1979
DOI: 10.1111/j.2044-8317.1979.tb00598.x
|View full text |Cite
|
Sign up to set email alerts
|

Analysis of repeated measurements

Abstract: Recent literature demonstrates that uniformity of population variances and covariances is a sufficient but not a necessary requirement for valid F ratios in repeated measures designs; the tests will be valid if the loss restrictive condition of circularity is satisfied. The circularity assumptions of various repeated measures designs are presented and the empirical literature is reviewed and interpreted in light of these assumptions. An empirical investigation is then presented which compares numerous data ana… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
75
0
3

Year Published

1984
1984
2005
2005

Publication Types

Select...
6
4

Relationship

0
10

Authors

Journals

citations
Cited by 147 publications
(79 citation statements)
references
References 0 publications
1
75
0
3
Order By: Relevance
“…459-460) and Anderson (1958, p. 259) provide statistical tests that may be used to test the assumption of sphericity. However, on the basis of the results of Monte Carlo studies by Keselman, Rogan, Mendoza, and Breen (1980) and Rogan, Keselman, and Mendoza (1979), these tests do not appear worth doing, because they are highly sensitive to departures from multivariate normality and from their respective null hypotheses. The test described by Bock (1975) is available as an option from SPSS (MANOVA), and the test described by Anderson (1958) is output by BMDP2V.…”
Section: Univariate Modementioning
confidence: 92%
“…459-460) and Anderson (1958, p. 259) provide statistical tests that may be used to test the assumption of sphericity. However, on the basis of the results of Monte Carlo studies by Keselman, Rogan, Mendoza, and Breen (1980) and Rogan, Keselman, and Mendoza (1979), these tests do not appear worth doing, because they are highly sensitive to departures from multivariate normality and from their respective null hypotheses. The test described by Bock (1975) is available as an option from SPSS (MANOVA), and the test described by Anderson (1958) is output by BMDP2V.…”
Section: Univariate Modementioning
confidence: 92%
“…Departures from sphericity can strongly bias the results of repeated-measures ANOVAS as well as the results of planned comparisons involving repeated measures (Rogan, Keselman, & Mendoza, 1979;Vasey & Thayer, 1987). For this reason, where sphericity assumptions are violated, F values are reported with the conservative degrees of freedom recommended by Greenhouse and Geisser (1959).…”
Section: Discussionmentioning
confidence: 99%
“…These were the multivariate analogue a to repeated measures ANOY A and two df-eorrected F tests, the Greenhouse-Geisser and Huyn-Feldt F tests (Rogan, Keselman, & Mendoza, 1979). Fortunately, the results of all three were always in agreement.…”
Section: Discussionmentioning
confidence: 62%