[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: stepwise et al

From   "b.qureishi" <>
Subject   Re: st: stepwise et al
Date   Mon, 27 Aug 2007 16:52:17 +0100

Thanks for the link Phil.

I have made progress in back testing my model without using stepwise. However,
as I am short on time, it would be atleast interesting to evaluate and compare
the differences in the respective relationships. Thefore, any direction would
be appreciated.

On a seperate, whilst back testing my model. I yeilded strong relationships.
However, when I changed my dependant variable (but mantained my independant
set) I was unable to generate any results. Instead a T statistic, I would get
"." Does anyone know why this is happening?
I am trying to determine what independant variables effect stock performance.
Therefore, my independant conditioning set is fixed, whereas my dependant
variables change-as they have been computed using an array of models.



Quoting Phil Schumm <>:

On Aug 27, 2007, at 7:08 AM, b.qureishi wrote:
Are you familiar with stepwise function on stata. I have a model that i need to back test. Im playing around with the function, however, am not making much progress. Your thoughts and assistance would be most appreciated.

It's not at all clear what your question is. However, before attempting to re-ask it, please see

if you haven't already. You may, based on that, decide to forgo the stepwise approach. In any case, know that you won't get a very warm reception for stepwise analyses on this list, for the reasons described above (nothing personal). Despite that, if you have a specific question about how to perform stepwise analyses in Stata, people here can help you with that.

-- Phil

* For searches and help try:

This e-mail may contain confidential and/or privileged information. If you are
not the intended recipient (or have received this e-mail in error) please
notify the sender immediately and destroy this e-mail. Any unauthorized
copying, disclosure or distribution of the material in this e-mail is strictly

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index