Type of Credit: Required
Credit(s)
Number of Students
This course is prepared for Master and Ph.D. students intending to conduct economics analysis using statistical tools (e.g. R, STATA).
能力項目說明
There are three purposes for this course. The first is to provide an introduction of National Health Insurance Data (NHID). The second is to provide an introduction of modern econometrics techniques on the cross-section and panel data, including difference-in-difference (DID), instrumental variable method (IV), Propensity Score Matching Method (PSM) and regression discontinuity method (RD). Finally, we show how these methods can be implemented using STATA (http://www.stata.com), a program for statistics, graphics, and data management
| 教學週次Course Week | 彈性補充教學週次Flexible Supplemental Instruction Week | 彈性補充教學類別Flexible Supplemental Instruction Type |
|---|---|---|
The first half of this course is to introduce NHID, and use STATA to select, clean, organize, and describe the data. The second part employs a research example to discusses some of modern techniques in the fields of micro-econometrics, including DID, IV and RD.
∙ Introduction of National Health Insurance Data
- NHID sample file
∙ Managing the data
- Convert raw data into STATA format data
- Describe the data
- Groups and subgroups the data
- Changing the data
- Data cleaning
- Summarize the data
- Combine the data
∙ Regression Analysis
- Lien Hsien-Ming, Shin-Yi Chou, and Jin-Tan Liu (2008) "Hospital Ownership and Performance: Evidence from Stroke and Cardiac Treatment in Taiwan," Journal of Health Economics 27:5, pp. 1208-1223
- Multiple Regression I (SW 6): Omitted variable bias, Multiple regression model.
- Assessing Regression Studies (SW 9): Internal and external validity, Threats to internal validity.
- Panel Data (SW 10): Fixed effects regression, Random effects regression.
∙ Questions and Experiments
- Experiments and Quasi-Experiments (SW 13):Quasi-experiments, Average treatment effect.
- MHE, Chapters 1 and 2
- DID (difference-in-difference) estimator.
∙ Difference in Difference Estimator
- NBER Summer Institute: Lecture Notes of Applied Econometrics on DID
- MHE, Chapters 5 and 8
∙ Instrumental Variables Method
- Instrumental Variables Regression (SW 12): General IV regression model, Checking instrument validity, Where do IV come from?
- Instrumental Variable Models with heterogeneous potential outcomes (MHE Chapters 4.4-4.5)
- NBER Summer Institute: Lecture Notes of Applied Econometrics on Instrumental Variables with Treatment Effect Heterogeneity: Local Average Treatment Effects
∙ Propensity Score Matching Method
- Rubin, D. B., 1977, "Assignment to a Treatment Group on the Basis of a Covariate," Journal of Educational Statistics [1], Spring 1977 1-26.
- Rubin, D. B., 1974, "Estimating Causal Effects of Treatments in Randomized and Nonrandomized Studies," Journal of Educational Psychology, 66, 688-701.
- NBER Summer Institute: Lecture Notes of Applied Econometrics on Matching Estimator
∙ Regression Discontinuity Method
- MHE, Chapters 6
- NBER Summer Institute: Lecture Notes of Regression Discontinuity Designs
There will be 4-5 quizzes that students are expected to work independently. There will be a final report which students are expected to work in groups; the details will be decided in the first class. Grading will be as follows:
Quizzes 40%
Report 60%.
There is no textbook for this course; however, the following three books are helpful for understanding the backgrounds of health systems of the United States and Taiwan.
∙ Christopher F. Baum, An Introduction to Modern Econometrics Using Stata, Stata Press (2006)
∙ J.M. Stock, H. H. and M. W. Watson, Introduction to Econometrics, 2nd Edition. Pearson/Addison Wesley 2007 (SW).
∙ J.D. Angrist and J.S. Pischke, Mostly Harmless Econometrics: An Empiricist's Companion, Princeton University Press, 2008.
www3.nccu.edu.tw/~hmlien