Heteroskedasticity in Stock Returns

G. William Schwert

University of Rochester, Rochester, NY 14627
and National Bureau of Economic Research

Paul J. Seguin

Analytic Focus LLC

Journal of Finance, 45 (September 1990) 1129-1155

We use predictions of aggregate stock return variances to estimate time-varying monthly variances for size-ranked portfolios. We propose and test a single factor model of heteroskedasticity for portfolio returns. This model implies time-varying betas. Implications of heteroskedasticity and time-varying betas for tests of the Capital Asset Pricing Model (CAPM) are then documented. Accounting for heteroskedasticity increases the evidence that risk-adjusted returns are related to firm size. Further, a constant correlation model is proposed and tested. Disaggregate volatilities predicted by this model are similar to those predicted by more complex multivariate generalized-autoregressive-conditional-heteroskedasticity (GARCH) procedures.

Key words: Heteroskedasticity, Generalized least squares, Beta, Capital asset pricing model, Stock returns, Size effect

JEL Classifications: G12, G31

Cited 179 times in the SSCI and SCOPUS through 2019
© Copyright 1990, American Finance Association
A full-text version of this paper, including tables and figures, is available in Acrobat's portable data format (.pdf).

Click here to download the reprint of the heteroskedasticity paper.

Click here to download a lower quality (and smaller file size) reprint of the heteroskedasticity paper.

Return to Publications Page

© Copyright 1998-2021, G. William Schwert

Last Updated on 6/10/2021