Week Two
Econometrics
(a) (i) Regress FGPA on a constant and SATV. Report the coefficient
of SATV and its standard error and p-value (give your answers
with 3 decimals).
(ii) Determine a 95% confidence interval (with 3 decimals) for
the effect on FGPA of an increase by 1 point in SATV.
Regressed using Microsoft Excel -
SUMMARY
OUTPUT
Regression Statistics
Multiple R 0.092167121
R Square 0.008494778
Adjusted R Square 0.006861326
Standard Error 0.458655877
Observations 609
ANOVA
Significance
df SS MS F F
Regression 1 1.094006 1.094006 5.200508 0.022926
Residual 607 127.6917 0.210365
Total 608 128.7857
Standard Upper Lower
Coefficients Error t Stat P-value Lower 95% 95% 95.0%
Intercept 2.441732463 0.155062 15.74681 4.26E-47 2.137209 2.746256 2.137209
SATV 0.063085845 0.027664 2.280462 0.022926 0.008758 0.117414 0.008758
The coefficient rounded to 3 decimals is: 0.063
The Standard error of Slope rounded to 3 decimals is: 0.028
The P-Value rounded to 3 decimals is: 0.023
The 95% confidence interval for effect on FGPA with an increase by 1 point is:
[0.0088, 0.1174]
(b) Answer questions (a-i) and (a-ii) also for the regression of FGPA on a
constant, SATV, SATM, and FEM.
SUMMARY
OUTPUT
Regression Statistics
Multiple R 0.288035928
R Square 0.082964696
Adjusted R Square 0.078417414
Standard Error 0.44182384
Observations 609
ANOVA
Significance
df SS MS F F
Regression 3 10.68466569 3.56155523 18.24489595 2.4115E-11
Residual 605 118.1010251 0.195208306
Total 608 128.7856908
Standard
Coefficients Error t Stat P-value Lower 95% Upper 95%
Intercept 1.557048213 0.216095514 7.20537036 1.72986E-12 1.132659785 1.981436641
SATM 0.172735887 0.031926713 5.410387396 9.07148E-08 0.110035244 0.23543653
SATV 0.014161897 0.027926969 0.507104667 0.612266162 -0.040683678 0.069007471
FEM 0.200271605 0.037380851 5.357598893 1.20027E-07 0.126859621 0.273683589
The coefficient rounded to 3 decimals is: 0.014
The Standard error rounded to 3 decimals is: 0.027
The P-Value rounded to 3 decimals is: 0.612
The 95% confidence interval for effect on FGPA with an increase by 1
point is: [-0.0406, 0.0690]
(c) Determine the (4 × 4) correlation matrix of FGPA, SATV, SATM,
and FEM. Use these correlations to explain the differences
between the outcomes in parts (a) and (b).
FGPA SATV SATM FEM
FGPA 1.000000 0.092167 0.195040 0.176491
SATV 0.092167 1.000000 0.287801 0.033577
SATM 0.195040 0.287801 1.000000 -0.162680
FEM 0.176491 0.033577 -0.162680 1.000000
When SATV was the only variable that we were working with, it had
a major impact on FGPA. However, when we introduce other
variables, this impact becomes a little less significant as noticed in
part b where we study the partial dependence. This is because SATM
and SATV are the correlated and due to that the impact is from the
influence of SATM.
(d) (i) Perform an F-test on the significance (at the 5% level)
of the effect of SATV on FGPA, based on the regression in part
(b) and another regression. Note: Use the F-test in terms of SSR
or R 2 and use 6 decimals in your computations. The relevant
critical value is 3.9.
(ii) Check numerically that F = t^2.
F-Test Two-Sample for
Variances
The Modified Model SSR rounded to 6 decimals is: 118.151224
The Modified Model R^2 rounded to 6 decimals is: 0.082575
The Part-B Model SSR rounded to 6 decimals is: 118.101025
The Part-B Model R^2 rounded to 6 decimals is: 0.082965
The F statistic rounded to 3 decimals is: 0.258
F-statistic is less than the provided critical value, i.e., 0.258 < 3.9, Null
hypothesis H0 is not rejected.
