Time-varying Group Unobserved Heterogeneity in Finance
UNIVERSITY OF TECHNOLOGY SYDNEY
Finance Department
Research Seminars in Finance
Topic: Time-varying Group Unobserved Heterogeneity in Finance
Speaker: Wing Wah Tham, University of NSW
Abstract: Accounting for time-varying unobserved heterogeneity poses a fundamental challenge for all empirical finance research. This paper discusses the limitations of two widely-used approaches to model unobserved heterogeneity in finance: two-way fixed effect (TFE) and interacted fixed effect models (IFE). We show how TFE and IFE models can provide inconsistent (biased) estimates and can affect statistical inference in many empirical finance settings. To overcome the bias, we propose the use of the “group fixed effect, GFE” class of models, which produce consistent estimates under unobserved group heterogeneity and even under the two-way fixed effect and interacted fixed effect data generating processes. We study the finite sample properties of GFE through simulations and demonstrate its economic importance through an empirical application. We also extend the GFE class of models to accommodate two-stage least squares estimators (central to empirical finance research) and propose a Hausman-type specification test for model evaluation. Finally, we provide researchers with guidance and user-written functions in statistical packages to overcome the limitations of existing approaches.
Moderator: Ester Felez Vinas, University of Technology Sydney
Date: Wednesday, 9th September 2020
Time: 12-1 p.m. (Australian Eastern Standard Time)
Venue: This is on online Zoom webinar.
Seminar protocols:
- The webinar will run for 45 minutes, followed by a 15 minute Q&A session.
- There will be a moderator for each seminar event, who will facilitate communication and resolve any technical issues.
- Participants can use the Q&A facility to ask questions during the presentation. The moderator will then alert the speaker and ask the questions raised.
Co-ordinator: Harry Scheule
Enquiries: Duncan Ford