Take Part in the Process of Being Skeptical of Data
Instructor: Rui ‘Ray’ Yang (杨锐), Ph.D.
Description
Researchers in business schools often conduct observational studies by collecting second-hand, non-experimental data from third-party reports, APIs, websites, etc. However, simply fitting a regression model to “someone else’s data” is likely to generate biased estimates and arrives at wrong conclusions. Although various popular methods (such as IV, DID, RDD, FE, matching, etc.) have been developed to identify a causal effect, the implementation processes behind published papers are often hidden from the readers. This seminar will introduce doctoral students to R programming by showing what the popular methods do to the data with hands-on coding practices. As an open-source software, R opens the door for researchers to easily crack the code of peers’ work and produce replicable research. In contrast to closed-source software, in which developers offer a “black box” solution and make it difficult for users to examine what is under the hood, R’s source code is freely available for users to study (to learn the methodology by themselves), customize, and re-distribute. This seminar is designed for pre-comp and pre-dissertation doctoral students who seek to analyze archival data in their research.
Session I: 10:00~11:30, Thur. 29th, April 2021
Zoom ID: 62132159592
Password: 495706
Link: https://zoom.com.cn/j/62132159592
Session II: 10:00~11:30, Thur. 6th, May 2021
Zoom ID: 63430976733
Password: 215804
Link: https://zoom.com.cn/j/63430976733