Search

Your search keyword '"Chang, Lei"' showing total 111 results
Start Over Author "Chang, Lei" Publication Type Conference Materials
111 results on '"Chang, Lei"'

8. A Comparison between the Nedelsky and Angoff Standard-Setting Methods.

Author

Chang, Lei

Abstract

It was hypothesized that, when compared to the Angoff method (W. H. Angoff, 1971), the Nedelsky method (L. Nedelsky, 1954) for standard setting had lower intrajudge inconsistency, lower cutscores, and lower cutscores especially for items presenting challenges to the judges. These hypotheses were tested and supported in a sample of 22 graduate students serving as judges to determine average performance level for 9 research methodology items using both methods. The more consistent Nedelsky methods are attributed to judges' focused use of response options as a consistent source of information. A close scrutiny of the plausibility and similarity of test item distractors tests the Nedelsky judges' own item knowledge, which, when challenged, results in a low item difficulty estimate. (Contains 3 tables and 27 references.) (Author/SLD)

Published
1996

9. Dependability of Anchoring Labels of Likert-Type Scales.

Author

Chang, Lei

Abstract

This study uses generalizability theory to examine the dependability of anchoring labels of Likert-type scales. Variance components associated with labeling were estimated in two samples using a two-facet random effect generalizability-study design. In one sample, 173 graduate students in education were administered 7 items measuring attitudes toward quantitative methodology. The other sample consisted of 108 graduate students in education who responded to the 8-item Life Orientation Test (M. F. Scheier and C. S. Carver, 1985). From both samples, variance components associated with labeling were found to be trivial, contributing little to the observed score variance. The dependability of anchoring labels was maintained for both normative and absolute interpretations of individual differences with respect to what was being measured. Two plausible explanations were provided. Respondents could primarily be using the numerical information in rating a Likert-type scale or could treat both the scale numerals and verbal labels as representing ordinal rather than equidistant relations. (Contains 2 tables and 29 references.) (Author/SLD)

Published
1996

10. Does a Standard Reflect Minimal Competency of Examinees or Judge Competency?

Author

Chang, Lei

Abstract

The present study examines the influence of judges' item-related knowledge on setting standards for competency tests. Seventeen judges from different professions took a 122-item teacher-certification test in economics while setting competency standards for the test using the Angoff procedure. Judges tended to set higher standards for items they got right and lower standards for items they had trouble with. Interjudge and intrajudge consistency were higher for items all judges got right than items some judges got wrong. Procedures to make judges' test-related knowledge and experience uniform are discussed. (Contains 19 references and 3 tables.) (SLD)

Published
1994

11. Using Confirmatory Factor Analysis of Multitrait-Multimethod Data To Assess the Psychometrical Equivalence of 4-Point and 6-Point Likert-Type Scales.

Author

Chang, Lei

Abstract

Equivalence in reliability and validity across 4-point and 6-point scales was assessed by fitting different measurement models through confirmatory factor analysis of a multitrait-multimethod covariance matrix. Responses to nine Likert-type items designed to measure perceived quantitative ability, self-perceived usefulness of quantitative methodology, and research values of quantitative methodology were obtained from 112 graduate education students at the University of Central Florida (Orlando). Systematic method variance due to numbers of scale points was identified. Separation of this systematic variance from true score variance resulted in greater reduction of reliability and validity for the 6-point scale than that for the 4-point scale. Overall, the 4-point scale was found to have better psychometric properties than the 6-point scale given the measurement conditions of the study. Factors that are speculated to intervene in the behavior of scale options are discussed to provide directions for further research. Nine tables present study findings. (Author/SLD)

Published
1993

Catalog

Books, media, physical & digital resources
See catalog results