Forecasting from fallible data: Correcting prediction bias with stein‐rule least squares
- 1 April 1988
- journal article
- research article
- Published by Wiley in Journal of Forecasting
- Vol. 7 (2) , 103-113
- https://doi.org/10.1002/for.3980070203
Abstract
In the presence of fallible data, standard estimation and forecasting techniques are biased and inconsistent. Surprisingly, the magnitude of this bias tends to increase, and not diminish, in time series applications as more observations become available. A solution to this ever‐present problem, Stein‐rule least squares (SRLS), is offered. It corrects for the bias and inconsistency of traditional estimators and provides a means for significantly improving the predictive accuracy of regression‐based forecasting techniques. A Monte Carlo study of the forecasting accuracy of SRLS, compared to its alternatives reveals its practical significance and small sample behaviour.Keywords
This publication has 29 references indexed in Scilit:
- Errors in variables in panel dataJournal of Econometrics, 1986
- Evaluation of the predictive performance of biased regression estimatorsJournal of Forecasting, 1985
- On estimating a consumption function when incomes are subject to measurement errorsEconomics Letters, 1981
- Extending the Classical Normal Errors-in-Variables ModelEconometrica, 1980
- Instrumental Variable Estimation of the Simple Errors-in-Variables ModelJournal of the American Statistical Association, 1980
- Properties of Some Estimators for the Errors-in-Variables ModelThe Annals of Statistics, 1980
- Regression Estimation after Correcting for AttenuationJournal of the American Statistical Association, 1978
- Biased versus unbiased estimationAdvances in Mathematics, 1975
- Data Analysis Using Stein's Estimator and its GeneralizationsJournal of the American Statistical Association, 1975
- Errors in Variables: A Consistent Estimator with Smaller MSE in Finite SamplesJournal of the American Statistical Association, 1974