This week, we’re going to do something a little different. Rather than focus on calculations and programming exercises, we’re going to think about and discuss study design, measurement, and inference.

Discuss the following questions as a group. Professor Rao will visit each group to help clarify any questions you may have. Nominate a member of your group to communicate your thoughts/conclusions to the class as a whole when we reconvene.

Measuring discrimination

1. What data would you use to determine whether educational inequality was causing racial income inequality?
  1. What variables would you need? What would the unit of observation be?
  2. How would you measure whether educational inequality could explain all of the observed racial income inequality?
  3. What kinds of inferential challenges might you run into?
2. Researchers like Charette argue that housing segregation drives educational inequality. How would you construct a variable measuring the degree of racial housing segregation in a city? How about in a neighborhood?
  1. What variables would you need? What would the unit of observation be?
  2. What values does your new variable take? What are its units?
  3. Is it numerical or categorical? Continuous or discrete?
3. Suppose you were unable to run a randomized control trial to measure the effect of housing segregation on educational inequality. What data would you need to measure how much educational inequality is attributable to housing segregation over time?
  1. What variables would you need? What would the unit of observation be?
  2. How would you use that data to measure the causal effect of housing segregation on educational inequality?
  3. What challenges might you run into?