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: How Do I limit the observations used in a regression?
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: How Do I limit the observations used in a regression?
Date
Sun, 15 Sep 2013 10:14:08 +0100
Short answer is to use -if-.
A longer answer is to wonder why you want to ignore some of your data.
On 14 Sep 2013, at 12:17, Felix Idelberger <[email protected]
> wrote:
Dear Folks,
It's my first time that I pose a question to this mailing list.
First I
would like to express my gratitude towards all that are helpful to
others including me.
I have about 1775 observations of which 1400 show very high values
of my
dependent variable. That's why I want to limit the number of
observations with high values of my dependent variable which will be
used in my regression. Additionally, I have 6 independent
dummy-variables which should be all equally represented in the
reduction
of these observations to let's say 240. These 1400 observations all
have
a value between 90-100.
Does someone know a good way to do this? I would like to tell Stata
that
it should only use every fifth observation that matches my criterion
and
that it observes an equal amount of observations that fulfill one of
my
dummy-variables.
Thank you in advance.
Yours sincerely,
Felix Idelberger
*
* 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/
*
* 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/