ECON306, Fall 2022
Solutions: Study Material for Midterm #2
1 Multiple Choice
circle the letter of the best answer.
A) You want to estimate the size of a car’s engine’s displacement (basically, how large is the engine).
The weight of a car has a causal effect on the size of an engine’s displacement (heavier cars need
larger engines). The length of a car does not have a causal effect on the size of a car’s engine.
There is a strong, positive correlation beteween weight and length. Which of the following
specifications is subject to omitted variable bias?
a) displacement = β0 + β1 weight + β2 length + ui
b) displacement = β0 + β1 weight + ui
c) displacement = β0 + β1 length + ui X
d) displacement = β1 weight + β2 length + ui
B) The interpretation of the slope coefficient in the model ln(Yi ) = β0 + β1Xi + ui is as follows:
a) an increase in X by one unit is associated with a β1 change in Y
b) an increase in X by one unit is associated with a 0.01β1 % change in Y.
c) an increase in X by one unit is associated with a β1 % change in Y.
d) an increase in X by one unit is associated with a 100β1 % change in Y. X
C) You would run into a problem with perfect multicollinearity if your regressors include
a) degress Fahrenheit and degrees Celsius X
b) dummy variables for every size drink but not intercept
c) students’ cumulative GPA and semester GPA
d) the value of the S&P 500 index and the value of the Dow Jones Industrial Average
D) If you intended to measure the speed of cars [in miles per hour(mph))] on a given stretch of road
with a radar gun, but then found out after your measurements were all taken that the radar gun
was set to km/h, how could you correct your results? Note: there are 1.609km in one mile.
1.6092 σspeed
2
a) Run the regression then multiply the relevant slope term by 2
1.6092 σspeed +1.6092
1.6092 σspeed
2
b) Run the regression then divide the relevant slope term by 2
1.609 σspeed +1.6092
2
c) Convert speed into mph then put that newly converted variable into the regression X
d) Go back in time and re-measure cars’ speed with the radar gun in the proper setting.
E) Which type of measurement error would not cause biased coefficients in a regression?
a) classical measurement error in X
b) classical measurement error in Y X
c) systematic measurement error in X
d) systematic measurement error in Y
Solutions: Study Material for Midterm #2
1 Multiple Choice
circle the letter of the best answer.
A) You want to estimate the size of a car’s engine’s displacement (basically, how large is the engine).
The weight of a car has a causal effect on the size of an engine’s displacement (heavier cars need
larger engines). The length of a car does not have a causal effect on the size of a car’s engine.
There is a strong, positive correlation beteween weight and length. Which of the following
specifications is subject to omitted variable bias?
a) displacement = β0 + β1 weight + β2 length + ui
b) displacement = β0 + β1 weight + ui
c) displacement = β0 + β1 length + ui X
d) displacement = β1 weight + β2 length + ui
B) The interpretation of the slope coefficient in the model ln(Yi ) = β0 + β1Xi + ui is as follows:
a) an increase in X by one unit is associated with a β1 change in Y
b) an increase in X by one unit is associated with a 0.01β1 % change in Y.
c) an increase in X by one unit is associated with a β1 % change in Y.
d) an increase in X by one unit is associated with a 100β1 % change in Y. X
C) You would run into a problem with perfect multicollinearity if your regressors include
a) degress Fahrenheit and degrees Celsius X
b) dummy variables for every size drink but not intercept
c) students’ cumulative GPA and semester GPA
d) the value of the S&P 500 index and the value of the Dow Jones Industrial Average
D) If you intended to measure the speed of cars [in miles per hour(mph))] on a given stretch of road
with a radar gun, but then found out after your measurements were all taken that the radar gun
was set to km/h, how could you correct your results? Note: there are 1.609km in one mile.
1.6092 σspeed
2
a) Run the regression then multiply the relevant slope term by 2
1.6092 σspeed +1.6092
1.6092 σspeed
2
b) Run the regression then divide the relevant slope term by 2
1.609 σspeed +1.6092
2
c) Convert speed into mph then put that newly converted variable into the regression X
d) Go back in time and re-measure cars’ speed with the radar gun in the proper setting.
E) Which type of measurement error would not cause biased coefficients in a regression?
a) classical measurement error in X
b) classical measurement error in Y X
c) systematic measurement error in X
d) systematic measurement error in Y
