出版社：LLC “Consulting Publishing Company “Business Perspectives”
摘要：This paper presents a stochastic model of earnings to study and test how the precision of information that analysts have about the unobservable expected earnings growth rates of firms affects the accuracy of analyst earnings forecasts.The article develops a maximum likelihood procedure to estimate the precision of information that analysts have about expected earnings growth rates.Using the I/B/E/S and COMPUSTAT data sets,the authors find that earnings forecast accuracy is positively associated with information precision.This empirical finding helps explain why analyst earnings forecasts are more accurate than the forecasts that are based only on historical earnings data.It implies that investor may be better off relying on information precision rather than the size of a brokerage house to choose forecasting services.
关键词：information precision estimation;information precision;analyst earnings forecast accuracy;continuous?time model and bayesian learning.
