October 9 In-Class Review Problems
Based on Problem 4.1 in the text:
Which of the following can cause the usual OLS t-statistics to be invalid?
a) heteroskedasticity
b) omitting an important variable
c) including two highly correlated independent variables
d) both a) & b)
Based on Problem 4.10 in the text:
I want to test the efficient market hypothesis (i.e. that market returns are not predictable) and thus obtain the following Stata output:
Source | SS df MS Number of obs = 142
------+------F( 4, 137) = 1.41
Model | 8649.26028 4 2162.31507 Prob > F = 0.2347
Residual | 210446.917 137 1536.10888 R-squared = 0.0395
------+------Adj R-squared = 0.0114
Total | 219096.178 141 1553.8736 Root MSE = 39.193
------
return | Coef. Std. Err. t P>|t| [95% Conf. Interval]
------+------
dkr | .3205444 .2009106 1.60 0.113 -.0767426 .7178314
eps | .0426986 .0781384 0.55 0.586 -.1118147 .1972119
netinc | -.0051086 .0046748 -1.09 0.276 -.0143526 .0041354
salary | .0034993 .0021935 1.60 0.113 -.0008382 .0078369
_cons | -14.37022 6.893616 -2.08 0.039 -28.00187 -.7385649
------
a) the lowest level I can definitely reject the hypothesis at is 3.95%
b) the lowest level I can definitely reject the hypothesis at is 23.47%
c) none of the x variables are significant, so I definitely can’t reject
d) I can’t definitely reject or not without more information
Based on Problem 4.17 in the text:
I produce the following output from Stata, where tenexp=tenure+experience:
lwage | Coef. Std. Err. t P>|t| [95% Conf. Interval]
------+------
educ | .0748638 .0065124 11.50 0.000 .062083 .0876446
tenure | -.0019537 .0047434 -0.41 0.681 -.0112627 .0073554
tenexp | .0153285 .0033696 4.55 0.000 .0087156 .0219413
_cons | 5.496696 .1105282 49.73 0.000 5.279782 5.713609
------
a) I can conclude that tenure has a negative, but insignificant effect on wage
b) I can conclude that experience has a positive and significant effect on wage
c) I can conclude that the effect of tenure and experience are not significantly different
d) I can conclude both b) and c)