Please complete before the next class.

Make sure that you’ve completed all previous HW first.


Causal Inference

Read and review your notes and my slides over causality and causal inference. Answer the following questions:

  1. Describe the four ways to obtain a correlation.
  2. Describe the other, fifth way you can get a correlation (i.e., by tricking yourself).
  3. I write that, under randomization, \(R^{obs}_T - R^{obs}_C \approx R^{hyp}_T - R^{hyp}_C\).
    1. What do each of these four quantities refer to? What do we call the left-hand side? The right-hand side?
    2. Notice that the equality is not exact. Instead, it is approximate. What is the only reason it is not exact.
    3. Explain why randomization allows us to rule out spuriousness and reverse causation.
    4. Describe the design of Gerber and Green’s turnout experiment. Describe the results (i.e., what percent of each group voted?). Discuss whether and how you can rule out any of the four possible ways to obtain a correlation.
  4. Was Gerber, Green, and Larimer’s study ethical?

FPP

Read chs. 1 and 2 of FPP (the textbook; see the syllabus) and do the assigned review exercises here. (Note: You only need to do the review exercises for chs. 1 and 2—do not do them all. We’ll get to the rest over the course of the semester. And yes, there is a reason I include this note.)


Creative Commons License
Carlisle Rainey