Statalist


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

Re: st: two level model


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: two level model
Date   Sat, 18 Aug 2007 21:21:39 -0400

Viktor--
The -glm- command you specified seems a reasonable starting point,
though I would specify -vce(cluster id)- to allow errors to be
correlated within person.  You might also explore -nlsur- which could
offer a modest gain in efficiency, and a wider variety of functional
forms to match the specification implied by your theory.  Just to be
clear--the people are making one choice (not multiple choices) and you
observe the resulting portfolio allocation, yes?  Are the shares
invested in various countries supposed to add to one?

On 8/18/07, Viktor Slavtchev <viktor.slavtchev@uni-jena.de> wrote:
> dear,
> I have followed model.
> People can make (multiple) choices. For example, people can invest their
> money in different countries, whereat multiple investment options are
> possible at the same time.

> Example
>
> id      country         investment_share        interest_rate   gender
> 1       Germany         .2      .02     0
> 1       US      .5      .03     0
> 1       UK      .1      .025    0
> 1       France  .1      .022    0
> 1       Italy   .1      .023    0

> I've just tried followed:
> xi: glm investment_share interest_rate gender i.id, family(binomial)
> link(logit) scale(x2)
>
> Is this an appropriate way to solve the problem?
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index