A primer for the estimation of structural equation models in the presence of missing data: Maximum likelihood algorithms

Abstract

Maximum likelihood algorithms have undergone substantial development, ye marketers have been slow to adopt these techniques to address missing data. This study familiarises marketers with the available maximum likelihood estimators, reviews missing data theory and research, and presents a structural equation modelling simulation study to demonstrate the advantages of maximum likelihood estimation versus other techniques. Results indicate that the full information maximum likelihood and expectation-maximisation outperform traditional techniques with respect to parameter estimate bias, model fit and parameter estimate efficiency. Marketers should be aware of the potential impact of missing data assumptions and decrease their reliance on ad hoc methods in favour of maximum likelihood estimators. [ABSTRACT FROM AUTHOR] Copyright of Journal of Targeting, Measurement & Analysis for Marketing is the property of Palgrave Macmillan Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)