南華大學2014財務金融與管理研討會

南華大學2014財務金融與管理研討會

Author: Jen-Chih Kuo (Department of Finance, Yuan Ze University)

Title: The influence of measurement errors in beta on estimation and testing in asset pricing

Keywords: errors-in-variables, asset pricing

Pages: 32 pages

Methodology: simulation.

Contribution: Even if CAPM is assumed true, the low power of rejecting the false null hypothesis, resulted from the EIV, could present the high probability to contradict the CAPM under some sample size and/or market conditions.

Main literature background: Shanken (1992) “On estimation of beta pricing models”, RFS 5, 1-34.

Shanken (1992) presents a formal econometric analysis of the two-pass methodology.

The estimation error in the first-pass betas impacts the asymptotic standard error of the second-pass risk premium estimator.

Kuo (2014) illustrates the contribution and validity of Shanken (1992).

Question: What are the merits and necessity of implementing SIMULATION instead of implementing empirical studies? Especially,

Kan, Robotti and Shanken (2013) “Pricing model performance and the two-pass cross-sectional regression methodology”, JF, 68(6), 2617-2649.

Examining eight prominent asset pricing models via US empirical data gathered from the websites of high-profile scholars, such as Fama and French, etc.

意見提供者：劉任昌 (德明財經科技大學財務金融系助理教授)