COURSE: Structural Equation Modeling – variance (SmartPLS) and covariance based (lavaan)
PROFESSOR: Prof. Dr. Diógenes de Souza Bido
SEMESTER: 2º/2018
DATE: Sept/21: 1 p.m. to 5 p.m., [break 5 p.m. to 6 p. m.], 6 p.m. to 10 p.m.
Sept/28: 1 p.m. to 5 p.m., [break 5 p.m. to 6 p. m.], 6 p.m. to 10 p.m.
Oct/19: 1 p.m. to 5 p.m., [break 5 p.m. to 6 p. m.], 6 p.m. to 10 p.m.
Oct/26: 1 p.m. to 5 p.m., [break 5 p.m. to 6 p. m.], 6 p.m. to 10 p.m.
Contents:
Structural Equation Modeling – variance based (SmartPLS):
- Measurement model assessment: convergent and discriminant validity, and reliability.
- Full model (path analysis with latent variables): importance-performance map analysis, multicollinearity, 2nd order latent variable, sample size definition, control variables, common method bias, moderation and Multigroup analysis.
Structural Equation Modeling – covariance based (lavaan – R package):
- Confirmatory factor analysis
- Full model (hypothesis testing)
Purpose:
The purpose of the course is to enable participants to: (i) Identify the situations in which PLS-SEM is the most recommended method; (ii) Recognize the differences between variance-based and covariance-based structural equation modeling; (iii) Use SmartPLS and lavaan in their research; (iv) Evaluate the measurement and the structural model; (v) Raise awareness of the need for rigor in their analyses.
Assessment:
Final grade = (HW1 + HW2)/2
Approval if: Final grade equal or greater than 6.0
Delivery by e-mail (diogenesbido@yahoo.com.br):
HW1 = October 15th
HW2 = November 5th
Expected students' profile: MSc and PhD students, professors and researchers.
- Students must have completed and passed courses in quantitative methods or data analysis (in their master or Ph.D. course), whose contents include:
- hypothesis test and statistical significance
- correlation and linear regression
- exploratory factor analysis
Language: The course will be taught in Portuguese.
- number of students: 40
Computer Lab:
- It is recommended that students bring their notebook (with R, R Studio, G*Power 3, and SmartPLS installed. The instructions will be send before the course beginning)
Suggestion for students, who want to buy books, to facilitate the study:
HAIR JR., J. F.; HULT, G. T. M.; RINGLE, C. M.; SARSTEDT, M. A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM). 2nd Ed.. Thousand Oaks, CA: Sage Publications, Inc., 2016.
HAIR JR., J. F.; SARSTEDT, M.; RINGLE, C. M.; GUDERGAN, S.P. Advanced Issues in Partial Least Squares Structural Equation Modeling. Thousand Oaks, CA: Sage Publications, Inc., 2017. [may/2017]
GARSON, G. D. (2016). Partial Least Squares: Regression and Structural Equation Models. Asheboro, NC: Statistical Associates Publishers. Available at (free) em: <http://info.smartpls.com/data/uploads/ebook_on_pls-sem.pdf>.
BEAUJEAN, A.A.; Latent Variable Modeling Using R: a step-by-step guide. New York: Routledge, 2014.
Syllabus:
Day |
Content |
Bibliographical references |
---|---|---|
september/21st
|
Exploratory and confirmatory analysis (Theory and Data) Structural and measurement model How to use SmartPLS: data, project, files Understanding the PLS algorithm: - Linear regression: betas, R² e bootstrap - Path analysis with observed variables: indirect, direct and total effects - Reflective latent variable and principal components. |
Software SmartPLS Software SPSS or Minitab or R (Rcmdr package)
Streiner (2005) and
Henseler et al. (2009, p.277-291). or Mackenzie et al. (2009) |
september/21st
|
Measurement model assessment: reflective - convergent and discriminant validity, and reliability - How to report the results
Emergent variables or Formative latent variables - Convergent validity - Confirmatory Tedrad Analysis - Formative variable in exogenous and endogenous position
|
Bido et al. (2016)
Gefen & Straub (2005)
Gudergan et al. (2008) or Ross (2014) |
september/28th
|
Full model – path analysis with latent variables in SmartPLS - Importance-performance map analysis - Multicollinearity in the structural model - 2nd order latent variable - sample size and statistical power with G*Power 3 - How to report the results |
Video IPMA
Wetzels et al. (2009) or Becker et al. (2012) or Wilson et al. (2007)
Software G*Power 3 & Manual or Faul et al. (2007)
|
september/28th
|
Moderation (multiplicative term) Multigroup analysis: observed heterogeneity (a priori) FIMIX: non-observed heterogeneity
HW1: (i) multicollinearity + 2nd order LV; (ii) importance-performance map analysis - Estimate the full model, adjust the measurement model and report and explain the results.
|
Henseler (2012) e Henseler et al. (2016) |
october/5th october/12th |
EnANPAD Holiday |
|
october/19th
|
SmartPLS x lavaan: - Latent variable scores and their uses - Attenuation (consistency at large) - Sample size and statistical power with G*Power 3
Software R, R packages, install packages, load packages
lavaan (Latent Variable Analysis) path analysis from covariance matrix and from raw data (dataset) confirmatory factor analysis and restrictions on parameters
|
Software R and lavaan package
Rosseel (2015, p.1-8) e materials from lavaan_site or Hair Jr. et al. (2010, p.600-638)
Videos: https://goo.gl/Q7zmyR |
october/19th |
Reflective: convergent, discriminant validity and reliability
Formative indicators in lavaan Identification and degree of freedom Modification indices |
Rosseel (2015, p.9-15) e materials from lavaan_site
Soper (2017)
Videos: https://goo.gl/Q7zmyR
|
october/26th |
Exercices: Kuhnel and Beaujean models Generate the path diagram Goodness of fit indices Defined command := (indirect effect) 2nd order Latent variable Estimation from ordinal data (WLSMV)
|
Videos: https://goo.gl/Q7zmyR |
october/26th |
Exercise from published paper.
HW2: Search an article with a structural model and covariance matrix among indicators (caution: do not use the correlations between latent variables). Run the model from these data in lavaan. Report and explain the results.
|
Videos: https://goo.gl/Q7zmyR |
[21/09/2018]
Software SmartPLS available at:
- v.3 (free 30-day trial): <https://www.smartpls.com/#downloads>.
- v.2 (free): <https://www.smartpls.com/smartpls2>.
Software R available at: <https://www.r-project.org/>.
Software G*Power 3 at: <http://www.gpower.hhu.de/>.
A-priori Sample Size Calculator for Structural Equation Models (online) at: <https://www.danielsoper.com/statcalc/calculator.aspx?id=89>
<http://www.quantpsy.org/rmsea/rmsea.htm>.
<http://timo.gnambs.at/en/scripts/powerforsem>.
STREINER, D.L. Finding our way: an introduction to path analysis. Canadian Journal of Psychiatry. v.50, n.2, p.115-122, 2005. [EBSCO]
HENSELER, J.; RINGLE, C. M.; SINKOVICS, R. R. The use of partial least squares path modeling in international marketing. Advances in International Marketing, Advances in International Marketing., v. 20, p. 277–319, 2009. available at: <http://is.gd/4EGtMc>.
MACKENZIE, S. B.; PODSAKOFF, P. M.; PODSAKOFF, N. P. Construct measurement and validation procedures in MIS and behavioral research: integrating new and existing techniques. MIS Quarterly, v. 35, n. 2, p. 293–334, 2011. available at: <http://is.gd/aeK8cl>.
BIDO, D.S. et al. Escalas como Ferramentas de Diagnóstico e Gestão: críticas ao uso da análise fatorial exploratória para a validação. [Relatório de pesquisa – CNPq], 2016.
GEFEN, D.; STRAUB, D. W. 2005. “A Practical Guide to Factorial Validity Using PLS-Graph: Tutorial and Annotated Example,” Communications of the Association for Information Systems, v.16, p. 91-109, 2005.
[28/09/2018]
GUDERGAN, S.; RINGLE, C.; WENDE, S.; WILL, A. Confirmatory tetrad analysis in PLS path modeling. Journal of Business Research, v. 61, n. 12, p. 1238–1249, 2008.
ROOS, J. M. The Vanishing Tetrad Test: Another test of model misspecification. Measurement: Interdisciplinary Research and Perspectives, v. 12, n. 3, p. 109–114, 2014.
Video “Importance-Performance Map Analysis (IPMA)”, disponível em: <https://www.smartpls.com/documentation/importance-performance-matrix>.
BECKER, J. M.; KLEIN, K.; WETZELS, M. Hierarchical Latent Variable Models in PLS-SEM: Guidelines for Using Reflective-Formative Type Models. Long Range Planning, v.45, n.5-6, p.359–394, 2012.
WETZELS, M.; ODEKERKEN-SCHRÖDER, G.; OPPEN, C. VAN. Using PLS path modeling for assessing hierarchical construct models: guidelines and empirical illustration. MIS Quarterly, v. 33, n. 1, p. 177–195, 2009.
WILSON, B.; HENSELER, J. Modeling reflective higher-order constructs using three approaches with PLS path modeling: a Monte Carlo comparison. Australian and New Zealand Marketing Academy (ANZMAC) Conference. Anais... p.791–800, 2007. Disponível em: <http://doc.utwente.nl/91758/1/BWilson_2.pdf>.
Software G*Power (free) e G*Power 3.1 manual. January 31, 2014. Disponíveis em: <http://www.gpower.hhu.de/>.
FAUL, F.; ERDFELDER, E.; LANG, A.-G.; BUCHNER, A. G*Power 3: a flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behavior Research Methods, v. 39, n. 2, p. 175–91, 2007.
CHIN, W. W.; THATCHER, J. B.; WRIGHT, R. T.; STEEL, D. Controling for common method variance in PLS analysis: the measured latent marker variable approach. In: ABDI, H.; CHIN, W. W.; VINZI, V. E.; RUSSOLILLO, G.; TRINCHERA, L. (Ed.). New Perspectives in Partial Least Squares and Related Methods. New York: Springer, 2013. p.231-239.
HENSELER, J.; HUBONA, G.; RAY, P. A. Using PLS Path Modeling in New Technology Research : Updated Guidelines Using PLS Path Modeling in New Technology Research : Updated Guidelines. Industrial Management & Data Systems, v. 116, p. 2–20, 2016.
ONÇA. S.S.; BIDO, D.S.; GODOY, A.S. Impacto da potência de equipes de trabalho e dos conflitos intragrupais na aprendizagem grupal. In: Encontro da ANPAD, XXXVIII, 2014, Rio de Janeiro. Anais... Rio de Janeiro: ANPAD, 2014, p.1-16.
Video: “PLS Multigroup Analysis” available at: <https://www.smartpls.com/documentation/pls-multigroup-analysis>.
HENSELER, J. PLS-MGA: A Non-Parametric Approach to Partial Least Squares-based Multi-Group Analysis. In: W. Gaul et al. (eds.), Challenges at the Interface of Data Analysis, Computer Science, and Optimization, Studies in Classification, Data Analysis, and Knowledge Organization, DOI 10.1007/978-3-642-24466-7 50, © Springer-Verlag Berlin Heidelberg, 2012. available at: <http://is.gd/AQRBth>.
HENSELER, J.; RINGLE, C. M.; SARSTEDT, M. Testing Measurement Invariance of Composites Using Partial Least Squares. International Marketing Review, forthcoming. 2016. available at: <http://info.smartpls.com/data/uploads/micom.pdf>.
[19/10/2018 e 26/10/2018]
ROSSEEL, Y. The lavaan tutorial. Belgium: Ghent University, Department of Data Analysis, 2015. available at: <http://lavaan.ugent.be/tutorial/tutorial.pdf>.
lavaan website: <http://lavaan.ugent.be/resources/teaching.html>
HAIR Jr., J.F.; BLACK, W.C.; BABIN, B.J.; ANDERSON, R.E. Multivariate Data Analysis, 7/e. Harlow: Pearson Prentice Hall, 2010. [Chapter 13 (p.600-638): Confirmatory Factor Analysis].
SOPER, D. S. A-priori Sample Size Calculator for Structural Equation Models [Software]. , 2017. Disponível em: <http://www.danielsoper.com/statcalc>. .
What to report?
GEFEN, D.; RIGDON, E. E.; STRAUB, D. An update and extension to SEM guidelines for administrative and social science research. MIS Quarterly, v.35, n.2, p.iii-xiv, 2011