Re: st: Regressions with combinatorial of variables

[Nick Cox <njcoxstata@gmail.com>]

I suggest that before trying to program this yourself, check out
-stepwise-, the Lindsey and Sheather paper in SJ 10(4) 2010 and above
all the discussion of stepwise in Frank Harrell's Regression modeling
strategies (Springer, New York, 2001).

I note that you have 2^131 ~ 3 * 10^39 possible models. (Well, one fewer.)

Nick

2011/2/1 José Luis Chávez Calva <josechc@gmail.com>:

> I have to run different regressions with combinations of variables (I
> have 131 vars), the problem is the following
>
> I have to run:
>     reg var1
> case 1) var1 is significant, then
>     reg var1 var2
> case 2) car1 is not significant, then
>     reg var2
> In both cases, if var2 is significant, then
> case 1) reg var1 var2 var3
> case 2) reg var2 var3
> In both cases, if var2 is not significant, then
> case 1) reg var1 var3
> case 2) reg var3
> ....
> And so on, in fact it is a kind of tree, I have tried different
> especifications (forvalues, locals, if,etc.) but I didn´t have
> results, I'm wondering if some of you have worked with something like
> this.
>
> p.s. It is for obtain a smoother of the serie.

*
*   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/