Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

st: panel data with irregular intervals


From   Klaus Pforr <kpforr@googlemail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: panel data with irregular intervals
Date   Tue, 10 Jul 2012 14:41:24 +0200

<>

dear problem-haver,

for this serious case of meta-humor I brought myself to comment on this post.

This is a hard question to answer generally. You could use a panel
data model, where your "time points" are the problems within each
problem solver with fixed or random problem-solver effects. The
command for this could be <xtreg score time_taken indep_vars, fe>
(with <xtset solver> before). Your data would be in sofar unbalanced
as you would have different number of problems for each solver.


Note, that having a variable that measures time does not automatically
imply, that you have a panel model over this time variable. And vice
versa, a panel data model does not need a time variable but firstly a
clustered data structure. Therefore, having time as an independent
variable, which obviously varies across problems and solvers, does not
mean, that you have an unbalanced panel data set. It is unbalanced,
because you have 4 problems for solver B and 3 problems for solver A
and C.

best

Klaus Pforr

__________________________________

Klaus Pforr
GESIS -- Leibniz Institut für Sozialwissenschaft
B2,1
Postfach 122155
D - 68072 Mannheim
Tel: +49 621 1246 298
Fax: +49 621 1246 100
E-Mail: klaus.pforr@gesis.org
__________________________________

-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von MunHeejin
Gesendet: Dienstag, 10. Juli 2012 08:43
An: statalist@hsphsun2.harvard.edu
Betreff: st: panel data with irregular intervals

Good day, statalisters.

I have data of problem-solving contests.
During a contest, solvers 'irregularly' submit solutions, and then
receive scores of the solutions.
The data set of a contest is as follows:
Solver Time Score Time_Taken Independent_Var1 Independent_Var2  A
1     20      1              0.5              0.7  A     4     30
3              0.7              0.8  A     5     50      1
 0.2              0.1  B     3     10      3              0.5
    0.2  B     7     15      4              0.7              0.6  B
 8     20      1              0.2              0.4  B    10     25
 2              0.1              0.5  C     1     20      1
  0.8              0.9  C     4     30      3              0.5
     0.2

In my opinion, general regression techniques may be not able to
estimate the effects of independent variables on Score and Time_Taken
due to extremely unbalanced data set.
How can I estimate the effects of independent variables on Score and Time_Taken?

Many thanks.
*
*   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/

*
*   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   |   Site index