NotesFAQContact Us
Search Tips
ERIC Number: ED400266
Record Type: Non-Journal
Publication Date: 1996-Apr
Pages: 17
Abstractor: N/A
Reference Count: N/A
The Use of Person Fit Statistics in Mail Surveys.
Green, Kathy E.
Person fit statistics are generated when item response theory is used to construct measures. While person fit statistics are well grounded in theory, their utility in aggregate reporting of survey data has not been demonstrated. This study evaluated effects on reliability and validity of including and excluding misfitting person response patterns, using the Rasch model. The following mail survey data sets were used: (1) responses of 3,839 adults to a survey on the effects of the women's movement; (2) responses of 271 people to a survey on self-health care attitudes; (3) responses of 555 teachers to a survey about test use; (4) responses of 410 teachers to a survey about attitudes toward research; and (5) responses of 213 college students and graduates to a survey about dissertations. Omission of misfitting persons served to increase reliability for all data sets, but had inconsistent effects on validity coefficients. All effects were small. (Contains 3 tables and 21 references.) (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