Hi all,

My question, although probably basic to most of you, is:  If you are
comparing two models, why might the test variables parameter estimates
be significant in the second case and not in the first yet the
R-square is decreased.  For example:

Model 1 - Some time period

y = x1 + x2 + x3 + x4 + x5  (x3, x4 x5 are dummy variables)

The coefficient is statistically significant (at .05) for none of the
variables but weakly significant (at .10) for x1.


Model 2 - Another time period

y = x1 + x2 + x3 + x4 + x5  (x3, x4 & x5 are dummy variables)

The coefficient is statistically significant (at .05) for the x1, x3,
and x5 variables.  The other variables are statistically insignificant
at greater than the .10 level.


Because of this I'm not quite sure why the R-squared would be
decreasing given statistically significant information has been added
to the model.

Any suggestions that can be offered would be greatly appreciated.


=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at
                  http://jse.stat.ncsu.edu/
=================================================================

Reply via email to