As a result of my frustrating experiences reading journal articles filled with cut-and-pasted texts and fraudulent data analysis, I have delved into structural equation modeling (SEM). Based on logical positivism, quantitative research seeks to identify causes of changes in measured social facts, attempting to establish universal context-free generalization (McMillan & Schumacher, 2001, p. 15-16). Quantitative research designs objectivity by using numbers, statistics, structure, and experimenter control. Quantitative research methodologies are employed for various types of studies: descriptive, correlational, and experimental. Descriptive research aims to summarize the variables in question. Correlational research explores the associations between variables in the study. In contrast, experimental research investigates the causal relationships between variables. Both correlational and experimental research approaches can conduct formal hypothesis testing through statistical methods. Depending on the sampling technique applied, findings from these studies can be extrapolated to larger populations (Bhandari, 2023). Multivariate (Collins, n.d.) refers to “involving more than one variable,” and multivariate analysis (Hair et al., 2010, p. 4) defines “all statistical techniques that simultaneously analyze multiple measurements of individuals or objects under investigation.” Structural equation modeling (SEM) refers to “multivariate technique combining aspects of factor analysis and multiple regression that enables the researcher to simultaneously examine a series of interrelated dependence relationships among the measured variables and latent constructs (variates) as well as between several latent constructs.” (Hair et al., 2010, p. 546)                                 

Structural Equation Modeling (SEM) offers several benefits for research, including its ability to test complex hypotheses about relationships among observed and latent variables, handle multiple dependent variables simultaneously, and assess the indirect effects of variables (Cohen et al., 2018, pp. 833-834). It combines factor analysis and multiple regression analysis, allowing for the examination of the structure of interrelations within a set of variables. SEM is particularly useful for theories that cannot be easily tested with simpler statistical methods, providing a comprehensive way to understand the underlying mechanisms of observed phenomena. Structural equation modeling (SEM) can be both recursive and nonrecursive. Recursive models are those where the causation is unidirectional, and there are no feedback loops between the variables (Hair et al., 2010, p. 640). Nonrecursive models, on the other hand, allow for bidirectional relationships and feedback loops among variables, making them more complex and capable of representing real-world phenomena where effects can also act as causes.

This flexibility in modeling different types of relationships is one of SEM's strengths, allowing researchers to capture more complex and dynamic processes in their studies.

According to Cohen et al. (2018, p. 836), the researchers should report the following: construct the model (the factors and the variables, decide the direction of causality (recursive or nonrecursive) identify the number of parameters to be estimated.

Assignment 2, EDDE 802 

https://docs.google.com/presentation/d/19dEfoIG-WMygX2EffFdT9PkgdaSBHaJd/edit?usp=sharing&ouid=110258642682501795802&rtpof=true&sd=true

References

Cankaya, E. M., Liew, J., & de Freitas, C. P. P. (2018). Curiosity and autonomy as factors that promote personal growth in the cross-cultural transition process of international students. Journal of International Students, 8(4), 1694–1708. https://doi.org/10.32674/jis.v8i4.225

Cohen, L., Manion, L., & Morrison, K. (2018). Research methods in education (8th ed.). Routledge. https://doi.org/10.4324/9781315456539

Fayda-Kinik, F. S. (2023). The impact of digital competences on academic procrastination in higher education: A structural equation modeling approach. Pegem Journal of Education and Instruction, 13(3), 25–35. https://doi.org/10.47750/pegegog.13.03.03

Gaskin, J. E. (2020). Structural equation modeling. MyEducator. https://app.myeducator.com/reader/web/1381b/

Hu, L. T., & Bentler, P. M. (1999). Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternatives. Structural Equation Modeling, 6(1), 1-55. https://doi.org/10.1080/10705519909540118

National Centre for Research Methods. (2024, February 23) Structural equation modeling: what is it and what can we use it for? (part 1 of 6). [Video]. YouTube. https://www.youtube.com/watch?v=eKkESdyMG9w&t=258s

Yu, T. (2018). Examining construct validity of the student online learning readiness (SOLR) instrument

 using confirmatory factor analysis. Online Learning, 22(4), 277-288. https://doi.org/10.24059/olj.v22i4.1297

Yu, T., & Richardson, J. C. (2015). An exploratory factor analysis and reliability analysis of the student online leaning readiness (SOLR) instrument. Online Learning, 19(9), 120-141. https://doi.org/10.24059/olj.v19i5.593