Structural equation modeling, or SEM, is a very general, chiefly linear, chiefly cross-sectional statistical modeling technique. Factor analysis, path analysis and regression all represent special cases of SEM. SEM is a largely confirmatory, rather than exploratory, technique. That is, a researcher are more likely to use SEM to determine whether a certain model is valid., rather than using SEM to "find" a suitable model--although SEM analyses often involve a certain exploratory element.
In SEM, interest usually focuses on latent constructs--abstract psychological variables like "intelligence" or "attitude toward the brand"--rather than on the manifest variables used to measure these constructs. Measurement is recognized as difficult and error-prone. By explicitly modeling measurement error, SEM users seek to derive unbiased estimates for the relations between latent constructs. To this end, SEM allows multiple measures to be associated with a single latent construct.
A structural equation model implies a structure of the covariance matrix of the measures (hence an alternative name for this field, "analysis of covariance structures"). Once the model's parameters have been estimated, the resulting model-implied covariance matrix can then be compared to an empirical or data-based covariance matrix. If the two matrices are consistent with one another, then the structural equation model can be considered a plausible explanation for relations between the measures.
Compared to regression and factor analysis, SEM is a relatively young field, having its roots in papers that appeared only in the late 1960s. As such, the methodology is still developing, and even fundamental concepts are subject to challenge and revision. This rapid change is a source of excitement for some researchers and a source of frustration for others.
Structural equation models are suitable when variables of interest cannot be measured perfectly.
S this is modelling technique which is only single latent construct.
"The growth of structural equation modeling: 1994-2001" is a fine paper that covers this thread!
The book is also found here at ResearchGate!
Article The Growth of Structural Equation Modeling: 1994-2001
Book A Step-By-Step Approach to Using SAS System for Factor Analy...
Dear @Gopinath, there are many benefits of Structural Equation Modeling to the researcher today; the following paper entitled: "Structural Equation Modelling in Market Research" by S. MacLean and K. Gray discusses this issue and explains many related concepts.
Abstract: Structural Equation Modelling (SEM) is a technique which effectively subsumes a whole range of standard multivariate analysis methods, including regression, factor analysis and analysis of variance. Whilst being a sophisticated theoretical tool, and certainly not easy to implement, SEM actually underlies much of what practicing market researchers do on a daily basis. That is, on the basis of things we can measure, we attempt to make predictions of things we cannot measure. For market research, SEM provides an opportunity (in fact, a requirement) to hypothesis models of market behaviour, and to test or confirm these models statistically. In the paper, some examples are presented to show some of the benefits of this modelling approach. Technically, SEM estimates the unknown coefficients in a set of linear structural equations. Variables in the equation system are usually directly observed variables, and unmeasured latent variables that are not observed but relate to observed variables. SEM assumes there is a causal structure among a set of latent variables, and that the observed variables are indicators of the latent variables. The latent variables may appear as linear combinations of observed variables, or they may be intervening variables in a causal chain. One of the findings deriving from the examples presented in the paper is that conclusions drawn from techniques such as Exploratory Factor Analysis and regression (eg as used in many customer satisfaction approaches) may be unsustainable in terms of their statistical integrity. See the whole paper at the link:
http://www.smallwaters.com/whitepapers/marketing/
I strongly agree with Prof. Shibu. SEM allows for tests of theoretical propositions in nonexperimental data. You can test whether the factor structure of job satisfaction or the relations among personality characteristics is the same in the U.S. versus Japan with this. You can test whether a reciprocal path accounts for a specific relation in your data better than does a one-way causal flow. You can test quantitative predictions (e.g., the theory says that the path is .80) against data. This is powerful stuff.
luna.cas.usf.edu/~mbrannic/files/regression/SEM.html
Structural equation models are suitable when variables of interest cannot be measured perfectly.
I used SEM for my dissertation which led to two publications on healthcare quality. I will quote from a passage, "Structural Equation Modeling (SEM) with Confirmatory Factor and Path Analysis, a versatile multivariate approach to the measurement of latent variables and the structural relationships among the study variables (Wan, 2002), is used to determine whether the exogenous (independent) variables are causally related to the endogenous (dependent) variables. This research method is a form of multivariate correlational statistics that tests the hypothesized relationships among ... factors of the theoretical...model.
This technique uses two statistical analyses. First, Confirmatory Factor Analysis evaluates the validity of the indicators associated with the underlying theoretical constructs. Second, multivariate analysis of the structural relationships among the study variables provides support of a theoretically specified framework and conclusions for improving...[outcomes]." Fiedler (2012)
When you add reliability testing on surveys modeled on the theoretical constructs, this approach can overcome the two major challenges of research--validity and reliability, so that statistical testing conclusions can be formulated and considered credible.
Fiedler, B.A. (2011). Effects of hospital structural complexity and process adequacy on the prevalence of systemic adverse events and compliance issues: A biomedical engineering technician perspective. Doctoral dissertation, University of Central Florida, Orlando, FL, USA.
Fiedler, B.A., Wan, T., Sivo, S. (2012). Inter-professional Hospital Quality Impact of Biomedical Engineering: Structural Equation Modeling. Saarbrücken, Germany: LAP LAMBERT Academic Publishing.
Fiedler, B.A., Bowles, R., & Oetjen, R. (2012). Biomedical Engineering Technician Dynamics on Hospital Quality: Intangible Shared Performance Measures. Saarbrücken, Germany: LAP LAMBERT Academic Publishing.
Wan, T. T. H. (2002). Evidence-Based Health Care Management: Multivariate Modeling Approaches. Boston, MA: Kluwer Academic Publishers.
Why use SEM?:
-It is flexible;
-Takes care of multicollinearity problems (in turn inflated standard error problems): multiple measures are included in the model (making the model more stable) but only one variable enters the prediction equation;
-Can model measurement error (account for additional influences)
-evocative graphic language: easy representation of relationships and equations
I agree with Maria and i would like to add that SEM allow us to analyse causal relationship between variables
SEM is really good statistical technique for modelling, it aims to obtain estimate of the parameters of the model; thus variance, covariance and loading factor. it indicates the causal relationship with the observed variables
Dear @Gopinath, there are thousands of articles and fine resources available in RG publication database. Link is attached.
https://www.researchgate.net/search.Search.html?query=Structural%20Equation%20Modeling&type=publication
Yes, SEM tools are younger than regression analysis. However, their relevance management science research cannot be under estimated given the limitations of regression analysis. SEM are not about confirmatory analyses. The PLS-SEM has come up and deals with exploratory issues, which in essence lead to theory development. The problems have been with the failure to carry out replica and validation studies to validate theories developed.
Yes, Onesimus Ayaya Sir,
SEM models are very relevant in exploratory studies, particularly those involving behavioral / psychological issues having complex inter-relationships between the variables. These are very widely used in research studies in Marketing / HRM / Social works / allied fields.
Nachtigall, C., Kroehne, U., Funke, F., & Steyer, R. (2003). Pros and cons of structural equation modeling. Methods Psychological Research Online, 8(2), 1-22.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling