Re: Re: st: Error w/ "inteff" command

[Nick Cox <njcoxstata@gmail.com>]

I have comments on various quite different levels:

1. -inteff- is from Stata Journal.

st0063_1 from http://www.stata-journal.com/software/sj4-3
    SJ4-3 st0063_1.  Computing interaction effects and standard ... /
    Computing interaction effects and standard errors in logit / and probit
    models / by Edward C. Norton, University of North Carolina at Chapel Hill,
    USA / Hua Wang, University of North Carolina at Chapel Hill, USA /

st0063 from http://www.stata-journal.com/software/sj4-2
    SJ4-2 st0063.  Computing interaction effets and standard ... / Computing
    interaction effets and standard errors in logit / and probit models / by
    Edward C. Norton, Hua Wang / University of North Carolina at Chapel Hill,
    USA / Chunrong Ai / University of Florida, USA, and Tsinghua University,

You are asked to explain where user-written commands you refer to come from.

2. As above, -inteff- is written up, so the SJ articles document what
it does. I've seen many questions about -inteff- on the list, but I
don't recollect seeing any answers from the authors, who don't appear
to be list members, so the implication is that unanswered questions on
the command should be directed at them.

3. Earlier in the thread, Kit in effect asked: why bother with
-inteff- given a full-blown and fully documented -margins- command. It
seems that his question has not been answered.

Nick

On Wed, Jan 2, 2013 at 3:48 PM, Erasmo Giambona <e.giambona@gmail.com> wrote:
> Dear Kit,
>
> I was finally able to get the "inteff" command to work again. Inteff
> and margins give me estimates on the interaction term that are
> similar, but not the same. Is this simply do to different
> approximation? Thanks. Please, see example below (using: webuse lbw2):
>
>
> . g age_lwt=age*lwt
>
> . probit  low age lwt age_lwt
>
> Iteration 0:   log likelihood =   -117.336
> Iteration 1:   log likelihood = -113.61015
> Iteration 2:   log likelihood = -113.58509
> Iteration 3:   log likelihood = -113.58509
>
> Probit regression                                 Number of obs   =        189
>                                                   LR chi2(3)      =       7.50
>                                                   Prob > chi2     =     0.0575
> Log likelihood = -113.58509                       Pseudo R2       =     0.0320
>
> ------------------------------------------------------------------------------
>          low |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
> -------------+----------------------------------------------------------------
>          age |  -.0316919   .0896229    -0.35   0.724    -.2073495    .1439658
>          lwt |  -.0087146   .0162868    -0.54   0.593     -.040636    .0232069
>      age_lwt |   .0000561   .0006749     0.08   0.934    -.0012666    .0013788
>        _cons |   1.186736   2.124989     0.56   0.577    -2.978165    5.351637
> ------------------------------------------------------------------------------
>
> . inteff low age lwt age_lwt
> Probit with two continuous variables interacted
> (0 observations deleted)
>
>     Variable |       Obs        Mean    Std. Dev.       Min        Max
> -------------+--------------------------------------------------------
>   _probit_ie |       189    .0000473    7.14e-06   .0000265   .0000548
>   _probit_se |       189    .0002247    .0000631   .0000304   .0002841
>    _probit_z |       189    .2615582    .2009778   .1001468   1.322986
>
> . margins, dydx(_all)
>
> Average marginal effects                          Number of obs   =        189
> Model VCE    : OIM
>
> Expression   : Pr(low), predict()
> dy/dx w.r.t. : age lwt age_lwt
>
> ------------------------------------------------------------------------------
>              |            Delta-method
>              |      dy/dx   Std. Err.      z    P>|z|     [95% Conf. Interval]
> -------------+----------------------------------------------------------------
>          age |  -.0108404   .0306064    -0.35   0.723    -.0708278    .0491469
>          lwt |  -.0029809   .0055547    -0.54   0.592    -.0138679    .0079061
>      age_lwt |   .0000192   .0002308     0.08   0.934    -.0004332    .0004715
> ------------------------------------------------------------------------------
>
>
>
>
>
>
>
>
> On Sat, Dec 29, 2012 at 11:16 PM, Christopher Baum <kit.baum@bc.edu> wrote:
>> <>
>> Erasmo said
>>
>> Does - margins, dydx(_all) - also handle the interaction of two dummy variables?
>>
>> Yes. ht (hypertension, yes/no) and smoke (yes/no) are such, and interacted in the model below. Notice that each has a positive main effect on low bw, but if they appear together the effect is, strangely enough, reduced (although the negative interaction coefficient is not distinguishable from zero).
>>
>> probit low c.age##i.race i.ht##i.smoke
>> margins, dydx(_all)
>>

*
*   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/