Stock Price Predictions with Accounting Information
Posted: 14 Jul 1997
Date Written: March 1997
FOR PAPER OR ELECTRONIC COPIES CONTACT: Pam Reinhart, 430 Fincher, Cox School of Business, Southern Methodist University, Dallas, TX 75275. Phone: (214) 768-3275. E-mail: MAILTO:firstname.lastname@example.orgIn this paper, we discuss a framework for approaching the problem of how best to estimate stock price given a set of accounting information. We apply the theory of inverse probability to formulate price predictions based on an estimate of the mean of the posterior distribution for price, given the information that the accounting process provides. The implications of incorporating into our framework alternative assumptions about accounting measurement error and the unconditional price distribution are discussed. An empirical methodology and statistical tests for evaluating prediction performance are also described. Finally, we present a limited set of empirical results that shed light on the functional form of a pricing model based on accounting earnings and book value. The form of our most refined model is consistent with recent empirical evidence that has identified convexity in the relationship between price and accounting information.
JEL Classification: M41, G12
Suggested Citation: Suggested Citation