Abstract
Nearly all psychosocial survey datasets contain missing data. Recent advances in statistical theory, and implementation of the theory in modeling software, have made it possible to handle various types of missing data with the proviso that data are missing at random. This study presents an application of a confirmatory factor analysis with incomplete data, demonstrating the utility of several maximum likelihood-based missing data estimation procedures: multigroup, single group, and expectation maximization multiple-imputation. The substantive example used to demonstrate these procedures was a 2-factor measurement model of achievement goal orientation in sports with a sample size of 1,002. Of the total sample, 124 participants (12%) had incomplete data in the form of nonresponse. Initial analysis showed that the data missing were completely random. Subsequent modeling of the incomplete data revealed that, across the 3 data estimation procedures, parameter estimates were remarkably similar and standard errors of estimates were small in magnitude, suggesting the consistency of these procedures in analyzing incomplete data.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Measurement in Physical Education and Exercise Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
