The influence of the presence of deviant item score patterns on the power of a person-fit statistic

R.R. Meijer

Research output: Book/ReportReportProfessional

44 Downloads (Pure)

Abstract

In studies investigating the power of person-fit statistics it is often assumed that the item parameters that are used to calculate the statistics can be estimated in a sample without aberrant persons. However, in practical test applications calibration samples most likely will contain aberrant persons. In the present study, the influence of the type and the number of aberrant persons in the calibration sample on the detection rate of the ZU3 statistic was investigated by means of simulated data. The ZU3 is a standardized version of the person-fit U3 statistic developed by H. Van der Flier (1980). An increase in the number of aberrant simulees resulted in a decrease in the power of ZU3. Furthermore, the type of aberrant behavior influenced the power of ZU3. The use of an iterative procedure to remove the aberrant persons from the dataset was investigated. Results suggested that this method can be used to improve the power of ZU3.
Original languageEnglish
Place of PublicationEnschede
PublisherUniversiteit Twente
Number of pages33
Publication statusPublished - 1994

Publication series

NameOMD research report
PublisherUniversity of Twente, Faculty of Educational Science and Technology
No.94-01

    Fingerprint

Keywords

  • Scores
  • Power (Statistics)
  • Estimation (Mathematics)
  • Test Items
  • Research Methodology
  • METIS-140156
  • Evaluation Methods
  • Foreign Countries
  • Identification
  • Simulation
  • IR-104205

Cite this

Meijer, R. R. (1994). The influence of the presence of deviant item score patterns on the power of a person-fit statistic. (OMD research report; No. 94-01). Enschede: Universiteit Twente.