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: Generating (simple) spatial variables (excluding the country of observation)


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Generating (simple) spatial variables (excluding the country of observation)
Date   Thu, 24 Feb 2011 01:46:57 +0000

Here is a recipe:

Total of others = Total of all - Total (value) of this one

Mean of others = Total of others / (Count of all - 1)

The argument is expanded in excruciating detail within an FAQ:

FAQ     . . Creating variables recording prop. of the other members of a group
        . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  N. J. Cox
        4/05    How do I create variables summarizing for each
                individual properties of the other members of a
                group?
                http://www.stata.com/support/faqs/data/members.html

In your case, this looks like (allowing for the possibility of an
unbalanced panel)

bysort year: gen nothers = _N - 1
bysort year : egen total = total(capital)
gen meanothers = (total - capital)  / nothers

The first line assumes no missings on -capital-. If there are missings
of capital, you need

bysort year : egen n = count(capital)
bysort year : egen total = total(capital)
gen meanothers = (total - capital)  / (n - 1)

and so that's the more general code.

Nick

On Wed, Feb 23, 2011 at 8:49 PM, Waedlich Felix <fwaedlich@gmail.com> wrote:

> I have a panel data set with 140 countries over a time period if 28 years and I want to analyze determinants of capital regulation.
>
> I want to estimate to what extent the level of regulation is influenced by the observable levels in specific reference groups (cultural, regional, etc.) Therefore I planned to generate variables based on the average restrictivness in these groups, which I will use as explanatory variable for my regression.
> Practically i have a dependent variable (capital) and several dummy variables which are supposed to serve as a filter to generate specific regulation averages for each country and year. I.e. all European countries like Belgium, France, etc. will look at the same level of restrictivness in 1978.
> Since, I am rather unexperienced with Stata, I could only came up with this egen code:
>
> . bysort year: egen mean_capital=mean(capital)
>
> So it looks like this:
>
>     +---------------------------------+
>     | mean_capital         country   year |
>     |---------------------------------|
>  1. | 3.848485   UNITED STATES   1978 |
>  2. | 3.825243   UNITED STATES   1979 |
>  3. | 3.847619   UNITED STATES   1980 |
>  4. | 3.839623   UNITED STATES   1981 |
>  29. | 3.848485          CANADA   1978 |
>  30. | 3.825243          CANADA   1979 |
>  31. | 3.847619          CANADA   1980 |
>  32. | 3.839623          CANADA   1981 |
>
> Theoretically, I need to generate this variable excluding the regulation level of the country I am observing. Meaning if there are four countries in one region, each country will only weigh in the level of regulation of the other 3 countries, but not his own regulation level.
>
>
> Does anybody has a clue?

*
*   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