RIEB Seminar
Three Lectures on Useful Concepts and Tools in Econometrics
(Jointly supported by RIEB Seminar / Rokko Forum / Kobe University Organization for Advanced and Integrated Research / Kobe University Center for Social Systems Innovation / Grant-in-Aid for Scientific Research (A))
Three Lectures on Useful Concepts and Tools in Econometrics
Jointly supported by RIEB Seminar / Rokko Forum / Kobe University Organization for Advanced and Integrated Research / Kobe University Center for Social Systems Innovation / Grant-in-Aid for Scientific Research (A)
| Lecturer | Keunkwan RYU (Department of Economics, Seoul National University, Korea) |
|---|---|
| Date & Time | Wednesday, Dec. 11, 2019, 3:10pm-4:40pm Thursday, Dec. 12, 2019, 1:30pm-4:40pm |
| Place | Meeting Room at RIEB (Annex, 2nd Floor) |
| Intended Audience | Faculties, Graduate Students, Undergraduates, and People with Equivalent Knowledge |
| Language | English |
| Remarks | *Booking required to attend the seminar. (Max.40 attendants) *Please contact to the Office of Promoting Research Collaboration, RIEB at "kenjo@rieb.kobe-u.ac.jp" with your name and affiliation. * Flyer [PDF, 104KB] |
| These lectures are designed to review what econometrics is all about from a different perspective, and to introduce useful tools in econometrics. These lectures would be useful for those students and/or researchers who are planning to write an empirically-oriented papers on applied issues. |
|---|
Wednesday, Dec. 11, 2019, 3:10pm-4:40pm
- Lecture I
- Overview of Econometrics
- Topic
- Statistical inference: Classical vs. Bayesian approaches (Hypothesis testing vs. Model selection, Objective oriented inferences, Lindley's paradox)
Classification: Direct vs. Indirect, Simple vs. Detailed
Thursday, Dec. 12, 2019, 1:30pm-3:00pm
- Lecture II
- Direct Classification
- Topic
- Conditional independence assumption (CIA), matching vs. multiple regression, propensity score matching (PSM), difference in differences (DinD)
Thursday, Dec. 12, 2019, 3:10pm-4:40pm
- Lecture III
- Indirect Classification
- Topic
- Observables vs. unobservables, instrumental variables (IV), treatment heterogeneity and LATE, regression discontinuity (RD)
- Other Issues
- Complementarity in size between data and model (small vs. big data, small vs. big model, XOR problem and deep neural network model, classification and regression trees (CART)