Spring 2012
Final Exam Questions
Due by electronic submission: Noon, Thursday, May 10
Instructions
1. This part of the exam is open-book; you may use whatever outside materials you wish. However, you may not communicate with anyone except the instructor about the exam.
2. The exam is due electronically at noon on Thursday, May 10. There is no time limit, but you should not need to spend more than a few hours on it.
3. You are responsible for making sure that you understand each question clearly. In case of any ambiguity, be sure to consult the instructor.
4. When you discuss the estimated effects of one variable on another, but sure to consider both statistical significance and economic significance.
5. If you use Stata commands/options or statistical methods that have not been discussed in class, you should briefly describe what the command/test/method does and justify why it is appropriate to use. You should supplement your answers with supporting Stata output when it is useful.
Question #1
Read the paper "Evaluating the Impact of Changing Mississippi's Tobacco Tax," by Al Myles and Albert J. Allen. Suppose that you have been asked by the editor of a journal to review this paper for publication. Prepare a 1-2 page review of the econometric analysis in the paper. You should consider whether the analysis is appropriate for answering the question the authors pose, issues of internal and external validity arising from the analysis, and ultimately whether you find the authors' answer convincing.
Question #2
Read the paper "Why is U.S. Poverty Higher in Nonmetropolitan than Metropolitan Areas? Evidence from the Panel Study of Income Dynamics," by Monica Fisher. Perform the same analysis that you did for Question #1 for this paper.
Question #3
During the 1880s, a small number of railroad companies controlled rail shipping of grain between the Midwest and major eastern markets. At times these companies functioned as a cartel to restrict the supply of grain shipments by rail; at other times the cartel fell apart and grain shipping prices were determined more competitively. You are to estimate the price elasticity of the demand for rail shipment of grain using a dataset grain.dta.
The variables in the dataset are shown in the table below:
| Variable | Description |
| week | Sequence number for the weekly observations in the sample |
| price | Weekly index of price of shipping a ton of grain by rail |
| quantity | Total tonnage of grain shipped in the week |
| ice | Dummy variable indicating whether the Great Lakes were impassable to grain-carrying ships due to ice |
| cartel | Dummy variable indicating whether the railroad cartel was restricting supply |
| seas1-seas12 | Dummy variables for the period of the year, with each period being four weeks in length (seas13 for the last four weeks of the year is omitted |
You are to use appropriate econometric techniques to estimate the price elasticity of the demand for rail shipping of grain. The demand for rail shipping is likely to be seasonal and to be affected by the availability of water shipment via the Great Lakes as a substitute.
Describe your results and defend your choice of econometric method both in terms of what theory suggests using a few diagnostic tests if appropriate.
Do not spend 20 hours on this problem! Do not spend 10 hours on this problem! Choose a functional form that make estimation of the elasticity of interest convenient, consider the range of potential complicating issues posed by the dataset and question, decide how to deal with them, run the regressions, do a few obvious validation tests, and then tell me what you did and how it turned out. There is no magical pot of gold here that reveals itself to you only if you try 500 different models. Don't neglect obvious difficulties, but you don't need to go looking for problems in non-obvious places. In other words, resist the very-Reed-like practice of making this harder than it is intended to be!