Re: st: Statistically Significant Increase in R-Squared

[Alan Acock <acock@mac.com>]

If you want to use the nested regression command from the menu it is in a strange place, statistics-->Other-->nested regression.

The menu takes you through all the options and nestreg use the appropriate test for a wide variety of regression models.

Alan Acock

On Jan 23, 2009, at 4:57 PM, Sergiy Radyakin wrote:

improves the model more than would be expected by chance."

sysuse auto
regress price length
di e(r2_a)
regress price length weight
di e(r2_a)
regress price length weight gear_ratio
di e(r2_a)
regress price length weight gear_ratio trunk
di e(r2_a)

Best regards, Sergiy Radyakin

On Fri, Jan 23, 2009 at 7:38 PM, Roger Roles <rogerroles2@yahoo.com> wrote:

Is there a way in Stata to determine whether or not the change in R-squared is statistically significant?  In other words, if I enter the second block of variables into my model, and there is an increase in R-squared, how can I determine if that change (from block 1 to block 2) is statistically significant?  Thank you!

*

*   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/