Re: st: margins & marginsplot when multiple outcomes are involved

[natalia malancu <natalia.malancu@gmail.com>]

Hi Roger,

thanks for your suggestions. I would look into the packages.
I guess since I'm interpreting the mlogit results in terms in odds
ratios , switching for illustrative purposes to probabilities might
get a bit confusing...or maybe not. I'll give it a thought.

Natalia

On Wed, Aug 29, 2012 at 10:02 PM, Roger B. Newson
<r.newson@imperial.ac.uk> wrote:
> Presumably, you could use -margins- (with the -post- option), followed by
> -nlcom-, to calculate scenario-specific odds. I don't know why anybody
> should want to do this, though.
>
> Odds are usually a means to the end of probabilities, not the other way
> round. My own packages -punaf-, -regpar-, -margprev- and -marglmean- are
> front ends for -margins- and -nlcom-, and can be used to compute scenario
> proportions and their differences and ratios after -mlogit-, using the
> -predict()- option.
>
> Best wishes
>
> Roger
>
>
> Roger B Newson BSc MSc DPhil
> Lecturer in Medical Statistics
> Respiratory Epidemiology and Public Health Group
> National Heart and Lung Institute
> Imperial College London
> Royal Brompton Campus
> Room 33, Emmanuel Kaye Building
> 1B Manresa Road
> London SW3 6LR
> UNITED KINGDOM
> Tel: +44 (0)20 7352 8121 ext 3381
> Fax: +44 (0)20 7351 8322
> Email: r.newson@imperial.ac.uk
> Web page: http://www.imperial.ac.uk/nhli/r.newson/
> Departmental Web page:
> http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/
>
> Opinions expressed are those of the author, not of the institution.
>
>
> On 29/08/2012 20:37, Scott Merryman wrote:
>>
>> Are relative odds the same thing as odds ratio?  Can you use the
>> probabilities in the margin0, margin1, and margin2 variables from my
>> example to calculate the odds?
>>
>> Perhaps someone with actual experience using -mlogit- and odds can help
>> out.
>>
>> Scott
>>
>>
>> On Wed, Aug 29, 2012 at 12:13 PM, natalia malancu
>> <natalia.malancu@gmail.com> wrote:
>>>
>>> Thank you so much, Scott.
>>> Meanwhile I  found a route using matrices, but your solution far more
>>> elegant and fast.
>>> One more question though: Is there a way is this context to use
>>> relative odds rather than probabilities in the response?
>>>
>>> Best,
>>> Natalia
>>
>> *
>> *   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/
*
*   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/