Peer Group Beta Reliability under Thin Trading Conditions: Results from a Simulated Environment in the Standard, Mean-Reversion and, Bayesian Framework.

63 Pages Posted: 22 Mar 2021

Date Written: February 17, 2021

Abstract

Finance literature has proposed numerous techniques in order to eradicate the effects of thin trading, ranging from (il-)liquidity indicators indicating distortions in beta estimates to beta correction procedures directly correcting them in the traditional market model. This study exam-ines the superiority of comprehensive sets of 16 popular (il-)liquidity indicators and 10 popular beta correction procedures among themselves as well as against each other according to bias (effi-ciency) and accuracy (predictive ability) in the standard framework. Furthermore, the analysis is duplicated for the mean-reversion and the Bayesian framework, thus relaxing the assumption of beta stationarity. The results indicate (i) the (il-)liquidity indicators to generally outperform the beta correction procedures in small as well as in large stock markets, across different levels of thin trad-ing, across different levels of risk (beta magnitudes) and, across all three market model frame-works, (ii) the Illiquidity (Amihud-Hasbrouck) Indicator and the Return-to-Turnover Indicator as well as the Trade-to-Trade Method to dominate in the standard and the mean-reversion frame-work, (iii) the Turnover Indicator as well as the Error Correction Model to dominate in the Bayesian framework and, (iv) the (il-)liquidity indicators to generate absolutely best indications on beta dis-tortions in the Bayesian framework as well as the beta correction procedures to generate absolute-ly best beta estimates in the standard framework.

Keywords: thin trading, liquidity indicators, beta correction procedures, peer group beta reliability

JEL Classification: G32

Suggested Citation

Grbenic, Stefan Otto, Peer Group Beta Reliability under Thin Trading Conditions: Results from a Simulated Environment in the Standard, Mean-Reversion and, Bayesian Framework. (February 17, 2021). Available at SSRN: https://ssrn.com/abstract=3787309. or http://dx.doi.org/10.2139/ssrn.3787309

Stefan Otto Grbenic (Contact Author)

Graz University of Technology ( email )

Rechbauerstra├če 12
Graz, 8010
Austria

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
56
Abstract Views
245
rank
507,041
PlumX Metrics