looks like it is a problem with -_rmcoll-, which is called by -oprobit-
but not by -regress-. -_rmcoll- turns "i.foreign#c.weight#c.weight"
into "i.foreign#co.weight#co.weight", which then throws the error.
. _rmcoll rep78 c.weight#c.weight i.foreign#c.weight#c.weight
. ret li
scalars:
r(k_omitted) = 1
macros:
r(varlist) : "rep78 c.weight#c.weight i(0
1)b0.foreign#co.weight#co.weight"
. reg rep78 c.weight#c.weight i(0 1)b0.foreign#co.weight#co.weight
invalid interaction specification;
multiple 'o' operators attached to a single variable are not allowed
within an interaction specification{p_end}
r(198);
* with one of the "co" turned to "c":
. reg rep78 c.weight#c.weight i(0 1)b0.foreign#co.weight#c.weight
Source | SS df MS Number of obs =
69
-------------+------------------------------ F( 2, 66) =
19.51
Model | 24.7558569 2 12.3779284 Prob > F =
0.0000
Residual | 41.8818243 66 .634573095 R-squared =
0.3715
-------------+------------------------------ Adj R-squared =
0.3525
Total | 66.6376812 68 .979965899 Root MSE =
.7966
------------------------------------------------------------------------------
rep78 | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+----------------------------------------------------------------
c.weight#|
c.weight | -1.62e-08 2.27e-08 -0.71 0.479 -6.15e-08
2.92e-08
|
foreign#|
c.weight#|
c.weight |
1 | 2.14e-07 4.27e-08 5.01 0.000 1.29e-07
2.99e-07
|
_cons | 3.222682 .2806022 11.48 0.000 2.662441
3.782922
------------------------------------------------------------------------------
Martin Weiss wrote:
<>
I used to think that the expansion of the -fvvarlist- happened
"independently" of the estimation command that requested it...
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Nick Winter
Gesendet: Dienstag, 13. Oktober 2009 17:29
An: [email protected]
Betreff: Re: st: AW: Interaction with squared variable
I can reproduce this with the auto dataset. Seems like something for
technical support...
. regress rep78 i.foreign c.weight c.weight#c.weight
i.foreign#(c.weight#c.weight)
<<model estimation output omitted>>
. oprobit rep78 i.foreign c.weight c.weight#c.weight
i.foreign#(c.weight#c.weight)
invalid interaction specification;
multiple 'o' operators attached to a single variable are not allowed
within an interaction specification{p_end}
r(198);
Nick Winter
Giuseppe Cappelletti wrote:
This is the message I get when I use the command ( oprobit y
i.gender c.x c.x#c.x i.gender#(c.x#c.x) )
"invalid interaction specification;
multiple 'o' operators attached to a single variable are not allowed
within an interaction specification{p_end}"
The same command works if I use a linear model that is regress y
i.gender c.x c.x#c.x i.gender#(c.x#c.x).
Thanks in advance
Giuseppe
<>
" but it does not work".
What exactly does not work? Note the FAQ onthis point...
HTH
Martin
*
* 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/
--
--------------------------------------------------------------
Nicholas Winter 434.924.6994 t
Assistant Professor 434.924.3359 f
Department of Politics [email protected] e
University of Virginia faculty.virginia.edu/nwinter w
PO Box 400787, 100 Cabell Hall
Charlottesville, VA 22904
*
* 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/
