Re: st: MIXLOGIT: marginal effects

[Arne Risa Hole <arnehole@gmail.com>]

Fine, let's agree to disagree. On the last point -mvreg- is hardly a
useful alternative for fitting multinomial choice models in general.

Arne

On 6 February 2012 17:42, Maarten Buis <maartenlbuis@gmail.com> wrote:
> On Mon, Feb 6, 2012 at 6:25 PM, Arne Risa Hole wrote:
>> Thanks Maarten, I take your point, but as Richard says there is
>> nothing stopping you from calculating marginal effects at different
>> values of the explanatory variables (although admittedly it's rarely
>> done in practice).
>
> That is fine, but in that case I would be reporting/plotting predicted
> probabilities rather than marginal effects. There is not a big
> difference between the two --- the latter is just the first derivative
> of the former --- but if you are going to report multiple numbers than
> the former seems more direct to me.
>
> Anyhow, as you said, this is typically not what people (or reviewers,
> advisers, etc.) want; they just want to know what "the" effect is and
> not be bothered with multiple different effects. In that case my
> previous post applies and marginal effects are (almost) always the
> wrong choice.
>
>> Also the LPM is fine as an alternative to binary
>> logit/probit but what about multinomial models?
>
> In that case I would look at -mvreg-.
>
> -- Maarten
>
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
>
>
> http://www.maartenbuis.nl
> --------------------------
> *
> *   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/