The Estimation of Variance-Covariance and Correlation Matrices from Incomplete Data
- 1 December 1970
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 35 (4) , 417-437
- https://doi.org/10.1007/bf02291818
Abstract
Employing simulated data, several methods for estimating correlation and variance-covariance matrices are studied for observations missing at random from data matrices. The effect of sample size, number of variables, percent of missing data and average intercorrelations of variables are examined for several proposed methods.Keywords
This publication has 17 references indexed in Scilit:
- Missing Values in Linear Multiple Discriminant AnalysisPublished by JSTOR ,1968
- A Measure of the Average IntercorrelationEducational and Psychological Measurement, 1968
- Linear Regression Analysis with Missing Observations among the Independent VariablesJournal of the American Statistical Association, 1964
- Maximum Likelihood Estimation with Incomplete Multivariate DataThe Annals of Mathematical Statistics, 1964
- Sample and Population Score Matrices and Sample Correlation Matrices from an Arbitrary Population Correlation MatrixPsychometrika, 1962
- Estimation of Parameters from Incomplete Multivariate SamplesJournal of the American Statistical Association, 1957
- Maximum Likelihood Estimates for a Multivariate Normal Distribution when Some Observations are MissingJournal of the American Statistical Association, 1957
- Multiple Regression with Missing Observations Among the Independent VariablesJournal of the American Statistical Association, 1956
- Equating Test Scores—A Maximum Likelihood SolutionPsychometrika, 1955
- Estimation of Parameters from Incomplete DataJournal of the American Statistical Association, 1955