Tarun Chordia, Amit Goyal, and Jay Shanken
-Are expected returns related to
– Risk/betas, OR
– Characteristics
-If both, which is more important?
-Use portfolios
-Helps mitigate EIV problem
–Fama and MacBeth (1973)
-But,
–Less efficient Ang, Liu, and Schwarz (2010)
–Method of grouping is important Lewellen, Nagel, and Shanken (2010)
-Use individual securities
-But, EIV problem
-Use individual securities
-Correct for EIV bias
-Litzenberger and Ramaswamy (1979), Shanken (1992), Kim (1995)
-Allow betas to change over time
-Two year rolling regressions
-Quantify contribution of betas vs characteristics in explaining the cross-section of returns
-All common stocks on NYSE, AMEX, and NASDAQ
-Sample: July 1963 to December 2013
-Price greater than $1 (for CSR)
-Sample of all stocks and non-microcap stocks (>20% NYSE percentile)
-Monthly average of over 3000 stocks with about 1500 non-microcap stocks
-Fama-French (2014) five factor model plus Momentum
-Mkt, SMB, HML, RMW, CMA
-Characteristics include size, B/M, past six month return (exclude last month), operating profitability and investment
-Assumed to be available 6 months after fiscal year-end
-Winsorized at the 99th and 1st percentiles
-Reject all factor models
-Rejection not news
-Characteristics more important than betas
-Risk premiums
-Negative on SMB
-Positive on RMW and CMA
-No premium on HML or MOM
-Less robust positive premium on Mkt