at diagnosis treatment type dummies . . . , re vce(robust)  or
    4. xtreg logincome age age_square age at diagnosis treatment type dummies . . . , re vce(cluster id)
 
The aim of using vce or cluster is to produce consistent VCE estimator when the disturbances are not identically distributed over the panels. 
 
 
5.  ** Hausman Taylor estimation
  
. xthtaylor  logincome age age_square age at diagnosis treatment_type dummies, endog(age treatment type dummies)
 
My question, as I am new to panel data analysis, is if I am doing the right way to address my question.
1.  Do I need to calculate weights because I am using a subset of the population? If yes, how do I do that?
2.  I am not sure – probably using dynamic models would be more appropriate 
3.  I need advice on my analysis procedure. This is of critical importance for my project.  I appreciate your valuable comments.
Thanks

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index