BUSN5000 HW 9 Part A

pdf

School

Northwestern University *

*We aren’t endorsed by this school

Course

5000

Subject

Statistics

Date

Feb 20, 2024

Type

pdf

Pages

6

Uploaded by arushic12

Report
11/13/23, 11 : 29 PM Assignment 9: Difference in Differences Page 1 of 6 https://chris-cornwell.shinyapps.io/Assignment9/#section-a-short-answer A: Short Answer Simple DD Question 1: The standard The standard DD analysis compares the di ! erence in DD analysis compares the di ! erence in average outcomes for the _____ observations _____ and _____ average outcomes for the _____ observations _____ and _____ treatment with the di ! erence in mean outcomes for the treatment with the di ! erence in mean outcomes for the controls _____ and _____ treatment. controls _____ and _____ treatment. treated, before, after, before, after Correct! Question 2: A DD analysis targets the average treatment e ! ect on the _____ A DD analysis targets the average treatment e ! ect on the _____ or or . treated, 1 Correct! Question 3: The target estimand cannot be estimated directly because The target estimand cannot be estimated directly because is _____. is _____. unobserved Correct! Question 4: The key identifying assumption in a DD analysis is that the The key identifying assumption in a DD analysis is that the treated and untreated outcomes would follow _____ trends in treated and untreated outcomes would follow _____ trends in the _____ of the treatment. the _____ of the treatment. parallel, absence Correct! 2 × 2 E ( - = _____) y 1 i y 0 i D i E ( = 1) y 0 i D i Assignment Assignment 9: 9: Difference Difference in in Differences Differences A: Short Answer (https://chris- cornwell.shinyapps.io/Assignment9/#section- a-short- answer) Part B: Empirical Analysis Submission Start Over
11/13/23, 11 : 29 PM Assignment 9: Difference in Differences Page 2 of 6 https://chris-cornwell.shinyapps.io/Assignment9/#section-a-short-answer Question 5: A simple before vs a " er comparison of treated observations A simple before vs a " er comparison of treated observations misses _____ that are shared by the control group. misses _____ that are shared by the control group. trends Correct! Question 6: A simple comparison of treated vs control observations a " er A simple comparison of treated vs control observations a " er treatment misses factors that cause non-random _____ into treatment misses factors that cause non-random _____ into treatment. treatment. selection Correct! Question 7: Use the code chunk below to construct a table of DD estimands for the case (i.e., pre/post expected outcomes for treated and untreated groups). Table 1 Table 1 2 × 2 R Code ! Start Over Run Code Submit Answer Fantastic! Correct! Estimands Estimands Group Before (t=0) After (t=1) Group Before (t=0) After (t=1) Treated (g=1) E(y_0|g=1, t=0) E(y_1|g=1, t Treated (g=1) E(y_0|g=1, t=0) E(y_1|g=1, t =1) =1) Untreated (g=0) E(y_0|g=0, t=0) E(y_1|g=0, t Untreated (g=0) E(y_0|g=0, t=0) E(y_1|g=0, t =1) =1) as.table(matrix(c("E(y_0|g=1, t=0)", "E(y_1 "E(y_0|g=0, t=0)", "E(y_1 nrow=2, byrow=TRUE, dimnames=list(Group = c("Treated (g=1)", " Estimands = c("Before (t=0)", "After (t=1) 1 2 3 4 5
11/13/23, 11 : 29 PM Assignment 9: Difference in Differences Page 3 of 6 https://chris-cornwell.shinyapps.io/Assignment9/#section-a-short-answer Use the code chunk below to construct a table of DD estimands for the case (i.e., pre/post expected outcomes for treated and untreated groups). The table below maps the DD estimands to parameters that capture di ! erences between groups and changes over time. Use the table to answer the remaining questions in this section. Table 2 Table 2 Question 8: The parameter The parameter reflects the average di ! erence between _____ reflects the average di ! erence between _____ and _____ outcomes. and _____ outcomes. treated, untreated Correct! Question 9: The parameter The parameter reflects the average di ! erence in outcomes reflects the average di ! erence in outcomes _____ and _____ treatment for the _____ group. _____ and _____ treatment for the _____ group. before, after, untreated Correct! Question 10: The parameter The parameter also reflects the _____ average di ! erence in also reflects the _____ average di ! erence in outcomes between periods 0 and 1 for the _____. outcomes between periods 0 and 1 for the _____. counterfactual, treated Correct! Question 11: 2 × 2
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
11/13/23, 11 : 29 PM Assignment 9: Difference in Differences Page 4 of 6 https://chris-cornwell.shinyapps.io/Assignment9/#section-a-short-answer If If varied by group, the _____ assumption would not hold. varied by group, the _____ assumption would not hold. parallel trends Correct! Question 12: The parameter The parameter represents the _____. represents the _____. ATT Correct! Continue Regression DD Question 13: The standard The standard DD analysis can be carried out by regressing DD analysis can be carried out by regressing the outcome on a _____ dummy, a period _____, and their the outcome on a _____ dummy, a period _____, and their _____. _____. group, dummy, interaction Correct! Question 14: A formal expression of the DD regression consistent with Table A formal expression of the DD regression consistent with Table 2 is: 2 is: Correct! Question 15: 2 × 2 y = + treat + after + u y = + treat + after + treat after + treat + after + treat after + u y = + treat + after + treat after + u
11/13/23, 11 : 29 PM Assignment 9: Difference in Differences Page 5 of 6 https://chris-cornwell.shinyapps.io/Assignment9/#section-a-short-answer A regression formulation of a DD design is appealing because it A regression formulation of a DD design is appealing because it Correct! Question 16: We described a TWFE model as a regression model for data with We described a TWFE model as a regression model for data with both a _____ and _____ dimension. both a _____ and _____ dimension. group, time Correct! Question 17: Estimating a TWFE model with data on multiple groups and Estimating a TWFE model with data on multiple groups and variation in treatment timing can identify the ATT if the variation in treatment timing can identify the ATT if the treatment e ! ect is _____ . treatment e ! ect is _____ . homogenous Correct! Question 18: Computing the correct standard errors for TWFE estimates Computing the correct standard errors for TWFE estimates usually requires _____ at the group level to account for _____ usually requires _____ at the group level to account for _____ and _____ correlation. and _____ correlation. clustering, heteroscedasticity, serial Correct! Continue facilitates standard error estimation generalizes for multiple time periods and treatment groups accommodates covariates all of the above
11/13/23, 11 : 29 PM Assignment 9: Difference in Differences Page 6 of 6 https://chris-cornwell.shinyapps.io/Assignment9/#section-a-short-answer Next Topic
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help