2019
DOI: 10.1177/2515245918808784
|View full text |Cite
|
Sign up to set email alerts
|

An Updated Recommendation for Multiple Comparisons

Abstract: Instructors of introductory and intermediate statistics courses often teach the use of analysis of variance (ANOVA) for the purpose of comparing more than two group means and pairwise comparison procedures (PCPs) to determine which group means differ from one another following a statistically significant ANOVA test. SPSS provides 18 PCPs. The purpose of this study was to determine which PCP has the best power and maintains Type I error control both when assumptions of equal sample size and equal variance are m… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
68
0
1

Year Published

2019
2019
2023
2023

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 110 publications
(70 citation statements)
references
References 64 publications
1
68
0
1
Order By: Relevance
“…Specifically, we aimed to determine whether clients classified as Recovered reported better emotional and psychosocial functioning compared with those classified as Unchanged, and whether clients classified as Improved were intermediate to the other groups. In order to determine which (if any) group means differed from one another, Games–Howell pairwise comparisons were conducted (Sauder & DeMars, ).…”
Section: Resultsmentioning
confidence: 99%
“…Specifically, we aimed to determine whether clients classified as Recovered reported better emotional and psychosocial functioning compared with those classified as Unchanged, and whether clients classified as Improved were intermediate to the other groups. In order to determine which (if any) group means differed from one another, Games–Howell pairwise comparisons were conducted (Sauder & DeMars, ).…”
Section: Resultsmentioning
confidence: 99%
“…19 A Bonferroni correction was used to adjust for multiple ANOVAs (.05/6 = p < .008) and post hoc tests employed the Games-Howell procedure, which is robust to type 1 error and accounts for unequal sample sizes. 20 The following effect sizes for partial η 2 guided interpretation of results: .01 (small), .06 (medium), and .14 (large). 21…”
Section: Methodsmentioning
confidence: 91%
“…If one-way ANOVA demonstrated an overall difference between groups, we proceeded to perform a post-hoc Tukey's honestly significant difference (Tukey's HSD) test. This post-hoc test controls for the familywise Type 1 error and provide adequate statistical power [45]. We also computed descriptive statistics for the FIPSE and used chi-square analysis to compare the self-reported learning in the nine domains between genders, between pre-clinical (first-and second-year) and clinical (third-to fifth-year) students.…”
Section: Discussionmentioning
confidence: 99%