CHDV 30102 Introduction to Causal Inference
(Cross-listed as MACS 51000, PBHS 43201, PLSC 30102, SOCI 30315, STAT 31900) Winter 2022
Instructors: Teaching Assistants: Lecture:
Office hours:
Copyright By PowCoder代写 加微信 powcoder
Objectives
Wednesdays Fridays
1:30 – 4:20 pm (1155 289B) 1:30 – 2:50 pm (1155 289B)
10:30 – 11:50 pm (NORC 249, 1155 East 60th St.) or by ZOOM by appointment.
This course is designed for graduate students and advanced undergraduate students from the social sciences, education, public health sciences, public policy, social service administration, and statistics who are involved in quantitative research and are interested in studying causality. The goal of this course is to equip students with basic knowledge of and analytic skills in causal inference. Topics include the following: the potential outcomes framework for defining causal effects; identification assumptions required for identifying causal effects in experimental and observational studies; propensity score based methods including matching, stratification, inverse- probability-of-treatment-weighting (IPTW), marginal mean weighting through stratification (MMWS), and doubly robust estimation; The course also introduces econometric methods including the instrumental variable (IV) method; difference in differences (DID) and generalized DID methods for cross-sectional and panel data; and regression discontinuity design (RDD). The course also covers the use of propensity-score method for the decomposition analysis of inequality. Intermediate Statistics or equivalent such as STAT 224/PBHS 324, PP 31301, BUS 41100, or SOC 30005 is a prerequisite. Students are expected to be familiar with multiple regression and have had exposure to generalized linear models. This course is a pre-requisite for “Mediation, moderation, and spillover effects,” taught by Professor Guanglei Hong.
Instructional Format
In each class, the instructors will provide an overview and will guide through the key statistical concepts and procedures, illustrating with application examples. The instructors will pose questions in class to lead discussions and examine student understanding of the materials. Students are expected to preview the readings for the week before class and review the content afterwards.
The required weekly labs are designed to review the concepts and procedures and provide tutorials for the assignments. In addition, students may use Piazza on Canvas to post questions or join discussions ideally the day before a lab or two days before an assignment is due (by 5 PM).
Students are encouraged to form study groups, while the written assignments are to be completed and graded on an individual basis.
Course Requirement
– Two written assignments
o Unit I. Propensity score-based methods (30% Grad; 50% Undergrad)
o Unit II. Econometric methods (30% Grad; 50% Undergrad)
o Assignments are due in two weeks after they are given.
– Final project (40%) —not required for undergraduate students
A 10~20 page write-up of your project, double-spaced, with two options:
1. A research proposal: elaborate a plan for studying a real-world problem of one’s
choice by employing three different causal inference methods; discuss major strengths and theoretical and practical concerns with each method in the context of the application.
2. A research paper: apply a causal inference method to a real-world problem and analyze the data of one’s choice.
A one-page tentative plan on the final project will be due in Week 7.
Round-table small group discussion and feedback in Week 9 (Wednesday and Friday). The final-project paper is due on Friday of the exam week (March 18th).
Late Submission Policy: All written assignments must be submitted as email attachments to and In addition to your answers to the exercise assignment, attach the STATA syntax, or the syntax of other software, which was used to obtain the answers. With the exceptions of personal or family emergencies, a late submission of an assignment will incur a penalty: An n-day delay will cause an n × 10% reduction in the grade for the assignment in question.
Statistical Software
Although students should feel free to use any software that they feel comfortable with for the written assignments, the statistical software for instruction in the lab will be StataSE15. We will show in the first lab session how to remotely access the software on the University server from your desktop or laptop computer.
To purchase a full version of Stata for Windows from the University of Chicago IT services, go to the following web site or visit the campus computer store: https://itservices.uchicago.edu/services/licensing/
Required Readings
The required readings are listed on the following pages for each week’s class and can be downloaded from Canvas. Most of these are journal articles; many have become classics and a “must-read” in the field of causal inference. These are supplemented by a number of chapters from the following book (available at the University of Chicago bookstore):
Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. West Sussex, UK: & Sons, Ltd.
E-book Link in the University of Chicago Library catalogue:
http://search.ebscohost.com.proxy.uchicago.edu/login.aspx?direct=true&scope=site&db=nlebk& db=nlabk&AN=1014315
Optional Reference Books:
. Imbens and . Rubin. (2015). Causal inference for statistics, social, and biomedical sciences. : Cambridge University Press.
. Morgan and . (2007). Counterfactuals and causal inference: Methods and principles for social research. Cambridge: Cambridge University Press.
. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge: Cambridge University Press.
Weekly Schedule
Unit I. Causal Inference Theories and Applications
Week 1. Potential Outcomes, Counterfactual Definition of Causality, and the (January 12th)
1. Taubes, G. (September 16, 2007). Do we really know what makes us healthy? The
Times magazine.
2. Holland, P. (1986). “Statistics and causal inference (with comments)”, Journal of the
American Statistical Association, 81(396), 945-960.
3. Rubin, D. B. (1986). “Statistics and causal inference: Comment: Which ifs have causal
answers,” Journal of the American Statistical Association, 81(396), 961-962.
4. Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. Chapter 2 “Review of causal inference concepts and methods.”
Section 2.1 “Causal inference theory,” pp.18-27.
Section 2.2.1 “Lord’s paradox”
5. Pearl, Judea. (2014). Lord’s Paradox Revisited. (Oh, ). UCLA Department of Computer Science Technical Report R-436 (downloadable in the web). Reading required only for section 1 “Lord’s original dilemma” and 2 “Interpretation,” in the first six pages.
6. Recommended: Imbens. G.W., and D.B. Rubin (2015). Causal Inference for Statistics, Social, and Biomedical Sciences. Chapter 1. “Causality: The Basic Framework,” pp. 1-22.
7. Recommended: Lord, F. M. (1967). A paradox in the interpretation of group comparisons. Psychological Bulletin, 68, 304-305.
8. Recommended: Lord, F. M. (1975). “Lord’s Paradox,” in S. B. Anderson et al., Encyclopedia of educational evaluation (pp. 232-236). San Francisco, CA: Jossey-Bass.
Week 2. Experimental Designs, Natural Experiments, Observational Studies, and Simpson’s Paradox (January 19th)
9. Rosenbaum, P. R. (1999). Choice as an alternative to control in observational studies (with comments). Statistical Science, 14(3), 259-278.
10. Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. Section 2.2.2 “Simpson’s paradox”
Section 2.3 “Identification and estimation,” pp.34-36.
11. Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. Chapter 3 “Review of causal inference designs and analytic methods.”
Section 3.1 “Experimental designs,” pp.40-44;
Section 3.2 “Quasiexperimental designs,” pp.44-45 (leave subsection 3.2.2 for later);
Section 3.3 “Statistical adjustment methods,” pp.46-51 (leave subsection 3.3.3 for later).
Unit II. Propensity Score-Based Methods Week 3. Propensity Score Matching and Stratification (January 26th )
12. Rubin, D. B. (1997). Estimating causal effects from large data sets using propensity score. Annuals of Internal Medicine, 127, 757-763.
13. Stuart, E.A. (2010). Matching Methods for Causal Inference: A review and a look forward. Statistical Science, 25(1), 1-21.
14. Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. Chapter 3 “Review of causal inference designs and analytic methods.”
Section 3.4 “Propensity score,” pp.55-69.
15. Recommended. Rosenbaum, P.R. and Rubin, D.B. (1984). “Reducing Bias in Observational Studies Using Sub-classification on Propensity Scores.” Journal of the American Statistical Association 79: 516-24.
Week 4. Inverse-Probability-of-Treatment Weighting (IPTW) and Marginal Mean Weighting through Stratification (MMWS) (February 2nd )
16. Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. Chapter 4 “Adjustment for selection bias through weighting,” pp.76-99.
17. Hong, G. (2015). Causality in a social world: Moderation, mediation and spill-over. Chapter 5 “Evaluations of multivalued treatments,” pp.100-123.
The first assignment will be given. It will be due in two weeks.
Week 5: Some extensions of the Propensity-score Methods (February 9th)
18. Imbens G.W. (2000) “The Role of the Propensity-Score in Estimating Dose-Response Functions.” Biometrika 87:706-710.
19 . Recommended: Yamaguchi, K. 2019. Gender Inequality in the Japanese Workplace and Employment, Chapter 5 “Impacts of Companies Work-Life Balance and the Restrictive Regular Employment System on Gender Wage Gap”. Springer:
Unit III. Econometric and Related Methods Week 6. The Instrumental Variable (IV) Method (February 16th )
6 20. Angrist, J. D., Imbens, G. W., & Rubin, D. B. (1996). Identification of causal effects using
instrumental variables. Journal of the American Statistical Association, 91(434), 444-472.
21. Krueger, A. B., & Whitmore, D. M. (2001). The effect of attending a small class in the early
22. Altonji, J. G., Elder, T. E., & Taber, C. R. (2005). An evaluation of instrumental variable strategies for estimating the effects of Catholic schooling. Journal of Human Resources, XL(4), 791-821.
23. Recommended. Heckman, J.J. (1997) Instrumental Variables: A Study of Implicit Behavioral Assumptions Used in Making Program Evaluations. Journal of Human Resources 32: 441-62.
Week 7. Difference-in-Differences Estimation and Its generalization by Propensity-Score Method (February 23th )
24. Meyer, B. D., Viscusi, W. K., & Durbin, D. L. (1995). Workers’ compensation and injury duration: Evidence from a natural experiment. The American Economic Review, 85(3), 322-340.
25. Abadie. A. (2005). Semi-parametric Difference-in-Differences Estimators. Review of Economic Studies, 72: 1-19.
26. Gentzkow, M. (2006). Television and voter turnout. The Quarterly Journal of Economics, 121(3), 931-972.
(The second assignment will be given and it is due in two weeks (March 9th)
Week 8-1. Regression Discontinuity Design (March 2nd )
27. Oreopoulos, P. (2006). Estimating average and local average treatment effects of education when compulsory schooling laws really matter. The American Economic Review, 96(1), 152-175.
28. Ludwig, J., & Miller, D. L. (2007). Does Head Start improve children’s outcomes? Evidence from a regression discontinuity design. Quarterly Journal of Economics, 122, 159-208.
29. Lee, D. S., & Lemieux, T. (2010). Regression discontinuity designs in economics. Journal of Economic Literature, 48(2), 281-355.
30. Recommended. Ito, Koichiro and Sallee, . Forthcoming. The Economics of Attribute-Based Regulation. Evidence from Fuel-Economy Standards. Review of Economics and Statistics.
Week 8-2. Decomposition method based on IPTW (March 2nd )
7 31. DiNardo, J., Fortin, N., & Lemieux (1996). Labor Market Institution and the Distribution of
Wages. Econometrica 64: 1001-44.
32. Yamaguchi, K. (2017). Decomposition Analysis of Segregation. Sociological Methodology
47: 246-273.
33. Recommended: Yamaguchi, K. 2019. Gender Inequality in the Japanese Workplace and Employment. Chapter 3 “Determinants of Gender Gap in the Proportion of Managers amomg White-Collar Regular Workers.”
Week 9: Round-table discussions (about 5 people for each group). (March 9th and 11th )
Instructors: & Won Choi Location: TBA
Every student must bring to class a handout that presents essential information about his or her final project. The class will be divided into small groups for round table discussions. It is planned that four of the groups will meet with the instructors on Wednesday March 9th at one of two different time slots; and four will meet on Friday March 11th at one of two different time slots, but the schedule may slightly change depending on the number of students.
Note: Students are strongly encouraged to seek individual consultation from the instructors during their office hours prior to the round table discussions.
Final written assignment due Wednesday, March 18 by 11:59 PM.
Students who plan to graduate by the end of the Winter Quarter should notify both instructors via email in Week 8 and should submit the final written assignment on or before Friday, March 11 by 11:59 PM.
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com