Measurement of Abnormal Returns From Small Firms
通过修正异方差性，降低了小公司股票组合的市场风险估计，提高了异常收益估计，并发现了6个月和12个月的周期性，为小公司效应提供了更强证据。
Abstract Correction for heteroscedasticity in returns from portfolios long in small firms and short in large firms listed on the New York Stock Exchange reduces the estimate of market risk and increases the estimated abnormal return. Greatly improved diagnostic test statistics are obtained, strengthening the evidence for the existence of positive average abnormal returns from small firms. Periodicity of order 6 and 12 months is identified. The estimation procedure operates by exploiting the autoregressive pattern of heteroscedasticity in the return data. KEY WORDS: Autoregressive heteroscedasticityPeriodicityRisk estimation