* References: Chapters 2 and 6 of
* Jeffrey M. Wooldridge, Introductory Econometrics: A Modern Approach,
* South-Western College Publishing, 2000.
SAMPLE 1 209
READ (CEOSAL1.shd) salary pcsalary sales roe pcroe ros indus &
     finance consprod utility lsalary lsales 

* Example 2.3, pp. 32-33; Example 2.6, pp. 36-37; Example 2.8, p. 40.
* Get summary statistics on the variables
STAT salary roe
* OLS regression 
* On the OLS command the first variable is the dependent variable.
* The LIST option on the OLS command lists the fitted values
* and residuals (see Table 2.2, pp. 36-37).
OLS salary roe / LIST
* The right portion of SHAZAM output from the LIST option shows
* a crude residual plot.

* Section 2.4 - Units of Measurement
* Express salary in dollars
GENR salardol=salary*1000
* Estimation results in Equation (2.40), p. 41.
OLS salardol roe
* Now rescale the independent variable
GENR roedec=roe/100
* Estimation results in Equation (2.41), p. 42.
OLS salary roedec

* Example 2.11, pp. 44-45
* The LOGLOG option on the OLS command specifies that both the
* dependent variable and explanatory variable are log-transformed.
* This option is used for calculating the elasticities reported 
* on the SHAZAM output.
OLS lsalary lsales / LOGLOG

* Example 6.4
* Equation (6.25), p. 195
OLS salary sales roe / RSTAT
* Equation (6.26), p. 195
OLS lsalary lsales roe / LOGLOG RSTAT
* The LOGLOG option on the OLS command specifies that the dependent
* variable is log transformed. 
* With the LOGLOG and RSTAT options, the SHAZAM output reports the
* statistic R-SQUARE BETWEEN ANTILOGS OBSERVED AND PREDICTED
* This R-square can be compared with the R-square reported
* for the equation with the dependent variable in levels.
STOP