BUSN5000 HW 7 Part A

10/30/23, 7 : 33 PM Assignment 7: Potential Outcomes Page 1 of 6 https://chris-cornwell.shinyapps.io/Assignment7/#section-a-short-answer A: Short Answer Correlation vs causation? Question 1: True or false. If True or false. If , , does not depend on does not depend on . False Correct! Question 2: True or false. If True or false. If causes causes , the conditional distribution of , the conditional distribution of given given must depend on must depend on . True Correct! Question 3: In the above DAG, In the above DAG, is a _____. is a _____. confounding variable Correct! Continue Potential outcomes Question 4: corr( x , y ) = 0 y x x y y x x Z Assignment Assignment 7: Potential 7: Potential Outcomes Outcomes A: Short Answer (https://chris- cornwell.shinyapps.io/Assignment7/#section- a-short- answer) B: Empirical Analysis Submission Start Over

10/30/23, 7 : 33 PM Assignment 7: Potential Outcomes Page 2 of 6 https://chris-cornwell.shinyapps.io/Assignment7/#section-a-short-answer You can’t observe the e ! ect of a treatment on an individual You can’t observe the e ! ect of a treatment on an individual because you can’t observe the ______ outcome. In this sense, because you can’t observe the ______ outcome. In this sense, causal inference is a ______ data problem. causal inference is a ______ data problem. counterfactual, missing Correct! Question 5: While individual treatment e ! ects are not observable, you may While individual treatment e ! ects are not observable, you may be able to identify the average treatment e ! ect (ATE), which is be able to identify the average treatment e ! ect (ATE), which is the di ! erence in average ______ outcomes. the di ! erence in average ______ outcomes. potential Correct! Question 6: Using the di ! erence in sample average outcomes for treated Using the di ! erence in sample average outcomes for treated and untreated individuals generally won’t work for estimating and untreated individuals generally won’t work for estimating the ATE because potential outcomes are not ______ of the ATE because potential outcomes are not ______ of treatment assignment, which results in ______ bias. treatment assignment, which results in ______ bias. independent, selection Correct! Recall the “switching equation”, which expresses observed outcomes in terms of potential outcomes: Using the switching equation, the di ! erence in the population average outcomes for the treated and untreated cases can be written as = (1 - ) + = + ( - ) . y i D i y 0 i D i y 1 i y 0 i y 1 i y 0 i D i E ( = 1) - E ( = 0) y i D i y i D i = E ( = 1) - E ( = 1) y 1 i D i y 0 i D i TERM 1 + (1) E ( = 1) - E ( = 0) y 0 i D i y 0 i D i TERM 2

10/30/23, 7 : 33 PM Assignment 7: Potential Outcomes Page 4 of 6 https://chris-cornwell.shinyapps.io/Assignment7/#section-a-short-answer However, if the potential outcomes are ______ of treatment However, if the potential outcomes are ______ of treatment assignment, the assignment mechanism is ______ and the assignment, the assignment mechanism is ______ and the di ! erence in sample average outcomes for treated and di ! erence in sample average outcomes for treated and untreated individuals will identify the ATE. untreated individuals will identify the ATE. independent, ignorable Correct! Question 11: Potential outcomes will be ______ of treatment assignment if Potential outcomes will be ______ of treatment assignment if individuals are ______ assigned to treated and untreated individuals are ______ assigned to treated and untreated groups. groups. independent, randomly Correct! Question 12: The conditional independence assumption (CIA) is a claim that The conditional independence assumption (CIA) is a claim that there is a set of covariates that once you control for them, you there is a set of covariates that once you control for them, you can consider the potential outcomes to be ______ of treatment can consider the potential outcomes to be ______ of treatment assignment. The CIA is a claim of un______ and is un______. assignment. The CIA is a claim of un______ and is un______. independent, confoundedness, testable Correct! Question 13: To estimate the ATE under a CIA, you also need overlap, which To estimate the ATE under a CIA, you also need overlap, which is the ability to observe ______ and ______ units for any set of is the ability to observe ______ and ______ units for any set of covariate values. covariate values. treated, untreated Correct! Question 14:

10/30/23, 7 : 33 PM Assignment 7: Potential Outcomes Page 5 of 6 https://chris-cornwell.shinyapps.io/Assignment7/#section-a-short-answer If you have a set of control variables for which a CIA holds, you If you have a set of control variables for which a CIA holds, you can identify the average e ! ect of the treatment on the outcome can identify the average e ! ect of the treatment on the outcome using a ______ of the outcome on a ______ dummy and ______ using a ______ of the outcome on a ______ dummy and ______ . regression, treatment, control variables Correct! Question 15: As an alternative to the procedure sketched out in the previous As an alternative to the procedure sketched out in the previous question, by the Frisch-Waugh-Lovell theorem, you could question, by the Frisch-Waugh-Lovell theorem, you could simply run a regression of the outcome on the ______ from a simply run a regression of the outcome on the ______ from a regression of the treatment indicator on the controls. regression of the treatment indicator on the controls. residuals Correct! Continue Next Topic