Structural change and time dependence in models of stock returns

Abstract In this paper, we provide evidence that the time-series properties of stock returns include both structural change and time dependence in the conditional variance. The absence of a structural change component tends to overstate the persistence parameter in a time-dependent model specification. The reason is that time-dependent model specifications do not distinguish between positive residuals that increase volatility from those that represent a resolution of uncertainty. A sequential mixture of normal distributions model of structural change is employed to estimate discrete change points in the time-series of volatility in either direction. Although the model of structural change appears to be the more descriptive process in a mutually exclusive comparison, a joint model of time dependence and structural change is most likely.

[1]  Walter N. Torous,et al.  The Effect of Volatility Changes on the Level of Stock Prices and Subsequent Expected Returns , 1991 .

[2]  G. C. Tiao,et al.  Bayesian inference in statistical analysis , 1973 .

[3]  Robert A. Connolly.  An Examination of the Robustness of the Weekend Effect , 1989, Journal of Financial and Quantitative Analysis.

[4]  Daniel B. Nelson.  CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[5]  V. Akgiray.  Conditional Heteroscedasticity in Time Series of Stock Returns: Evidence and Forecasts , 1989 .

[6]  Robert F. Engle,et al.  Testing for Common Features: Reply , 1993 .

[7]  Adrian Pagan,et al.  Alternative Models for Conditional Stock Volatility , 1989 .

[8]  R. Chou.  Volatility persistence and stock valuations: Some empirical evidence using garch , 1988 .

[9]  Dongcheol Kim,et al.  Alternative Models for the Conditional Heteroscedasticity of Stock Returns , 1994 .

[10]  G. Box,et al.  On a measure of lack of fit in time series models , 1978 .

[11]  Stanley J. Kon.  Models of Stock Returns—A Comparison , 1984 .

[12]  R. Officer.  The Distribution of Stock Returns , 1972 .

[13]  T. Day,et al.  Stock market volatility and the information content of stock index options , 1992 .

[14]  J. Durbin,et al.  Techniques for Testing the Constancy of Regression Relationships Over Time , 1975 .

[15]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[16]  Russell P. Robins,et al.  Estimating Time Varying Risk Premia in the Term Structure: The Arch-M Model , 1987 .

[17]  B. Mandelbrot.  The Variation of Certain Speculative Prices , 1963 .

[18]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[19]  A. Christie,et al.  The stochastic behavior of common stock variances: value , 1982 .

[20]  G. Schwert,et al.  Heteroskedasticity in Stock Returns , 1989 .

[21]  T. Bollerslev,et al.  A CONDITIONALLY HETEROSKEDASTIC TIME SERIES MODEL FOR SPECULATIVE PRICES AND RATES OF RETURN , 1987 .

[22]  G. Schwert.  Why Does Stock Market Volatility Change Over Time? , 1988 .

[23]  Stanley J. Kon,et al.  Sequential parameter nonstationarity in stock market returns , 1996 .

[24]  Richard T. Baillie,et al.  Stock Returns and Volatility , 1990, Journal of Financial and Quantitative Analysis.

[25]  William Mendenhall,et al.  Introduction to Probability and Statistics , 1961, The Mathematical Gazette.

[26]  W. Beaver.  The Information Content Of Annual Earnings Announcements , 1968 .

[27]  Tim Bollerslev,et al.  Quasi-maximum likelihood estimation of dynamic models with time varying covariances , 1988 .

[28]  M. Degroot.  Optimal Statistical Decisions , 1970 .

[29]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[30]  J. Wooldridge,et al.  A Capital Asset Pricing Model with Time-Varying Covariances , 1988, Journal of Political Economy.

[31]  James N. Bodurtha,et al.  Testing the CAPM with Time-Varying Risks and Returns , 1991 .

[32]  K. French,et al.  Expected stock returns and volatility , 1987 .

[33]  R. Quandt.  The Estimation of the Parameters of a Linear Regression System Obeying Two Separate Regimes , 1958 .

[34]  R. Quandt.  Tests of the Hypothesis That a Linear Regression System Obeys Two Separate Regimes , 1960 .

[35]  David Lindley,et al.  Introduction to Probability and Statistics from a Bayesian Viewpoint , 1966 .

[36]  J. Patell,et al.  The Ex Ante And Ex Post Price Effects Of Quarterly Earnings Announcements Reflected In Option And Stock-Prices , 1981 .

[37]  L. Glosten,et al.  On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks , 1993 .

[38]  Andrew H. Chen,et al.  Investigations of Nonstationarity in Prices , 1974 .

[39]  Robert F. Engle,et al.  Testing for Common Features , 1993 .

[40]  R. Miller,et al.  On the Stable Paretian Behavior of Stock-Market Prices , 1974 .

[41]  John Y. Campbell,et al.  No News is Good News: An Asymmetric Model of Changing Volatility in Stock Returns , 1991 .

[42]  E. Fama.  The Behavior of Stock-Market Prices , 1965 .

[43]  Dongcheol Kim,et al.  A Bayesian Significance Test of the Stationarity of Regression Parameters , 1991 .

[44]  Christopher G. Lamoureux,et al.  Persistence in Variance, Structural Change, and the GARCH Model , 1990 .