A causal effect of X on Y is defined as:

A) a non-zero correlation between X and Y

B.) a positive relationship between X and Y
C.) either positive, negative or non-linear relationship between X and Y
D.) either a positive, negative or non-linear relationship between X and Y when all other
variables that affect Y are held constant
D
Correlation between X and Y can only be interpreted as a causal relationship of X and Y if:
A.) Y is unaffected by X in a linear way
B.) Y is an affected by any variable other than X
C.) Y is unaffected by any variable that is correlated with X
D.) Both A and C
D
If the variance of grades in this course is 16, each student should (unconditionally) expect their
grade to deviate from the class average by:
A.) 32 points
B.) 16 points
C.) 8 points
D.) 4 points
D
The variance of a random variable Y:
A.) is always less than the variance of the simple mean
B.) is always greater than the variance of the same mean
C.) is equal to the variance of the same mean when the sample size is 1
D.) none of the above
C
As the sample size increases, the variance of the sample mean
A.) increases
B.) decreases
C.) stays constant
D.) not enough info to know
B
A negative covariant between X and Y implies that
A.) as X increases, Y increases
B.) there is no linear relationship between X and Y
C.) -1 < Corr(X,Y) < 0
D.) none of the above
C
Two random variables X and Y are considered independent of each other if Corr(X,Y) = 0
A.) True
B.) False
B
If a change in variable X causes a change in variable Y, variable Xis called the
A.) dependent variable
B.) explanatory variable
C.) independent variable
D.) both B and C
D
In the equation " Y = Bo + B1X + u " Bo is the ____________ an B1 is the ____________.
A.) error term, slope
B.) error term, intercept
C.) intercept, slope
D.) none of the above
C
In a simple linear regression equation, if X increases by 3:
A.) Y increases by B1
B.) Y increases by 3 * (Bo + B1)
C.) Y increases by B1/3
D.) none of the above
D
If the total sum of squares (SST) in a regression is 81, and the sum of squares residuals (SSR)
is 25, what is R-squared?
0.69
An R-squared close to 1 implies that X and Y are positively correlated with one another.
A.) True
B.) False
B
The error term in a regression equation is said to exhibit homoskedacity if
A.) it has zero conditional mean
B.) is has the same variance for all values of the explanatory variable
C.) it has the same value for all values of the explanatory variable
D.) none of the above
B
All of the following are assumed for establishing that Ordinary Least Square (OLS) is the best
linear unbiased expect
A.) the regression equation is linear
B.) the sample outcomes on the explanatory variable are all the same value
C.) the error term ha the same variance given any value of the explanatory variable
D.) all of the above are assumed for establishing that OLS is BEST
B
The OLS method estimates Bo and B1 by
A.) minimizing the sum of residuals
B.) minimizing the sum of squared differences between predicted values and observed values
C.) minimizing the sum of squared residuals
D.) both B and C
D
In a simple linear regression equation, if X increases by 3:
A.) Y increases by B1
B.) Y increases by 3 * (Bo + B1)
C.) Y increases by B1/3
D.) none of the above
D
If the total sum of squares (SST) in a regression is 81, and the sum of squares residuals (SSR)
is 25, what is R-squared?
0.69
An R-squared close to 1 implies that X and Y are positively correlated with one another.
A.) True
B.) False
B
The error term in a regression equation is said to exhibit homoskedacity if
A.) it has zero conditional mean
B.) is has the same variance for all values of the explanatory variable
C.) it has the same value for all values of the explanatory variable
D.) none of the above
B
All of the following are assumed for establishing that Ordinary Least Square (OLS) is the best
linear unbiased expect
A.) the regression equation is linear
B.) the sample outcomes on the explanatory variable are all the same value
C.) the error term ha the same variance given any value of the explanatory variable
D.) all of the above are assumed for establishing that OLS is BEST
B
The OLS method estimates Bo and B1 by
A.) minimizing the sum of residuals
B.) minimizing the sum of squared differences between predicted values and observed values
C.) minimizing the sum of squared residuals
D.) both B and C
D
When it comes to measuring causal effects, one advantage that a simple linear regression
model has over a simple correlation is:
A.) B1 measures non-linear relationships while a simple correlation coefficient does not
B.) a simple linear regression model allows you to control for unobserved variables while a
simple correlation coefficient does not
C.) both A and C
D.) none of the above
D
The main benefit of using multiple regression over simple regression is:
A.) multiple estimates are usually more efficient than simple estimates
B.) multiple estimates usually have a lower variance than simple estimates
C.) multiple estimates are less susceptible to bias than simple estimates
D.) both A and B
C
The main drawback of using multiple regression over simple regression is:
A.) multiple estimates are usually less efficient than simple estimates
B.) multiple estimates usually have a higher variance than simple estimates
C.) multiple estimates are more susceptible to bias than simple estimates
D.) both A and B
B
As the number of relevant independent variables in a regression increases, the R-squared of a
regression
A.) increases
B.) decreases
C.) stays constant
D.) exhibits greater heteroskedasticity
A
Multicollinearity refers to the situation where:
A.) R-squared > 0
B.) two or more independent variables are highly correlated with one another
C.) two or more of the independent variables are perfect correlated
D.) none of the above
B
In practice, the main problem with multicollinearity is that it:
A.) violates one of the OLS assumptions
B.) raises the standard deviation of the coefficient estimates
C.) biases the coefficient estimate
D.) all of the above
B
The null hypothesis Ho: B2>0 states that:
A.) X2 has a positive effect on B2
B.) Y has a positive effect on X2
C.) X2 has a positive effect on Y
D.) none of the above
C
You should reject the null hypothesis Ho: B1=0 if:
A.) | t-stat | > critical value
B.) t-stat > -critical value
C.) either t-stat > critical value or t-stat < -critical value
D.) both A and C
D
You should reject the null hypothesis Ho: B1>0 if:
A.) tstat < critical value
B.) | tstat | < critical value
C.) tstat > critical value
D.) tstat < -critical value
D
Which of the statements are true?
A.) confidence intervals provide a range of likely values for a population parameters
B.) when the standard deviation of a coefficient increases, the confidence interval increases
C.) when the sample size of a regression increases, the confidence interval for the coefficient
estimate narrows down
D.) both A and C
D
The F-stat is always non-negative because R-squared in the restricted model is never larger
than R-squared in the unrestricted model.
A.) True
B.) False
A