Predicting Stock Returns on the Basis of Financial and Market Variables

Abstract:     
The article develops a statistical model for predicting stock returns on the basis of financial and market variables. The article employs Bayesian probabilities under independent variables assumption as statistical methodology. The resulting model yields average excess return of 3.2 percent per month over Russell 3000 index. Another attractive quality of the model is its parsimony: only five variables. The resulting model has the potential to be of practical use in predicting stock returns by both institutional and individual investors.

Number of Pages in PDF File: 8

Keywords: stock returns, financial ratios, stock market, alpha, market inefficiency

JEL Classification: C50, C51, C52, C53

working papers series