Saeed Pahlevan Sharif1, Imtiaz Mostafiz2, Vinitha Guptan1.
Abstract
BACKGROUND: A growing number of nursing studies have used structural equation modelling (SEM) analysis. However, there is little research assessing the use of SEM analysis in nursing research. AIM: To present a systematic review of nursing research that uses SEM. DISCUSSION: The review revealed poor reporting of information about the determination of sample size, missing data, normality and outliers. Most studies neither computed composite reliability nor assessed convergent and discriminant validity. There was a lack of consistency in performing the analysis. Some of the studies conducted exploratory factor analysis before performing confirmatory factor analysis, without discussing its necessity. Although most studies declared the estimation method and software used, there were many that did not.
CONCLUSION: Little information about the different steps of conducting SEM analysis was provided in the studies. Weaknesses and areas of improvement for future empirical SEM studies were identified. IMPLICATIONS FOR PRACTICE: When conducting SEM, there are many issues that should be addressed. Overlooking these issues may invalidate findings. The results of this review provide nurse researchers with best practice guidelines for conducting SEM and pave the way for researchers to adopt this method in their studies. ©2018 RCN Publishing Company Ltd. All rights reserved. Not to be copied, transmitted or recorded in any way, in whole or part, without prior permission of the publishers.
BACKGROUND: A growing number of nursing studies have used structural equation modelling (SEM) analysis. However, there is little research assessing the use of SEM analysis in nursing research. AIM: To present a systematic review of nursing research that uses SEM. DISCUSSION: The review revealed poor reporting of information about the determination of sample size, missing data, normality and outliers. Most studies neither computed composite reliability nor assessed convergent and discriminant validity. There was a lack of consistency in performing the analysis. Some of the studies conducted exploratory factor analysis before performing confirmatory factor analysis, without discussing its necessity. Although most studies declared the estimation method and software used, there were many that did not.
CONCLUSION: Little information about the different steps of conducting SEM analysis was provided in the studies. Weaknesses and areas of improvement for future empirical SEM studies were identified. IMPLICATIONS FOR PRACTICE: When conducting SEM, there are many issues that should be addressed. Overlooking these issues may invalidate findings. The results of this review provide nurse researchers with best practice guidelines for conducting SEM and pave the way for researchers to adopt this method in their studies. ©2018 RCN Publishing Company Ltd. All rights reserved. Not to be copied, transmitted or recorded in any way, in whole or part, without prior permission of the publishers.
Keywords:
data collection; methodology; nursing research; structural equation modelling; systematic review
Mesh：
Year: 2018
PMID： 30207432 DOI： 10.7748/nr.2018.e1577
Source DB: PubMed Journal: Nurse Res ISSN： 1351-5578