NotesFAQContact Us
Collection
Advanced
Search Tips
Descriptor
Discriminant Analysis2
Error of Measurement2
Research Problems2
Sampling2
Computer Software1
Educational Research1
Predictor Variables1
Psychological Studies1
Regression (Statistics)1
Research Methodology1
Source
Educational and Psychological…1
Author
Moore, James D., Jr.1
Thompson, Bruce1
Publication Type
Reports - Evaluative2
Journal Articles1
Speeches/Meeting Papers1
Education Level
Audience
Location
Laws, Policies, & Programs
Assessments and Surveys
What Works Clearinghouse Rating
Showing all 2 results Save | Export
Stepwise Regression and Stepwise Discriminant Analysis Need Not Apply Here: A Guidelines Editorial.
Peer reviewed Peer reviewed
Thompson, Bruce – Educational and Psychological Measurement, 1995
Three problems with stepwise research methods are explored. Computer packages may use incorrect degrees of freedom in stepwise computations. In addition, stepwise methods do not identify correctly the best variable set of a given size. A third problem is that stepwise methods tend to capitalize on sampling error. (SLD)
Descriptors: Discriminant Analysis, Error of Measurement, Research Methodology, Research Problems
Stepwise Methods Are as Bad in Discriminant Analysis as They Are Anywhere Else.
PDF on ERIC Download full text
Moore, James D., Jr. – 1996
The serious problems associated with the use of stepwise methods are well documented. Various authors have leveled scathing criticisms against the use of stepwise techniques, yet it is not uncommon to find these methods continually employed in educational and psychological research. The three main problems with stepwise techniques are: (1)…
Descriptors: Computer Software, Discriminant Analysis, Educational Research, Error of Measurement