DEPARTMENT...... : Accounting and Finance (CFC)
PROGRAM................ : School of Methods
COURSE.................... : Econometrics for Finance
PROFESSOR............. : Rafael F. Schiozer
DAY/HOUR............... : Wednesdays, 8:00-11:40 AM
2nd semester / 2018
OBJECTIVES AND CONTENTS
This course provides students with working knowledge of econometrical methods for finance research, with a focus on causal identification. This is accomplished by covering several methods commonly employed in empirical research in business and finance. The course is more directed to end users of econometric tools, teaching students how to properly use the tools, and less focused on deriving econometric properties. The course does not cover time series econometrics.
I expect that students will be better prepared to do (especially empirical) research in corporate finance and banking topics after taking this course. I also expect students to develop their critical thinking and learn to make academic presentations in a professional manner, which is fundamental to researchers.
Non-finance students are welcome to this course. I think students from other areas can benefit from taking this course. Even though most of the applications and readings are finance-related, the tools you will learn can be used in virtually any area.
Limitations: Time limitations impose certain restrictions on what we can accomplish in this course. For example, we will not cover all of the methods you might need or should know. We also will not cover each method in excruciating detail. Arguably, you could build an entire course around each method.
FORMAT
We will conduct the course in Portuguese, but most required readings are in English.
The course is designed to help you learn econometric methods via a three-pronged approach.
(1) Lectures and econometric readings will help you with the econometric intuition behind each method. This is not a theory course; this is a course for end users of econometric tools.
(2) Course readings will expose you to examples of the methods being used in published and working papers. Seeing how the tools are actually used by other researchers is often far more useful in helping students understand the tools. I will mostly rely on examples from Finance, though I may also reference examples from other fields.
(3) Course assignments will require you to use the methods analyzed in the course. There will be 2 exercises. You will have to manipulate and analyze data using the various econometric techniques. Our working software will be Stata. The applications will be finance-related. In addition, there will be assignments where you analyze and criticize other researchers’ use of these tools.
ASSESSMENT CRITERIA
Presentation / discussion of papers: 15%
Half-page handouts: 10%
Stata exercises: 20%
Quizzes: 20%
Final Exam: 35%
REQUIRED BACKGROUND
The course does not have any formal pre-requisites. However, I expect you to have good knowledge of Statistics and undergraduate-level Econometrics. I will assume that you have a good working knowledge on:
- Hypothesis testing;
- Notions of single and multiple regression analysis; (knowledge of panel data econometrics may be useful, but is not mandatory)
If you are not familiar with these concepts, I highly recommend that you study on your own and/or take an online course in Statistics previously to taking this course. A very good one is a course by Prof. Philip Stark, available here: http://www.stat.berkeley.edu/~stark/SticiGui/index.htm
Your knowledge in Corporate Finance is also helpful, but not mandatory.
COURSE SCHEDULE AND READING LIST
I will teach from slides, which I will make available to you before each class on Eclass. I will be drawing from a variety of sources including various textbooks, journal articles, working papers, and other professors’ lecture notes.
There is no single required “textbook,” but I will mostly follow the sequence of Angrist & Pischke’s book (Wooldridge’s book provides the theoretical background if you are interested in econometric theory). I make note of the appropriate references for each lecture on the exhibit below, where I show the relevant methodology readings for each lecture. Students are expected to read these prior to the lecture.
Additionally, most lectures will contain student presentations of papers related to the previous week’s lecture topic. A list of papers to be presented is given below.
Each session will cover 2 or 3 papers. All the students must read all the papers for each session. I will form the groups *, and assign each group their paper in the week ahead. One student will present the discussions prepared by his/her group**. Each group will make a ~15 minute PowerPoint presentation that discusses the paper, and each presentation will be followed by in-class discussion. The purpose of the assignment is twofold: (1) Presentations are one key way people in academia will come to know (and assess) you. So, it’s a good idea to get some practice now. And (2), this will help you think critically about the papers. To ensure participation following each presentation, each group must also type up one concern they had about each of the papers their group did NOT present and hand these in at the start of class (I call these half-page handouts). Your group will state this concern at the start of the discussion. The comments should be very short [2-3 sentences] and designed to do one of two things: (a) isolate what your group thought the biggest problem of the paper was, or (b) identify a concern you think the presenting group might overlook.
* The number of students per group will depend on the number of students enrolled for the course.
** I may cold call students to answer a specific question about the paper. If the answer is poor, this will damage the grade for the whole group. This is done to reduce moral hazard and avoid someone from the group to free-ride.
Guidelines for a good discussion (you do not have to strictly follow this order, but it may help you in preparing your presentation):
- Briefly describe what the paper does and what it finds;
- Make your point about the assumptions and/or identification strategy;
- Suggest improvements;
- Identify eventual gaps or defects. Be critical. You may use your own judgement or the literature that followed in the subject. In this case, make explicit mention to the papers you are referring to.
- Try not to be too picky about minor defects. Try to find fundamental flaws in the identification strategy and/or in the interpretation of the results.
The first meeting will be lecture-only. From the 2nd meeting on, we will have approximately 2 hours of lecture followed by a 15 minute break and around 1h15min of presentations and discussion.Two of our sessions will start with 30 minute quizzes (see below).
Books and methodological papers
Mandatory readings:
Angrist, Joshua D., and Jorn-Steffen Pischke, 2009, Mostly Harmless Econometrics, Princeton University Press, New Jersey. [AP]
Roberts, Michael R., and Toni M. Whited, 2011, “Endogeneity in Empirical Corporate Finance,” Handbook of the Economics of Finance, vol. 2, http://ssrn.com/abstract=1748604 [R&W]
Bertrand, M., E. Duflo, and S. Mullainathan. 2004. How Much Should We Trust Differences-in Differences Estimates? Quarterly Journal of Economics 119:249–75. [B,D&M]
Gormley, Todd A., and David A. Matsa, 2014, “Common Errors: How to (and Not to) Control for Unobserved Heterogeneity,” Review of Financial Studies, 2014.
Non-mandatory readings:
Wooldridge, Jeffrey M., 2010, Econometric Analysis of Cross-Section and Panel Data, MIT Press, Massachusetts, Second Edition [W]
Course schedule
|
Session |
Date |
Topics |
Readings |
Paper Presentations [PP] and assignments due |
|
1 |
10/Oct [WED] |
Quick review: OLS Estimation and Inference; Hypothesis testing; Statistical Properties of Regressions;
Causality |
AP – 3.1.; AP – 3.2; R&W paper, section 2 W – Chapters 2, 3 and 4 |
|
|
2 |
17/Oct [WED] |
Causality (cont.)
Quick review: panel data
QUIZ #1 |
AP – 3.4; 3.5.; 5.1; 5.3 W – 10.1; 10.2; 10.3;10.5; 10.6; 10.7 |
[PP] Classics |
|
3 |
24/Oct [WED] |
Other uses of fixed effects
Instrumental variables (intr.)
|
Lecture Notes
AP – 4.1; 4.4; 4.6. W – Chapter 5. R&W paper, section 3 |
[PP] Causality |
|
4 |
26/Oct* [FRI] |
Instrumental variables (cont.)
Natural Experiments |
AP – 5.2 |
[PP] Other uses of FE and Instrumental variables #1 Assignment #1 |
|
5 |
7/Nov [WED] |
Natural Experiments (cont.) |
B,D&M Paper R&W paper, section 4 |
[PP] Instrumental variables #2 and Natural experiments #1 |
|
6 |
14/Nov [WED] |
Common mistakes and erros
Non-standard standard errors
QUIZ #2 |
G&M paper
AP 8.1; 8.2 |
[PP] Natural experiments #2 |
|
7 |
21/Nov [WED] |
Non-linear regression models;
Other techniques (very brief): matching and RDD |
W – 13.1; 13.2; 13.3; 15.1-15.6; 15-8
AP 6.1; 6.2 |
[PP] Common mistakes |
|
8 |
28/Nov [WED] |
FINAL EXAM |
|
|
|
- |
29/Nov [THU] |
Last assignment due (at midnight) |
|
Assignment #2 |
*Session #4 is exceptionally on Friday
All classes are from 8:00AM to 11:40 AM. The final exam is form 9:00 AM to 11:30AM.
Papers to be presented (all the students must read all the papers, one student will present each paper)
Classics #1
Berger, P., and Eli Ofek, 1995, “Diversification’s Effect on Firm Value,” Journal of Financial Economics 37, 39−65.
Bates, Thomas W.; Kathleen M. Kahle, Rene M. Stulz; Why do US Firms Hold So Much More Cash than They Used to?, Journal of Finance, Volume 64, Issue 5, 2009.
Opler, Timothy, Larry Pinkowitz, and Rene Stulz, 1999, “The determinants and implications of corporate cash holdings,” Journal of Financial Economics 14, 1059-1082.
Causality
Rajan, Raghuram G., and Luigi Zingales, 1998, “Financial dependence and growth,”American Economic Review, 88(3), 559-586.
Becker, Bo, Zoran Ivkovic, and Scott Weisbenner, 2011, “Local dividend clienteles,” Journal of Finance, 66(2), 655-683.
La Porta, Rafael, Florencio Lopez-de-Silanes, Andrei Shleifer, and Robert Vishny, 1998, “Law and finance,” Journal of Political Economy 106, 1113-1155.
Other uses of fixed effects
Khwaja, Asim Ijaz, and Atif Mian, 2008, “Tracing the Impact of Bank Liquidity Shocks: Evidence from an Emerging Market,” American Economic Review, 98(4), 1413-1442.
Gormley, T., Nandini Gupta, and Anand Jha, Quiet life no more? Corporate bankruptcy and bank competition, Journal of Financial and Quantitative Analysis, pp. 581-611, 2018.
Instrumental Variables#1
Duchin, R., Gilbert, T., Harford, J., & Hrdlicka, C., (2017). Precautionary Savings with Risky Assets: When Cash is Not Cash. The Journal of Finance, Vol. 72(2), pp. 793-852.
Instrumental Variables#2
Paravisini, D. “Local Bank Financial Constraints and Firm Access to External Finance”, Journal of Finance, 63(5): 2161-2193, 2008.
Natural Experiments #1
Bertrand, Marianne, and Sendhil Mullainathan, 2003 “Enjoying the quiet life? Corporate governance and managerial preferences,” Journal of Political Economy, 111(5), 1043-75.
Jayaratne, Jith, and Philip Strahan, 1996, “The finance-growth nexus evidence from bank branch deregulation,” Quarterly Journal of Economics, 111(3), 639-670.
Natural Experiments #2
Gropp, Reint, Thomas Mosk, Steven Ongena and Carlo Wix, Forthcoming, Bank response to higher capital requirements: Evidence from a quasi-natural experiment, Review of Financial Studies.
Qian, Jun, Strahan, P., and Zhishu Yang, The impact of incentives and communication costs on information production and use: evidence from bank lending, Journal of Finance, 2015.
Fisman, R., Paravisini, D. and Vig, V. “Cultural Proximity and Loan Outcomes”, American Economic Review, 2017
Common Limitations & Errors
Giroud, Xavier, and Holger Mueller, 2010, “Does corporate governance matter in competitive industries?” Journal of Financial Economics, 95, 312-331.
Ljungqvist, Alexander, Christopher Malloy, and Felicia Marston, 2009, “Rewriting history,” Journal of Finance, 64(4), 1935-1960.
Bennedsen, Morten, Francisco Perez-Gonzalez, and Daniel Wolfenzon, 2012, “Evaluating the Impact of the Boss: Evidence from CEO Hospitalization Events”, working paper, http://www.stanford.edu/~fperezg/valueboss.pdf
