Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: synthetic panel


From   Ackah Charles <akaobo@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: synthetic panel
Date   Mon, 27 Mar 2006 03:27:33 -0800 (PST)

Hi,

Does anybody know how to form synthetic panels from
repeated cross-sections? It appears I have
successfully constructed the 'pseudo panel' but there
are a few things I don't understand about the cohort
means for example pstatus and loc2. pstatus is meant
to be a categorical variable 0, 1 and 2.  Now if you
take cohort means of pstatus you get something like
this
+---------------------------------------+
     | cohortid   yr        loc2     pstatus |
     |---------------------------------------|
  1. |        1    1   1.6363636   1.4545455 |
  2. |        1    2   1.9230769   1.6923077 |
  3. |        2    1   1.9090909   1.4090909 |
  4. |        2    2         1.7         1.7 |
  5. |        3    1   1.7179487   .94871795 |
     |---------------------------------------|
  6. |        3    2   1.6363636   1.6818181 |
  7. |        4    1   1.7692307   1.1538461 |
  8. |        4    2   1.9285715   1.3571428 |
  9. |        5    1   1.8235294   1.0784314 |
 10. |        5    2   1.7945205   1.6027397 |

 
How do I explain the fact that the pstatus of cohort 3
in yr 1 was 0.95 and all the rest which fall between
pstatus 1 and 2 ( eg. 1.45). The same is for loc2
which is supposed to be 1 for urban and 2 for rural.
Now I get something like 1.63 for cohort 1 in yr 1.

Any help will be much appreciated. 

Charles Ackah
Research Student 
University of Nottingham
UK

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com 
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2020 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index