Application of Structural Equation Modeling (Sem) in Hypothesis Testing

Henry Kimani Mburu
Morgan State University
Earl G. Graves School of Business and Management
1700 E. Cold Spring Lane, Baltimore, MD 21251 USA
Tel +1 (443) 866-0041, Email: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract
This is a methodological paper illustrating how structural equation modeling (SEM) technique can be used to test hypothesis.  The illustration involves a job analysis assignment in human resource management. Hypotheses are made and tested.  Results are used to amend the hypotheses in line with the results.  The paper also illustrates how to use exploratory factor analysis variable construction based on existing job analysis literature.  Using data collected from bus drivers for a job analysis project, the paper has three main stages.  At the first stage data is subjected to exploratory factor analysis (EFA) to identify a reasonable number of variables to work with.  Reliability of the constructs is tested.  The second stage involves naming the constructs, and using them to specify a measurement model applying confirmatory factor analysis (CFA).  The third stage uses structural equation modeling to test the hypotheses and to re-specify the model before determining the final results.
Full Text [PDF]