Abstract
The main purpose of this paper is to demonstrate a method to forecast stock price using analyst earnings forecasts as essential signals of firm valuation. The demonstrated method is based on the residual income model (RIM), with adjustment for autocorrelation. Over the past decade, the RIM has been widely accepted as a theoretical framework for equity valuation based on fundamental information from financial reports. This paper shows how to implement the RIM for forecasting and how to address autocorrelation to improve forecast accuracy. Overall, this paper provides a method to forecast stock price that blends fundamental data with mechanical analyses of past time series.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Many prior RIM papers use ex-dividend price equations, the results of which carry through to relate price at time t to equity book value at time t and discounted abnormal earnings starting at time t + 1. This paper’s Eq. 1 uses cum-dividend price and carries through to relate price at time t to equity book value at time t − 1 and discounted abnormal earnings at time t. This approach helps define abnormal earnings based on expected earnings of the contemporaneous period and therefore can aid the actual price forecast task. In other words, in linking price and contemporaneous abnormal earnings, this model parallels the forecaster’s decision in forecasting stock price at a certain point in period t (starting at t − 1 and ending at t), when her information consists of book value at the beginning of the year (bv t−1), and earnings forecasts of the current year (x t ).
Many studies often add the following information dynamics to the RIM regression:
$$ \begin{aligned} x_{t + 1}^{a} & = w\,x_{t}^{a} + v_{t} + \varepsilon_{1,t + 1} \\ v_{t} & = \rho v_{t - 1} + \varepsilon_{2,t} \\ \end{aligned} $$where ω is the coefficient representing the persistence of abnormal earnings. This information dynamics links other information in the current period to future excess earnings, not to current stock price. It focuses on abnormal earnings and the issue of earnings persistence, which is favorable for the task of forecasting earnings, and is a fruitful way to study the properties of future earnings. Statistically, this closed form serves to correct autocorrelation. But this focus creates an intermediate step for the task of forecasting stock price, because RIM regressions must estimate future abnormal earnings first before estimating stock price.
Scale differences arise when large (small) firms have large (small) values of many variables. If the magnitudes of the differences are unrelated to the research question, they result in biased regression coefficients. Lo and Lys (2000) show that scale differences are severe enough to lead to opposite coefficient signs in RIM models. Barth and Kallapur (1996) argue that scale differences are problematic regardless of whether the variables are deflated or expressed in per-share form.
I eventually find that both work equally well, consistent with the wisdom that sophisticated time series models are not superior to the simple AR(1) model. In fact, the received empirical literature is overwhelmingly dominated by AR(1), as it is optimistic to expect to know precisely the correct form of autocorrelation in any situation (Greene 2000).
According to the seminal study by Cochrane and Orcutt (1949), high correlations between autocorrelated series may be obtained purely by chance, and when this happens what is largely explained is the variance due to the regular movements through time.
There are theoretical and empirical issues in measuring net operating assets (see the discussions by Callen and Segal 2005). My computation of net operating assets follows the definition of Compustat Research Insight.
References
Barth M, Kallapur S (1996) The effects of cross-sectional scale differences on regression results in empirical accounting research. Contemp Account Res 13(Fall):527–567
Brown S, Lo K, Lys T (1999) Use of R-square in accounting research: measuring changes in value relevance over the last four decades. J Account Econ 28:83–115
Callen JL, Morel M (2001) Linear accounting valuation when abnormal earnings are AR (2). Rev Quant Financ Acc 16:191–203
Callen JL, Segal D (2005) Empirical tests of the Feltham-Ohlson (1995) Model. Rev Acc Stud 10:409–429
Choi Y, O’Hanlon JE, Pope P (2006) Conservative accounting and linear information valuation models. Contemp Account Res 23:73–101
Cochrane D, Orcutt GH (1949) Application of least squares regression to relationships containing auto-correlated error terms. J Am Stat Assoc 44:32–61
Courteau L, Kao J, Richardson GD (2001) Equity valuation employing the ideal versus Ad Hoc terminal value expressions. Contemp Account Res 18:625–661
Dechow PM, Hutton AP, Sloan RG (1999) An empirical assessment of the residual income valuation model. J Account Econ 26:1–34
Dopuch N, Seethamraju C, Xu W (2008) An empirical assessment of the premium associated with meeting or beating both time-series earnings expectations and analysts’ forecasts. Rev Quant Financ Acc 34:147–166
Feltham GA, Ohlson JA (1995) Valuation and clean surplus accounting for operating and financial activities. Contemp Account Res 11:689–731
Francis J, Olsson P, Dennis R (2000) Comparing the accuracy and explainability of dividend, free cash flow, and abnormal earnings equity value estimates. J Account Res 38((Spring)):45–70
Frankel R, Lee CMC (1998) Accounting valuation, market expectation, and cross-sectional stock returns. J Account Econ 25:283–319
Godfrey L (1978a) Testing against General Autoregressive and Moving Average Error Models When the Regressors Include Lagged Dependent Variables. Econometrica 46:1293–1301
Godfrey L (1978b) Testing for Higher Order Serial Correlation in Regression Equations When the Regressors Include Lagged Dependent Variables. Econometrica 46:1303–1310
Greene WH (2000) Econometric analysis, 4th edn. Prentice Hall, London
Iqbal M, Cochran S, Schaffer D (2007) Foreign exchange volatility shifts and futures hedging: An ICSS-GARCH approach. Rev Pac Basin Fin Mark Policies 10:349–388
Kothari SP, Zimmerman JL (1995) Price and return models. J Account Econ 20:155–192
Lo K, Lys T (2000) The Ohlson model: contribution to valuation theory, limitations, and empirical applications. J Account Auditing Fin 15:337–367
Lundholm RJ, O’Keefe TB (2001) On comparing cash flow and accrual accounting models for the use in equity valuation: a response to Penman. Contemp Account Res 18:693–696
Morel M (1999) Multi-lagged specification of the Ohlson Model. J Account Auditing Fin 12:147–161
Morel M (2003) Endogenous parameter time series estimation of the Ohlson Model: Linear and Nonlinear analyses. J Bus Fin Account 30:1341–1362
Myers JN (1999) Implementing Residual Income Valuation with Linear Information Dynamics. Account Rev 74:1–28
Neter J, Wasserman W, Kutner M (1990) Applied linear statistical models—regression, analysis of variance, and experimental designs. Irwin, Illinois
Ohlson JA (1995) Earnings, book values, and dividends in equity valuation. Contemp Account Res 18:661–687
Peasnell KV (1982) Some Formal Connections Between Economic Values and Yields and Accounting Numbers. J Bus Fin Account 9:361–381
Penman SH, Sougiannis T (1998) A comparison of dividend, cash flow, and earnings approaches to equity valuation. Contemp Account Res 15:343–383
Rawlings JO (2001) Applied regression analysis: a research tool. Springer, New York
Rubinstein M (1976) The valuation of uncertain income streams and the pricing of options. Bell J Econ 17:407–408
SAS Publishing (1996) Forecasting examples for business and economics using SAS. SAS Institute Inc., Cary NC, USA
Shumway RH, Stoffer D (2006) Time series analysis and its applications. Springer, New York
Sougiannis T (1994) The accounting based valuation of corporate R&D. Account Rev 68:44–68
Sougiannis T, Yaekura T (2001) The accuracy and bias of equity values inferred from analysts’ earnings forecasts. J Account Auditing Fin 16:331–362
Tsay RS (2002) Analysis of financial time series. Wiley, New York
Tsay RS, Lin Y, Wang H (2008) Residual income, value-relevant information and equity valuation: a simultaneous equations approach. Rev Quant Financ Acc 31:331–358
Yen G, Lee CF (2008) Efficient Market Hypothesis (EMH): Past, Present and Future. Rev Pac Basin Fin Mark Policies 11:305–329
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Higgins, H.N. Forecasting stock price with the residual income model. Rev Quant Finan Acc 36, 583–604 (2011). https://doi.org/10.1007/s11156-010-0187-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11156-010-0187-y