Prof. G. William Schwert
Secretary: Kathleen Madsen, CS1-102 or CS3-110M, 585-275-8187
Also, determining the right decision is only the beginning of a process. A sound factual basis for the decision is a major part of getting it implemented, but the effectiveness of this will be much enhanced if it is communicated well. Thus, another facet of the class is the effective communication of your argument in favor of a decision. Therefore, in class discussions, assignments, exams, and on the project, there will be a premium for avoidance of unnecessary terminology and effective managerial-style presentation.
One warning -- statistical analysis is no substitute for thinking. It can help to clarify, to sort out which of a number of plausible arguments best fits the facts, and so on. But it cannot tell you what the relevant things to think about are, or obviate the need for experience and good judgment.
APS 425 is a lot of work and very cumulative. This is the wrong course to get behind in. This is going to be a hard course, but the reason for this is that you are going to learn a lot. There is little point to coming to the School for years and not leaving a lot different than you arrived!
At the same time I can assure you that there is nothing really deep in this course. It is a course that responds well to effort.
It is a good idea to keep this in mind because about two thirds of the way through the class a lot of you will be feeling pretty anxious. We will have covered a lot of ground, and by that stage it may not have "come together." But I can tell you that if you keep at it, once you have cranked through the assignments and done your project, it will come together.
To reiterate, this is a hard course, but it is material that is worth learning, and you will learn it if you try.
All of the cases and the project are group assignments. I have a separate memo that describes my approach to grading group assignments, but I think it is worthwhile to share a few thoughts about the optimal way to participate in group work. If you have been involved in study groups that are diversified in terms of background and academic specializations in the past you may have noticed a tendency for the group to assign primary responsibility for a particular assignment to the person with the comparative advantage at completing the task. While this may result in the highest grade for the assignment, and it may involve the least aggregate amount of work for the members of the group, it is the WORST model for learning the material in the course. Usually, the members of the group glance through the memo, and perhaps help with editing the draft, but are not deeply involved in producing the analysis underlying the memo.
Instead, I recommend that all members of the group attempt to complete the analysis (including computer work) and meet to compare and contrast their proposed solutions to the problem. Only after a thorough discussion of the alternative approaches should the group reach a consensus on the final product. In this way, everyone learns to perform the analysis, and the process of reaching consensus teaches everyone how to do the analysis as well as how to communicate about it. Perhaps this maximizes the group effort, but it also maximizes the learning that occurs (and hence the benefit from participating in the course).
Since all exams are individual, not group, assignments, I strongly encourage every student to actively participate in the group work. In this way each of you will be prepared to respond to the challenges of the individual assignments. In the longer run, you will be able to produce valuable work on your own after you have left Simon and your class teammates (and me).
Every Simon Business School student is expected to be completely honest in all academic matters. Simon students will not in any way misrepresent their academic work or attempt to advance their academic position through fraudulent or unauthorized means. No Simon student will be involved knowingly with another student's violation of this standard of honest behavior.
Please refer to the Student Handbook for any questions regarding the Code of Academic Integrity.
Since I have now been teaching this course for quite a few years, there may be some graded assignments that are similar in some ways to assignments that have been given in the past. It is a violation of the Simon Code of Academic Integrity to use material from any prior offering of APS 425 to aid in the completion of any graded assignment. A proven violation of the Code can lead to a failing grade on an assignment or project, course failure, suspension and/or dismissal from the program.
There will be several homework assignments that are group responsibilities. Homework grades will count 20% of your final grade. Also, there will be a major project due on 12/1/2015 that is also a group assignment worth 20% of your course grade. The project report should be less than 2,000 words (about 10 double-spaced pages) describing your analysis of an interesting dataset. You may include well-documented tables and figures as appendices as long as they are referred to in the report. The report should be written as if you were giving it to your boss (who took a regression course many years ago, but does not use it in his everyday work). Thus, you should not rely on statistical jargon to explain your analysis, but you should also not spend time explaining regression to him (i.e., me). You should start early in the quarter to plan and begin work on your project - last minute efforts are likely to produce poor results.
When you turn in your project (12/1/2015), each group will turn in their grade-allocation sheet containing:
Wooldridge, Jeffrey M. Introductory Econometrics, 5th ed., 2013, South-Western, ISBN: 9781111531041 (henceforth JW) [Also available as an Ebook at a lower price]
The recommended text for this course is:
Francis X. Diebold, Forecasting in Economics, Business, Finance and Beyond, (available for free in PDF).
I will generally not lecture from these books. Rather, I think of them as references.
In addition, I will use Eviews for all of my lectures, answer sheets, etc. Moreover, the exams will require you to analyze data that are provided in Eviews datasets. Therefore, you need to buy and use Eviews to succeed in this course. Since the University of Rochester has a site license, you can purchase a full version of the software for $95 online
The Eviews Users Guide, Part 1, and Part II (henceforth EV) contain some useful discussion that relates the topics we will discuss in class to the options available in Eviews.
I. Review of Multiple Regression
JW, Chaps. 1-4
JW, Chap. 19 (read early - advice on how to write an empirical paper)
EV, Part V, Chap. 19, pp. 5-22; Chap. 24, pp. 163-176
JW, Chap. 6.2-6.3 (pp. 191-207)
[epidural data; wine price data]
JW, Chap. 7.1-7.4 (pp. 227-248), Chap. 9.1 (pp. 303-308), Chap. 9.5 (pp. 324-331)
EV, Part V, Chap. 19, pp. 22; Chap. 20, pp. 28-32; Chap. 23, pp. 170-179
EV, Part II, Chap. 11, pp. 374-376
JW, Chap. 6.4 (pp. 207-215)
EV, Part IV, Chap. 23, pp. 135-148
II. Heteroskedasticity (non-constant variance of the errors)
EV, Part IV, Chap. 20, pp. 32-40; Chap. 24, p. 182
III. Analysis of Categorical Data
JW, Chap. 7.5-7.7 (pp. 249-257) , Chap. 8.5 (pp. 294-296), Chap. 17.1 (pp. 583-596)
EV, Part VI, Chap. 28, pp. 297-316 (some techniques that are beyond the scope of this course)
[epidural data] IV. Analysis of Time Series Data
EV, Part V, Chap. 22, pp. 87-134 (some techniques that are beyond the scope of this course)
JW, Chap. 10.5 (pp. 363-373)
FD, Chap. 6
*Nelson, Charles R. and H. Kang, "Pitfalls in the Use of Time as an Explanatory Variable in Regression," Journal of Business and Economic Statistics, 2 (1984) 73-82.
Cowden, Dudley J., "The Perils of Polynomials", Management Science, (July 1963) 542-550.
FD, Chap. 7
FD, Chaps. 8, 9
*Nelson, Charles R., "The Interpretation
of R2 in Autoregressive-Moving Average Time Series Models,"
The American Statistician, 30 (1976) 175-180.
[Stock price and inflation data]
EV, Part VII, Chap. 36, pp. 527- 539
Plosser, Charles R. and G. William Schwert, "Estimation of a Noninvertible Moving Average Process: The Case of Overdifferencing", Journal of Econometrics, (September 1977) 199-224.
Schwert, G. William, "Effects of Model Specification on Tests for Unit Roots in Macroeconomic Data," Journal of Monetary Economics, 20 (1987) 73-103.
JW, Chapter 11.3 (pp. 388-396), Chap. 12, Chap. 18
EV, Part VIII, Chap. 38, pp. 623-649
*Nelson, Charles R. and G. William Schwert, "On Testing the Hypothesis That the Real Rate of Interest Is Constant," American Economic Review, 67 (1977) 478-486.
Fama, Eugene F., "Short Term Interest Rates as Predictors of Inflation", American Economic Review, (June 1975) 269-282.
Plosser, Charles I. and G. William Schwert, "Money, Income and Sunspots: Measuring Economic Relationships and the Effects of Differencing," Journal of Monetary Economics, 4 (1978) 637-660.
Engle, Robert F. and C. W. J. Granger, "Co-Integration and Error Correction: Representation, Estimation, and Testing," Econometrica, 55 (1987) 251-276.Novy-Marx, Robert, "Predicting Anomaly Performance with Politics, the Weather, Global Warming, Sunspots, and the Stars." Journal of Financial Economics, 112 (2014) 137-146.
[Stock price and inflation data]
EV, Part VI, Chap. 25
FD, Chaps. 10
*Hentschel, Ludger, "All in the Family: Nesting Symmetric and Asymmetric GARCH Models," Journal of Financial Economics, 39 (1995) 71-104.
Schwert, G. William, "Why Does Stock Market Volatility Change Over Time?" Journal of Finance, 44 (December 1989) 1115-1153.
French, Kenneth R., G. William Schwert, and Robert F. Stambaugh, "Expected
Stock Returns and Volatility," Journal of Financial Economics, 19
(September 1987) 3-29.
If you want the current version of the Adobe Acrobat Reader for other platforms, visit Adobe's web page by clicking the image below.
Click here to download
the full text of this course outline.