Critical Values for Yen’s Q3: Identification of Local Dependence in the Rasch Model Using Residual Correlations

Applied Psychological Measurement - Tập 41 Số 3 - Trang 178-194 - 2017
Karl Bang Christensen1, Guido Makransky2, Mike Horton3
1University of Copenhagen, Denmark
2University of Southern Denmark, Odense, Denmark
3University of Leeds, UK

Tóm tắt

The assumption of local independence is central to all item response theory (IRT) models. Violations can lead to inflated estimates of reliability and problems with construct validity. For the most widely used fit statistic Q3, there are currently no well-documented suggestions of the critical values which should be used to indicate local dependence (LD), and for this reason, a variety of arbitrary rules of thumb are used. In this study, an empirical data example and Monte Carlo simulation were used to investigate the different factors that can influence the null distribution of residual correlations, with the objective of proposing guidelines that researchers and practitioners can follow when making decisions about LD during scale development and validation. A parametric bootstrapping procedure should be implemented in each separate situation to obtain the critical value of LD applicable to the data set, and provide example critical values for a number of data structure situations. The results show that for the Q3 fit statistic, no single critical value is appropriate for all situations, as the percentiles in the empirical null distribution are influenced by the number of items, the sample size, and the number of response categories. Furthermore, the results show that LD should be considered relative to the average observed residual correlation, rather than to a uniform value, as this results in more stable percentiles for the null distribution of an adjusted fit statistic.

Từ khóa


Tài liệu tham khảo

10.1007/BF02291180

10.1007/BF02293814

10.1016/B978-0-12-238180-5.50013-6

10.1177/0146621612441858

10.1177/0146621609360202

Andrich D., 2003, Journal of Applied Measurement, 4, 205

Andrich D., 2010, RUMM2030

Barkley R., 1999, Defiant teens: A clinician’s manual for assessment and family intervention

10.2307/1165285

Christensen K. B., 2006, Journal of Applied Measurement, 7, 407

10.2340/16501977-0858

10.1097/01.BRS.0000103346.38557.73

10.3102/10769986023002129

10.1177/0146621615622635

Fisher R. A., 1915, Biometrika, 10, 507

10.1177/0146621602250530

10.1093/fampra/cmu073

10.1007/978-0-387-49839-3_13

10.1186/1472-6920-11-83

Holland P. W., 1988, Test validity, 129

10.1037/1082-989X.2.3.261

10.1007/BF02295736

10.1007/BF02294990

10.1007/BF02294174

10.1177/0146621611410227

10.1081/STA-120030148

10.1007/978-0-387-49839-3_21

Kreiner S., 2011, Advances in mathematics research, 12, 19

10.2340/16501977-0797

Lazarsfeld P. F., 1968, Latent structure analysis

10.1177/0013164412453841

10.1177/0146621612458174

10.1111/bmsp.12030

Lord F. M., 1968, Statistical theories of mental test scores

10.1177/0146621604272739

10.1177/1073191114535242

10.1177/1073191114535242

Marais I., 2009, Journal of Applied Measurement, 10, 17

10.1002/9781118574454.ch7

Marais I., 2008, Journal of Applied Measurement, 9, 105

Marais I., 2008, Journal of Applied Measurement, 9, 1

10.1007/BF02296272

10.1037/a0039015

10.1186/1477-7525-7-58

Rasch G., 1960, Probabilistic models for some intelligence and attainment tests

10.1097/01.mlr.0000250483.85507.04

10.1080/00273171.2012.715555

10.1186/1471-2474-15-95

10.1007/BF02306030

10.1198/016214502760046961

10.1002/art.24065

10.1002/art.23108

10.1007/BF02296270

10.1177/0146621604271053

10.1007/BF02294627

10.1007/BF02301412

10.1177/014662168400800201

10.1111/j.1745-3984.1993.tb00423.x

10.1177/014662169501900406