Econ 170 - Fall 2005: September 2005 Archives

« August 2005 | Main | October 2005 »

September 29, 2005

The F Test

Posted by bparke at 11:59 PM | Comments (0)

Football Log

. regress attendance wins

Source | SS df MS Number of obs = 30
-------------+------------------------------ F( 1, 28) = 6.61
Model | 3.7518e+10 1 3.7518e+10 Prob > F = 0.0157
Residual | 1.5889e+11 28 5.6746e+09 R-squared = 0.1910
-------------+------------------------------ Adj R-squared = 0.1621
Total | 1.9641e+11 29 6.7726e+09 Root MSE = 75330

------------------------------------------------------------------------------
attendance | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
wins | 12352.97 4804.158 2.57 0.016 2512.096 22193.84
_cons | 392509.8 40518.55 9.69 0.000 309511.3 475508.2
------------------------------------------------------------------------------

. regress attendance wins losses

Source | SS df MS Number of obs = 30
-------------+------------------------------ F( 2, 27) = 5.50
Model | 5.6848e+10 2 2.8424e+10 Prob > F = 0.0099
Residual | 1.3956e+11 27 5.1688e+09 R-squared = 0.2894
-------------+------------------------------ Adj R-squared = 0.2368
Total | 1.9641e+11 29 6.7726e+09 Root MSE = 71895

------------------------------------------------------------------------------
attendance | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
wins | -61923.24 38681.87 -1.60 0.121 -141291.9 17445.4
losses | -74803.57 38681.87 -1.93 0.064 -154172.2 4565.08
_cons | 1575209 612810.3 2.57 0.016 317826.5 2832592
------------------------------------------------------------------------------

. regress attendance

Source | SS df MS Number of obs = 30
-------------+------------------------------ F( 0, 29) = 0.00
Model | 0 0 . Prob > F = .
Residual | 1.9641e+11 29 6.7726e+09 R-squared = 0.0000
-------------+------------------------------ Adj R-squared = 0.0000
Total | 1.9641e+11 29 6.7726e+09 Root MSE = 82296

------------------------------------------------------------------------------
attendance | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_cons | 490510 15025.14 32.65 0.000 459780.1 521239.8
------------------------------------------------------------------------------

. - preserve

. log close
log: T:\170-temp\football1.log
log type: text
closed on: 29 Sep 2005, 12:04:56

Posted by bparke at 03:00 PM | Comments (0)

September 27, 2005

Understanding Regressions

Posted by bparke at 11:50 PM | Comments (0)

September 22, 2005

How to Use Stata

We spent the entire class period talking about how to do the exercises with Stata.

We learned where to find the following on the Stata output.

Posted by bparke at 10:47 PM | Comments (0)

September 20, 2005

Review of Moments of Random Variables

Posted by bparke at 10:28 PM | Comments (0)

Regression Theory

We start with some basic assumptions.

The regression does not yield the true, unknown parameters precisely because the random error terms impart random effects on the slope.

Some important algebra (not in the textbook):

Correlation between the regressor and the error term causes bias.

Posted by bparke at 10:25 PM | Comments (0)

September 15, 2005

Ordinary Least Squares

Issue in choosing the dependent and independent variable:

We also talked about the difference between an accounting identify (see above) and a behavioral relationship.

Unlike covariance and correlation, ordinary least squares assumes a particular orientation for the deviations from a straight line. This leads to some interesting differences in formulas.