- Consider Column (2) of table VI. Set up an econometric model corresponding to this specification and explain the different parts of the econometric model. Pay particular attention to interpreting the coefficients and the error term (residual). What assumptions will you make about the error term?
- Explain and interpret all the numbers and stars in this Column
- Why do they find different coefficients on News in Columns (1) and (2)?
- Consider in particular the estimated effect of news coverage on disaster relief found in Columns (1) and (2). Why may this not be a good estimate of the causal effect of news coverage? How does this show up in the econometric model you presented in question 1?
- In Columns (6)-(8) Eisensee and Str?mberg use instrumental variables. Explain what this is, why they use it, and what assumptions has to be made for the instrument to be valid.
- The instrument for news coverage is whether there were Olympic games going on at the same time as the disaster struck. Discuss whether this is a valid instrument for news coverage of the disaster.
- Compare the findings in Columns (1) and (2) to those in (6) and (7) and discuss.
- Why is Table IV relevant for judging the validity of the instrument employed in the paper?
Seminar 1 (Sept 6, 2013): Review of some econometric concepts
We base this review on Thomas Eisensee and David Str?mberg 's paper News Droughts, News Floods, and U. S. Disaster Relief, where they study where natural disasters have the larges destructive effect, and what determined disaster relief. You do not need to read the whole paper in detail, but you should have some clue about what the authors attempt to do.
You may also benefit from looking through the overview of econometrics before the seminar as well as this article by Henning Finseraas and Andreas Kotsadam (in Norwegian)
Published Aug. 22, 2013 2:58 PM