15 Exercise 4 (Problem Set 5)
- Due date: July 9th (Tue) 11pm.
- This is the last problem set!
15.1 Rules
- If you are enrolled in Japanese class (i.e., Wednesday 2nd), you can use both Japanese and English to write your answer.
- Submit your solution through
CourseN@vi
. - Important: Submission format
- If you use Rmarkdown, please compile your Rmarkdown file into either “html” or “PDF” file and submit both the compiled file and a Rmarkdown file.
- If you do not use Rmarkdown, please submit the document file that contains your answer and R script file (.R file) separately, that is, you submit two files.
15.2 Question 1: Hansford and Gomez (2010, APSR)
- This problem set is based on Thomas Hansford and Brad Gomez “Estimating the Electoral Effects of Voter Turnout” The American Political Science Review Vol. 104, No. 2 (May 2010), pp. 268-288
- Use the same dataset I introduced in the chapter for instrumental variable estimation.
15.3 Questions
- What is the research question of this paper? Provide a summary in one paragraph.
- What is the difficulty of the analysis? Provide a summary in one paragraph.
- What is the research design, i.e., how do authors overcome the issue? Provide a summary in one paragraph.
- Replicate the first three columns of Table A1 (1st stage regression in Table 1) to the best of your ability.
- Replicate Table 1 to the best of your ability.
- Briefly discuss the results from Table 1 in light of the first three hypotheses (Partisan Effect Hypothesis, Two-Effects Hypothesis, and Anti-Imcumbent Hypothesis).
Note
- Do not too much worry about the standard errors in the replication exercise. Focus on the replication of the point estimates.
- In Table A1, you do not have to replicate “F test (all covariates)” and “R2”.
- In Table 1, you do not have to replicate the last five rows (i.e., the row “F test, all covariates” and below. )
- Ignore a star
*
. Though this used to be convention, some journals recently started to require authors NOT to put any stars in regression tables. For a more discussion on this matter, see the followings:- Brodeur et al (2016) “Star Wars: The Empirics Strike Back” AEJ-Applied https://www.aeaweb.org/articles?id=10.1257/app.20150044
- AER Style Guide for Accepted Articles https://www.aeaweb.org/journals/aer/submissions/accepted-articles/styleguide