Why you should consider SEM: A guide to getting started

Abstract

Structural Equation Modeling (SEM) offers researchers additional flexibility and enhanced research conclusions, yet it is still underutilized in accounting. This may be in part because many researchers are not sufficiently familiar with SEM. SEM can be difficult to apply, especially if the research study was not appropriately planned to accommodate the necessary assumptions and data requirements. This article helps researchers overcome some barriers to using SEM by providing a simple guide to effectively planning a study suitable for an SEM analysis while also suggesting references and additional reading on the topic. To further encourage the use of SEM, the practical benefits of using SEM over the traditional regression approach for some research situations are also explained. Finally, a comparison of a regression and an SEM analysis of the same data testing the same theoretical model is included in the Appendices A and B in order to compare the differences in the research conclusions obtained by the two methods of analysis.

Citation

Blanthorne, C., Allison Jones-Farmer, L. and Dreike Almer, E. (2006), "Why you should consider SEM: A guide to getting started", Arnold, V., Clinton, B.D., Luckett, P., Roberts, R., Wolfe, C. and Wright, S. (Ed.) Advances in Accounting Behavioral Research (Advances in Accounting Behavioural Research, Vol. 9), Emerald Group Publishing Limited, Leeds, pp. 179-207. https://doi.org/10.1016/S1475-1488(06)09007-7