Question 1

Explain why we may choose to employ a varying slopes RD model instead of a linear RD model.

Accepted Answer

When we suspect that the slope of the line could be different before and after the cutoff, meaning when we suspect that the relationship between the assignment variable and the dependent variable of interest is different before and after the treatment is applied

Question 2

Show and explain why the correlation between the error term and T disappears when we control for the assignment variable.

Accepted Answer

$$\begin{aligned}
Y _ { i } & = \beta _ { 0 } + \beta _ { 1 } T _ { i } + \beta _ { 2 } X _ { 1 i } + \epsilon _ { i } \
& = \beta _ { 0 } + \beta _ { 1 } T _ { i } + \beta _ { 2 } X _ { 1 i } + \rho X _ { 1 i } + \nu _ { i }
\end{aligned}$$
We can ro-arrange and re-label $\beta _ { 2 } + \rho$ as $\hat { \beta } _ { 2 }$, producing
$$\begin{aligned}
Y _ { i } & = \beta _ { 0 } + \beta _ { 1 } T _ { i } + \left( \beta _ { 2 } + \rho \right) X _ { 1 i } + \nu _ { i } \
& = \beta _ { 0 } + \beta _ { 1 } T _ { i } + \tilde { \beta } _ { 2 } X _ { 1 i } + \nu _ { i }
\end{aligned}$$

Question 3

We employ binned graphs in order to.

Accepted Answer

A)  Help us ignore the functional form of model and allow use to use a liner model regardless of the true relationship. 
B)  Help us determine the functional form of the model. 
C)  Increase the statistical power of the model. 
D)  Deal with endogeneity. 
A)  Help us ignore the functional form of model and allow use to use a liner model regardless of the true relationship. 
B)  Help us determine the functional form of the model. 
C)  Increase the statistical power of the model. 
D)  Deal with endogeneity. B

Question 4

What is one of the limitations of using RD models in order to help make/shape policy decisions?

Accepted Answer

A)  The treatment effect may not be generalizable. 
B)  The cost of running and setting up an experiment to run an RD model can be prohibitively expensive. 
C)  Different assignment variables (and corresponding cutoff) can show treatment effects, difficult to tell which assignment variable is accurate. 
D)  Policymakers are much more comfortable randomly assigning treatment status than assigning treatment based on some assignment variable such as a test score or needs index. 
A)  The treatment effect may not be generalizable. 
B)  The cost of running and setting up an experiment to run an RD model can be prohibitively expensive. 
C)  Different assignment variables (and corresponding cutoff) can show treatment effects, difficult to tell which assignment variable is accurate. 
D)  Policymakers are much more comfortable randomly assigning treatment status than assigning treatment based on some assignment variable such as a test score or needs index.

Question 5

In order to diagnose if variables other than Y (dependent variable) jump at the cutoff, one must use which of the following equations:

Accepted Answer

A)  Yi=B0+B1Ti+B2(X1i-
C)  +B3(X1i-
C)  Ti +ei 
B)  Yi=B0+B1Ti+B2(X1i-
C)  +B3(X2i) Ti +ei 
C)  X2i=g0+g1Ti+g2(X1i-
C)  +vi 
D)  Xi=B0+B1Yi+B2(Yi-
C)  +B3(X2i) Ti +ei 
A)  Yi=B0+B1Ti+B2(X1i-
C)  +B3(X1i-
C)  Ti +ei 
B)  Yi=B0+B1Ti+B2(X1i-
C)  +B3(X2i) Ti +ei 
C)  X2i=g0+g1Ti+g2(X1i-
C)  +vi 
D)  Xi=B0+B1Yi+B2(Yi-
C)  +B3(X2i) Ti +ei

Question 6

Which one of the following is a key assumption in regression discontinuity models?

Accepted Answer

A)  The cutoff is random 
B)  The error term jumps at the cutoff 
C)  The error term is continuous and does not jump at the cutoff 
D)  The assignment variable is uncorrelated with the error term 
A)  The cutoff is random 
B)  The error term jumps at the cutoff 
C)  The error term is continuous and does not jump at the cutoff 
D)  The assignment variable is uncorrelated with the error term

Question 7

If the assignment variable is correlated with the error term, then a RD model will provide a biased estimate of the treatment effect.

Accepted Answer

A) True 
 B)False

Question 8

What is the consequence of having an error term that jumps at cutoff in a RD model?

Accepted Answer

A)  B1, the coefficient for the treatment effect is biased. 
B)  B2, the coefficient for the slope is biased. 
C)  We need to use a polynomial model. 
D)  We need to use a varying slopes model. 
A)  B1, the coefficient for the treatment effect is biased. 
B)  B2, the coefficient for the slope is biased. 
C)  We need to use a polynomial model. 
D)  We need to use a varying slopes model.

Question 9

One of the drawbacks of narrowing the window/range of the assignment variable is:

Accepted Answer

A)  Decrease in statistical power 
B)  Leads to bias if used on linear model 
C)  Leads to bias if used on a non-linear model. 
D)  Underestimates the effect of the treatment at the cutoff 
A)  Decrease in statistical power 
B)  Leads to bias if used on linear model 
C)  Leads to bias if used on a non-linear model. 
D)  Underestimates the effect of the treatment at the cutoff

Question 10

One of the main problems faced by RD is the fact that the error can be discontinuous at the treatment threshold.

Accepted Answer

A) True 
 B)False

Question 11

Consider a plot of a model of the form Yi = B0 +B1Ti + B2(X1i-C) + ei. Which of the following is true?

Accepted Answer

A)  B0 is the bump at the cutoff 
B)  B1 is the slope of the line 
C)  B2 is the slope of the line 
D)  B2 is the bump at the cutoff 
A)  B0 is the bump at the cutoff 
B)  B1 is the slope of the line 
C)  B2 is the slope of the line 
D)  B2 is the bump at the cutoff

Question 12

Please explain how to asses if other variables act differently at the point of discontinuity, and explain the consequence of other variables jumping at the point of discontinuity.

Accepted Answer

The answer of Please explain how to asses if other...

Question 13

Describe the benefits and drawbacks of adjusting the window of an RD model.

Accepted Answer

The answer of Describe the benefits and drawbacks of adjusting...

Question 14

Which of the following is a diagnostic test to assess the appropriateness of using a RD model?

Accepted Answer

A)  Use a histogram in order to make sure there is clustering on one side of the cutoff. 
B)  Run a RD model and see if the effect is statistically significant 
C)  Run a RD using other covariates as the dependent variable. 
D)  See if the results are the same using each cutoff separately. 
A)  Use a histogram in order to make sure there is clustering on one side of the cutoff. 
B)  Run a RD model and see if the effect is statistically significant 
C)  Run a RD using other covariates as the dependent variable. 
D)  See if the results are the same using each cutoff separately.

Question 15

A key assumption for RD is that the error term does not jump at the point of discontinuity.

Accepted Answer

A) True 
 B)False

Question 16

Using polynomial models in RD can produce bumps at the cutoff that are larger than they should be.

Accepted Answer

A) True 
 B)False

Question 17

Which of the following is the reason polynomial RD models can be dangerous to use?

Accepted Answer

A)  There is no danger in using a polynomial model instead of a varying slopes model. 
B)  Polynomial models are sensitive and can produce bumps at the cutoff that are larger than they should be. 
C)  Polynomial models lead to further endogeneity when the error term is not continuous. 
D)  Polynomial models can produce multicollinearity. 
A)  There is no danger in using a polynomial model instead of a varying slopes model. 
B)  Polynomial models are sensitive and can produce bumps at the cutoff that are larger than they should be. 
C)  Polynomial models lead to further endogeneity when the error term is not continuous. 
D)  Polynomial models can produce multicollinearity.

Question 18

Provide the equation for a polynomial RD model and explain a potential drawback of using a polynomial model and how we can deal with such a drawback.

Accepted Answer

The answer of Provide the equation for a polynomial RD...

Question 19

Which of the following shows the varying slopes RD model?

Accepted Answer

A)  Yi = B0 + B1Ti + B2(X1i-
C)  + B3(X1i-
C)  Ti + ei 
B)  Yi = B0 + B1Ti + B2(X1i-
C)  + B3(X1i-
C)  Ti 2 + ei 
C)  Yi = B0 + B1Ti + B2(X1i-
C)  + B3(X1i-
C)  2 + ei 
D)  Yi = B0 + B1Ti + B2(X1i-
C)  + ei 
A)  Yi = B0 + B1Ti + B2(X1i-
C)  + B3(X1i-
C)  Ti + ei 
B)  Yi = B0 + B1Ti + B2(X1i-
C)  + B3(X1i-
C)  Ti 2 + ei 
C)  Yi = B0 + B1Ti + B2(X1i-
C)  + B3(X1i-
C)  2 + ei 
D)  Yi = B0 + B1Ti + B2(X1i-
C)  + ei

Question 20

The smaller the window we use around the RD cutoff, the less we have to worry about the functional form of the model.

Accepted Answer

A) True 
 B)False

Explain why we may choose to employ a varying slopes RD model instead of a linear RD model.

Show and explain why the correlation between the error term and T disappears when we control for the assignment variable.

We employ binned graphs in order to.

What is one of the limitations of using RD models in order to help make/shape policy decisions?

In order to diagnose if variables other than Y (dependent variable) jump at the cutoff, one must use which of the following equations:

Which one of the following is a key assumption in regression discontinuity models?

If the assignment variable is correlated with the error term, then a RD model will provide a biased estimate of the treatment effect.

What is the consequence of having an error term that jumps at cutoff in a RD model?

One of the drawbacks of narrowing the window/range of the assignment variable is:

One of the main problems faced by RD is the fact that the error can be discontinuous at the treatment threshold.

Consider a plot of a model of the form Y_i= B₀+B1T_i+ B2(X_1i-C) + e_i. Which of the following is true?

Please explain how to asses if other variables act differently at the point of discontinuity, and explain the consequence of other variables jumping at the point of discontinuity.

Describe the benefits and drawbacks of adjusting the window of an RD model.

Which of the following is a diagnostic test to assess the appropriateness of using a RD model?

A key assumption for RD is that the error term does not jump at the point of discontinuity.

Using polynomial models in RD can produce bumps at the cutoff that are larger than they should be.

Which of the following is the reason polynomial RD models can be dangerous to use?

Provide the equation for a polynomial RD model and explain a potential drawback of using a polynomial model and how we can deal with such a drawback.

Which of the following shows the varying slopes RD model?

The smaller the window we use around the RD cutoff, the less we have to worry about the functional form of the model.

The Quest for Causality

Stats in the Wild: Good Data Practices

Bivariate Ols: the Foundation of Econometric Analysis

Hypothesis Testing and Interval Estimation: Answering Research Questions

Multivariate Ols: Where the Action Is

Dummy Variables: Smarter Than You Think

Specifying Models

Using Fixed Effects to Fight Endogeneity in Panel Data and Difference-In-Difference Models

Instrumental Variables: Using Exogenous Variation to Fight Endogeneity

Experiments: Dealing With Real-World Challenges

Dummy Dependent Variables

Time Series: Dealing With Stickiness Over Time

Advanced Ols

Advanced Panel Data

Filters

Exam 11: Regression Discontinuity: Looking for Jumps in Data

Explain why we may choose to employ a varying slopes RD model instead of a linear RD model.

Show and explain why the correlation between the error term and T disappears when we control for the assignment variable.

We employ binned graphs in order to.

What is one of the limitations of using RD models in order to help make/shape policy decisions?

In order to diagnose if variables other than Y (dependent variable) jump at the cutoff, one must use which of the following equations:

Which one of the following is a key assumption in regression discontinuity models?

If the assignment variable is correlated with the error term, then a RD model will provide a biased estimate of the treatment effect.

What is the consequence of having an error term that jumps at cutoff in a RD model?

One of the drawbacks of narrowing the window/range of the assignment variable is:

One of the main problems faced by RD is the fact that the error can be discontinuous at the treatment threshold.

Consider a plot of a model of the form Yi = B0 +B1Ti + B2(X1i-C) + ei. Which of the following is true?

Please explain how to asses if other variables act differently at the point of discontinuity, and explain the consequence of other variables jumping at the point of discontinuity.

Describe the benefits and drawbacks of adjusting the window of an RD model.

Which of the following is a diagnostic test to assess the appropriateness of using a RD model?

A key assumption for RD is that the error term does not jump at the point of discontinuity.

Using polynomial models in RD can produce bumps at the cutoff that are larger than they should be.

Which of the following is the reason polynomial RD models can be dangerous to use?

Provide the equation for a polynomial RD model and explain a potential drawback of using a polynomial model and how we can deal with such a drawback.

Which of the following shows the varying slopes RD model?

The smaller the window we use around the RD cutoff, the less we have to worry about the functional form of the model.

The Quest for Causality

Stats in the Wild: Good Data Practices

Bivariate Ols: the Foundation of Econometric Analysis

Hypothesis Testing and Interval Estimation: Answering Research Questions

Multivariate Ols: Where the Action Is

Dummy Variables: Smarter Than You Think

Specifying Models

Using Fixed Effects to Fight Endogeneity in Panel Data and Difference-In-Difference Models

Instrumental Variables: Using Exogenous Variation to Fight Endogeneity

Experiments: Dealing With Real-World Challenges

Dummy Dependent Variables

Time Series: Dealing With Stickiness Over Time

Advanced Ols

Advanced Panel Data

Filters

Consider a plot of a model of the form Y_i= B₀+B1T_i+ B2(X_1i-C) + e_i. Which of the following is true?