Discontinuity Design for a Merit Scholarship
This example illustrates a discontinuity design using a merit-based scholarship. Imagine a scholarship is awarded to students who score 900 or more on a 1,000-point exam. To determine the scholarship's causal effect, we can compare students who scored just above this threshold to those who scored just below it. For instance, a student with a score of 902 receives the scholarship (the treatment group), while a student with 898 does not (the control group). The key assumption is that these two students have virtually the same underlying ability. By comparing their outcomes, we can isolate the impact of the scholarship itself, as the sharp cut-off at 900 creates the 'discontinuity' for the study.
0
1
Tags
Library Science
Economics
Economy
Social Science
Empirical Science
Science
CORE Econ
Introduction to Microeconomics Course
Ch.5 The rules of the game: Who gets what and why - The Economy 2.0 Microeconomics @ CORE Econ
Related
Discontinuity Design for a Merit Scholarship
Historians have proposed different frameworks to explain the historical wealth disparity between the West and other regions. Match each specific argument below to the explanatory framework it best represents.
A researcher wants to evaluate the impact of a new government program that provides extra funding to schools where the student poverty rate is above 40%. To do this, the researcher compares the academic outcomes of a school with a 75% poverty rate (which received funding) to a school with a 15% poverty rate (which did not). The researcher concludes the funding was ineffective because academic outcomes were not significantly different. What is the primary methodological flaw in this researcher's approach?
Designing a Study for a Financial Aid Program
Evaluating a Tutoring Program
Evaluating a Tutoring Program
A city implements a new policy to provide free public transit passes to all residents whose annual household income is below $30,000. A researcher evaluates the policy's impact on employment rates by comparing the employment outcomes of residents with incomes between $29,000 and $29,999 (who received the pass) to those with incomes between $30,000 and $30,999 (who did not). Which of the following scenarios represents the most significant threat to the validity of this study's design?
A city implements a new policy to provide free public transit passes to all residents whose annual household income is below $30,000. A researcher evaluates the policy's impact on employment rates by comparing the employment outcomes of residents with incomes between $29,000 and $29,999 (who received the pass) to those with incomes between $30,000 and $30,999 (who did not). Which of the following scenarios represents the most significant threat to the validity of this study's design?
A city wants to study the effect of a new small business grant on local employment. The grant is awarded to all businesses located on streets with a 'walkability score' of 75 or higher. To measure the grant's impact, researchers compare the change in employment for businesses on streets with scores between 75-77 (who received the grant) to businesses on streets with scores between 73-74 (who did not). For this study's conclusion about the grant's effect to be valid, which of the following must be the most critical assumption?
Evaluating a Free Tuition Policy
A research team wants to determine the causal effect of a specific intervention. In which of the following scenarios would a discontinuity analysis be the most appropriate and valid research method?
Discontinuity Design for a Merit Scholarship
A researcher conducts a study to measure the impact of joining a competitive debate team on students' final grades in their government class. The study finds that students who voluntarily joined the debate team had significantly higher final grades than students who did not. The researcher concludes that participation in debate directly causes academic improvement in government class. Which statement best analyzes the primary flaw in this conclusion?
Analyzing a Workplace Study
Evaluating a Tutoring Program Study
Evaluating a Music Program's Impact
A study observes that towns with a higher number of firefighters per capita also tend to have more property damage from fires. Based on this strong positive correlation, the most logical conclusion is that having more firefighters on staff leads to an increase in fire-related property damage.
Each 'Study Finding' below describes a correlation between two variables that might be mistaken for a direct causal link. Match each finding to the most likely 'Hidden Factor' that explains the relationship.
A study observes that individuals who regularly attend the gym have a lower incidence of a specific chronic illness compared to those who do not. However, it's possible that people who choose to go to the gym are also more likely to have healthier diets, and this dietary difference could be the real reason for their better health outcomes. In this analysis, the 'healthier diet' is an example of a(n) ___________ variable, making it difficult to determine the true health benefit of gym attendance alone.
Analyzing a City's Crime Reduction Program
Evaluating a Corporate Training Program
A study finds that children who own high-end, technologically advanced bicycles tend to have higher scores on standardized science tests. The researchers conclude that interacting with the complex mechanics and materials of these bicycles stimulates an interest and aptitude for science. What is the most likely confounding variable that challenges this conclusion?
Learn After
A university implements a mandatory academic support program for students who score below 50 on a 100-point placement test. To evaluate the program's effectiveness, researchers compare the final course grades of students who scored 49 (and entered the program) with those who scored 50 (and did not). Which of the following potential issues represents the most significant threat to the validity of the conclusion that the program caused any observed difference in grades?
Evaluating a Customer Loyalty Program
Evaluating Scholarship Effectiveness
The Logic of Discontinuity Design
A researcher is evaluating a scholarship program where students with a GPA of 3.5 or higher are eligible to apply. To measure the scholarship's impact, the researcher compares the post-graduation salaries of students with a 3.51 GPA who successfully applied and received the scholarship to the salaries of students with a 3.49 GPA who were ineligible. Based on the principles of using a sharp cutoff to establish causality, any observed salary difference between these two groups can be confidently attributed solely to the effect of receiving the scholarship.
A research study aims to measure the impact of a free financial literacy course. The course is automatically offered to all individuals with a credit score of 620 or lower. To assess the course's effectiveness, analysts compare the financial health of individuals just below this score to those just above it one year later. Match each component of the study design to its correct description in this scenario.
A study is designed to measure the impact of a new tutoring program offered to students with a GPA below 2.5. To ensure the comparison between students just above and just below the 2.5 GPA threshold is valid, the most critical assumption is that students cannot precisely ________ their GPA in order to gain or avoid access to the program.
A research team wants to evaluate the causal impact of a new, intensive math tutoring program. The program is automatically assigned to all high school students who score below 600 on a standardized math assessment. Arrange the following steps in the correct logical order for conducting a study based on this sharp cutoff.
Critiquing a Small Business Grant Study
A city wants to evaluate the impact of a new summer reading program on students' vocabulary. The program is offered for free to all students who score less than 70 (out of 100) on a standardized pre-test. Two methods are proposed to measure the program's effect:
Method 1: Compare the average vocabulary of all students who participated (pre-test score < 70) with the average vocabulary of all students who did not (pre-test score ≥ 70).
Method 2: Compare the average vocabulary of students who scored just below 70 (e.g., 68-69) with the average vocabulary of students who scored just above 70 (e.g., 70-71).
Which method provides a more reliable estimate of the program's true causal effect, and why?