Premium
SIMPLE APPROXIMATIONS IN THE ESTIMATION OF MANY PARAMETERS
Author(s) -
Jackson Paul H.
Publication year - 1972
Publication title -
british journal of mathematical and statistical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.157
H-Index - 51
eISSN - 2044-8317
pISSN - 0007-1102
DOI - 10.1111/j.2044-8317.1972.tb00493.x
Subject(s) - simple (philosophy) , mathematics , class (philosophy) , statistics , estimation , field (mathematics) , bayesian probability , econometrics , subject (documents) , regression , computer science , artificial intelligence , pure mathematics , philosophy , management , epistemology , library science , economics
In the field of educational measurement, one often wishes to estimate a parameter of a particular type for each member of some class of subjects, in circumstances where knowledge of the data for the whole class can be used to improve the estimate for each individual subject. The logic of an early formula due to Kelley for true scores (individual means) is first studied, and is then extended to variances, regression weights, correlation coefficients and proportions. The estimates obtained are viewed as simple approximations to those which might be obtained from a Bayesian structural model.