ERIC Number: ED334196
Record Type: RIE
Publication Date: 1987-Oct
Reference Count: N/A
Characteristics of Multiple Comparison Procedures.
Yusuf, Mian Muhammad; And Others
Multiple comparison procedures (MCPs), in the context of analysis of variance, are becoming more popular than the overall F tests. An attempt is made to clarify confusion among the different MCPs by systematically comparing and contrasting the procedures in terms of their purposes, restrictions, robustness to assumptions, and other special features that are relevant to any analysis of variance design. Focus is on providing a flowchart to assist researchers in making sound decisions regarding the choice of a MCP. The MCPs compared include: (1) multiple t; (2) multiple F; (3) Dunn; (4) Dunn-Sidak; (5) Dunnett; (6) Fisher's LSD; (7) Tukey's HSD; (8) Spjotvoll-Stoline's t; (9) Tukey-Kramer; (10) Games-Howell; (11) Tamhane; (12) Scheffe's; (13) Brown-Forsythe; (14) Newman-Keuls; and (15) Duncan. Table 1 summarizes characteristics of these procedures, and Table 2 presents a flowchart. (SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Identifiers: Multiple Comparison Tests
Note: Paper presented at the Annual Meeting of the Midwestern Educational Research Association (Chicago, IL, October 15-17, 1987).