The Journal of Financial and Quantitative Analysis

In this paper some effects of nonstationary parameters upon inferences and decisions in portfolio analysis are investigated. A Bayesian inferential model with nonstationary parameters is presented and is applied to the problem of portfolio choice. For this model, nonstationarity 1) implies greater uncertainty about future returns; 2) implies that in forecasting future returns, recent returns should receive more weight than not-so-recent returns; 3) restricts the amount of information that can be obtained about future values of the parameters of interest; 4) shifts investment among risky securities and from risky securities to risk-free securities; and 5) yields optimal portfolios with smaller expected returns than corresponding optimal portfolios in the stationary case.

I. Introduction: Neoclassical theory and the evolutionary alternative, 90, — II. A specific evolutionary model, 93. — III. Calibration of the model, 98. — IV. Simulation results, 102. — V. Conclusion, 116.