Item Analysis using Classical Test Theory and Item Response Theory, Validity and Reliability of the Korean version of a Pressure Ulcer Prevention Knowledge
10.7586/jkbns.2018.20.1.11
- Author:
Myung Ja KANG
1
;
Myoung Soo KIM
Author Information
1. Department of National Cancer Screening, Pusan National University Hospital, Busan, Korea.
- Publication Type:Original Article
- Keywords:
Psychometrics;
Knowledge;
Pressure ulcer
- MeSH:
Discrimination (Psychology);
Hospitals, University;
Humans;
Logistic Models;
Nurses;
Pressure Ulcer;
Psychometrics;
Reproducibility of Results
- From:Journal of Korean Biological Nursing Science
2018;20(1):11-19
- CountryRepublic of Korea
- Language:Korean
-
Abstract:
PURPOSE: The purposes of this study were to perform items analysis using the classical test theory (CTT) and the item response theory (IRT), and to establish the validity and reliability of the Korean version of pressure ulcer prevention knowledge. METHODS: The 26-item pressure ulcer prevention knowledge instrument was translated into Korean, and the item analysis of the 22 items having an adequate content validity index (CVI), was conducted. A total of 240 registered nurses in 2 university hospitals completed the questionnaire. Each item was analyzed applying CTT and IRT according to 2-parameter logistic model. Response alternatives quality, item difficulty and item discrimination were evaluated. For testing validity and reliability, Pearson correlation coefficient and Kuder Richardson-20 (KR-20) were used. RESULTS: Scale CVI was .90 (Item-CVI range=.75–1.00). The total correct answer rate for this study population was relatively low as 52.5%. The quality of response alternatives was found to be relatively good (range=.02–.83). The item difficulty of the questions ranged form .10 to .86 according to CTT and −12.19 to 29.92 according to the IRT. This instrument had 12-low, 2-medium and 8-high item difficulty applying IRT. The values for the item discrimination ranged .04–.57 applying CTT and .00–1.47 applying IRT. And overall internal consistency (KR-20) was .62 and stability (test-retest) was .82. CONCLUSION: The instrument had relatively weak construct validity, item discrimination according to the IRT. Therefore, the cautious usage of a Korean version of this instrument would be recommended for discrimination because there are so many attractive response alternatives and low internal consistency.
