/lp/american-psychological-association/parametric-statistics-and-levels-of-measurement-RGFQjCMjRx
References (13)
-
R. Darlington (1973)
Comparing two groups by simple graphs.Psychological Bulletin, 79
-
S. Maxwell, H. Delaney (1985)
Measurement and Statistics: An Examination of Construct Validity.Psychological Bulletin, 97
-
J. Michell (1986)
Measurement scales and statistics: A clash of paradigms.Psychological Bulletin, 100
-
B. Spencer (1983)
Test Scores as Social Statistics: Comparing DistributionsJournal of Educational Statistics, 8
-
J. Gaito (1980)
Measurement scales and statistics: Resurgence of an old misconception.Psychological Bulletin, 87
-
T. Gregoire, B. Driver (1987)
Analysis of ordinal data to detect population differences.Psychological Bulletin, 101
-
E. Borgatta, G. Bohrnstedt (1980)
Level of MeasurementSociological Methods & Research, 9
-
S. Stevens (1951)
Mathematics, measurement, and psychophysics. -
James Townsend, F. Ashby (1984)
Measurement Scales and Statistics: The Misconception MisconceivedPsychological Bulletin, 96
-
E. Lehmann (1955)
Ordered Families of DistributionsAnnals of Mathematical Statistics, 26
-
B. Baker, C. Hardyck, L. Petrinovich (1966)
Weak Measurements vs. Strong Statistics: An Empirical Critique of S. S. Stevens' Proscriptions nn StatisticsEducational and Psychological Measurement, 26
-
L. Mead, S. Stevens (1951)
Handbook of experimental psychology -
J. Snodgrass, J. Townsend, F. Ashby (1983)
The Stochastic Modeling of Elementary Psychological Processes
- Publisher
- American Psychological Association
- Copyright
- Copyright © 1988 American Psychological Association
- ISSN
- 0033-2909
- eISSN
- 1939-1455
- DOI
- 10.1037/0033-2909.104.1.137
- Publisher site
- See Article on Publisher Site
Abstract
If Yis a continuous, ordinal measure of a latent variable θ and Yhas a normal distribution with equal variances in several groups, then ttests and one-way analyses of variance on Y can be used to testhypotheses about population mean differences on θ in the corresponding groups. IfX and Y are continuous, ordinal measures of latentvariables θ and Φ, and if X and Y havea bivariate normal distribution, then a test of the null hypothesis that the populationcorrelation between X and Y is zero is also a test ofthe hypothesis that θ and Φ are independent.
Journal
Psychological Bulletin – American Psychological Association
Published: Jul 1, 1988