| Objective: Use the Gretl program to replicate
Example 2.2.3 on 42-54 using the finaid2.csv
data file. The data file contains information on the Financial Aid
Award (in dollars), Parent's Expected Contribution (in dollars) and the
Student's High School Rank (in percentiles) for 50 college students.
I. Programming: Click here
for programming directions. Note: this data is cross-sectional
data, i.e., it's measured across individuals at a point of time.
II. Assignment:
a. Generate descriptive statistics (means, standard deviations,
minimums and maximums) for each variable. Briefly discuss.
b. Run a regression of FINAID on PARENT and HSRANK.
Print out the regression results, including predicted values and residuals.
c. What regression "model" are you estimating? Specifically,
what kind of relationship are you assuming exists between which variables?
Describe verbally and algebraically.
d. Specifically, what do the observed FINAID, predicted FINAID,
and residual columns tell you? How are they computed?
e. Interpret the coefficients.
f. How could the regression results be used to predict
financial aid award amounts? Give an example.
g. What does the R squared value measure? the adjusted
R squared? Which should be used?
h. Compute the standardized coefficients and elasticities.
What do they show? |