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]

Re: st: RE: xtset issues


From   Ada Ma <[email protected]>
To   [email protected]
Subject   Re: st: RE: xtset issues
Date   Tue, 27 Jul 2010 05:27:46 +0100

Thanks for the suggestion but the link doesn't resolve my problem as
the additional observations weren't duplicates but valid observations
due to people having multiple (several part time) jobs.

I found an old remedy by taking personal average for both explanatory
and dependent variables, then calculate the difference between
observed values and average values and use these calculated values in
estimation instead.  It worked a treat although with the weights it
was a bit tedious to do.

Many thanks to all who read and esp those who responded to my email!!

Regards,
Ada



On Mon, Jul 26, 2010 at 2:36 PM, Martin Weiss <[email protected]> wrote:
>
> <>
>
> Try the FAQ at http://www.stata.com/support/faqs/data/repeatedtime.html
>
>
>
> HTH
> Martin
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Ada Ma
> Sent: Montag, 26. Juli 2010 12:45
> To: [email protected]
> Subject: st: xtset issues
>
> Hi Statalist,
>
> I am trying to estimate a fixed effects regression with many
> individuals.  It is a wage regression, using annual data.  The problem
> is that some people have multiple jobs.  This means that some
> individuals have several observations within each time period, so if I
> use:
>
> xtset piden year, y
>
> Stata will issue an error message saying that there are multiple
> observations within each time period.
>
> I can't estimate this model using anything else as I have too many
> individuals - I have over 155,000 individuals in my model - if I use
> -areg- or -xi- I will get the "matsize too small" error message.
>
> I can't use the user written command -felsdvreg-  either as the model
> comes with importance weights that I must use.
>
> If you have any suggestions on what I may do, please fire away!
>
> Many thanks in advance.
>
> Regards,
> Ada Ma
> *
> *   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/
>



-- 
Ada Ma
Research Fellow
Health Economics Research Unit
University of Aberdeen, UK.
http://www.abdn.ac.uk/heru/
Tel: +44 (0) 1224 555189
Fax: +44 (0) 1224 550926

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