NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED448170
Record Type: Non-Journal
Publication Date: 2000-Nov-16
Pages: 27
Abstractor: N/A
Reference Count: N/A
ISBN: N/A
ISSN: N/A
Interpreting the Four Types of Sums of Squares in SPSS.
Tanguma, Jesus; Speed, F. M.
This paper analyzes three possible research designs using each of the four types of sums of squares in the Statistical Package for the Social Sciences (SPSS). When the design is balanced (i.e., each cell has the same number of observations), all of the SPSS types of sums of squares yield equivalent results (testable hypotheses and sums of squares) for testing the significance of analysis of variance models. When the design is unbalanced, (i.e., not all cells have the same number of observations), only Type III and Type IV sums of squares agree. In addition, only the hypotheses being tested under Type III and Type IV sums of squares are interpretable. If there are empty cells in the design, none of the types of sums of squares agree. Moreover, only the hypotheses being tested under Type IV sums of squares are interpretable. However, these hypotheses are dependent on the variability and pattern of the missing cells. Thus, any conclusions based on these sums of squares should be made with caution. (Contains 15 tables.) (Author/SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A