1984
DOI: 10.2307/2531158
|View full text |Cite
|
Sign up to set email alerts
|

Procedures for Comparing Samples with Multiple Endpoints

Abstract: Five procedures are considered for the comparison of two or more multivariate samples. These procedures include a newly proposed nonparametric rank-sum test and a generalized least squares test. Also considered are the following tests: ordinary least squares, Hotelling's T2, and a Bonferroni per-experiment error-rate approach. Applications are envisaged in which each variable represents a qualitatively different measure of response to treatment. The null hypothesis of no treatment difference is tested with pow… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

5
731
0
6

Year Published

1992
1992
2014
2014

Publication Types

Select...
10

Relationship

0
10

Authors

Journals

citations
Cited by 1,059 publications
(742 citation statements)
references
References 7 publications
5
731
0
6
Order By: Relevance
“…13 FVC was measured by spirometry according to standard methods, using the best effort of three determinations as the measure of FVC for that day. 14,15 Two tests, typically one day apart, were performed during each evaluation and the best effort was used as the result for all analyses.…”
Section: Efficacy Assessmentmentioning
confidence: 99%
“…13 FVC was measured by spirometry according to standard methods, using the best effort of three determinations as the measure of FVC for that day. 14,15 Two tests, typically one day apart, were performed during each evaluation and the best effort was used as the result for all analyses.…”
Section: Efficacy Assessmentmentioning
confidence: 99%
“…The composite score was created by calculating individual z-scores for each test and then summing the scores, an approach we have used previously (21,22) and that is recommended over modeling each predictor individually because it increases statistical power and reduces type-I error (23,24). Because age was confounded with native disease (patients with cystic fibrosis [CF] are younger than patients without CF), we did not control for age in our primary analyses of neurocognitive function.…”
Section: Methodsmentioning
confidence: 99%
“…The comparisons were also made between respective good and poor recovery subgroups of the two groups employing global test statistics. 14 …”
Section: Discussionmentioning
confidence: 99%