Comparing Regressions when Measurement Error Variances are known
- 1 March 1974
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 39 (1) , 53-68
- https://doi.org/10.1007/bf02291577
Abstract
In a multiple (or multivariate) regression model where the predictors are subject to errors of measurement with a known variance-covariance structure, two-sample hypotheses are formulated for (i) equality of regressions on true scores and (ii) equality of residual variances (or covariance matrices) after regression on true scores. The hypotheses are tested using a large-sample procedure based on maximum likelihood estimators. Formulas for the test statistic are presented; these may be avoided in practice by using a general purpose computer program. The procedure has been applied to a comparison of learning in high schools using achievement test data.Keywords
This publication has 11 references indexed in Scilit:
- Comparing Conditional Means and Variances in a Regression Model with Measurement Errors of Known VariancesJournal of the American Statistical Association, 1972
- On Obtaining Large-Sample Tests from Asymptotically Normal EstimatorsThe Annals of Mathematical Statistics, 1971
- Estimating structural and functional relationshipsJournal of Multivariate Analysis, 1971
- Errors of Measurement in StatisticsTechnometrics, 1968
- Large-Sample Covariance Analysis when the Control Variable is FallibleJournal of the American Statistical Association, 1960
- The Fitting of Straight Lines when Both Variables are Subject to ErrorJournal of the American Statistical Association, 1959
- A Note on Trace-Differentiation and the Ω-operatorProceedings of the Edinburgh Mathematical Society, 1953
- REGRESSION, STRUCTURE AND FUNCTIONAL RELATIONSHIP. PART IBiometrika, 1951
- Symbolic Matrix DerivativesThe Annals of Mathematical Statistics, 1948
- On Solutions of the Behrens-Fisher Problem, Based on the $t$-DistributionThe Annals of Mathematical Statistics, 1943