Premium
Measuring Nurses’ Value, Implementation, and Knowledge of Evidence‐Based Practice: Further Psychometric Testing of the Quick‐EBP‐VIK Survey
Author(s) -
Connor Linda,
Paul Fiona,
McCabe Margaret,
Ziniel Sonja
Publication year - 2017
Publication title -
worldviews on evidence‐based nursing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.052
H-Index - 49
eISSN - 1741-6787
pISSN - 1545-102X
DOI - 10.1111/wvn.12190
Subject(s) - psychometric testing , value (mathematics) , survey instrument , psychology , medical education , medicine , applied psychology , psychometrics , computer science , clinical psychology , internal consistency , machine learning
Background The Quick‐EBP‐VIK is a new instrument for measuring nurses’ value, implementation, and knowledge of EBP. Psychometric testing was conducted in two parts. Part 1 describes the tool development and validity testing which resulted in the development of a 25‐item survey after receiving ≥0.80 Item‐Level Content Validity Index for both clarity and relevance. Part 2 describes psychometric testing was necessary to assess additional types of validity and reliability. Aim The purpose of this paper is to further describe the psychometric testing of the Quick‐EBP‐VIK survey instrument. Methods This descriptive study was designed to assess test–retest reliability, internal consistency and construct validity via a web‐based survey. The survey instrument was e‐mailed to all nurses at the study hospital. Nurses who responded to the first survey (Wave 1) received another e‐mail invitation to complete the survey instrument again (Wave 2) for the purpose of assessing the test–retest reliability of the instrument. Results A total of 1,177 deliverable e‐mails were sent to all nursing staff at one free standing pediatric hospital with Magnet ® designation in the northeast. A total of 382 nurses returned completed surveys, indicating a 32.5% response rate for Wave 1. A total of 131 nurses responded to Wave 2 indicating a response rate of 34.3%. The intraclass correlation coefficients for the items included in the final instrument ranged from 0.43 to 0.80 and were deemed sufficient. These represent a sufficient intraclass correlation coefficient. The Cronbach's Alpha values for each of the three domains are all higher than 0.7 indicating that the items of each of the measurement dimension are internally consistent. However, the composite reliability of the third domain was slightly lower than 0.7 when using Raykov's Rho. Linking Evidence to Action The Quick‐EBP‐VIK instrument has gone through rigorous comprehensive testing and has demonstrated good psychometric properties.