Factor-based structural equation modeling with WarpPLS

Dear colleagues:

The link below, for an article forthcoming in the Australasian Marketing Journal (AMJ), provides a discussion on the limitations of using composites in structural equation modeling (SEM). It also discusses a new factor-based method that builds on the classic partial least squares (PLS) technique developed by Herman Wold. This new method, also presented elsewhere (see ISJ article titled “From composites to factors: Bridging the gap between PLS and covariance‐based structural equation modeling”), addresses those limitations of using composites in SEM.

https://www.sciencedirect.com/science/article/abs/pii/S1441358218303215

The article linked above is titled “Factor-based structural equation modeling with WarpPLS”. The discussion in this AMJ article is very applied and, hopefully, conceptually straightforward.

Some of you may be wondering why I am so convinced that, if questionnaires are used for data collection, the resulting data must be factor-based and simply cannot be composite-based. The reason is simple. For question-statements to be devised by researchers, so that indicators measuring latent constructs can be obtained via questionnaires, the mental ideas associated with the constructs must first exist in the minds of the researchers. The direction of causality is clear: from constructs to indicators. This direction of causality gives rise to measurement residuals, which distinguish factors from composites.

Having said that, I believe that we can have what I refer to as "analytic composites", which can be seen as exact linear combinations of indicators. These are unique entities, which are designed to serve specific purposes. Analytic composites are widely used in a variety of fields, including business - e.g., the Dow Jones Industrial Average. With analytic composites, there is no way the original weights can be accurately recovered based on the data. To obtain those weights, one has to either ask the designer or, in the person’s absence, derive the weights from domain-relevant theory.

Remember, the whole point of SEM is to recover the original population parameters based on the sample data collected via questionnaires. The data are the indicators. The original parameters are path coefficients, loadings, weights etc.

In SEM we do not have the original factors at the start of the analysis, we only have the indicators and theory-driven models with structural and measurement components. The new factor-based method discussed in the AMJ article linked above yields correlation-preserving estimates of the factors.

Happy New Year!

Ned

Webinar series: Intermediate PLS-SEM using WarpPLS 6.0

Early Registration Ends 10/19: Intermediate PLS-SEM using WarpPLS 6.0.

Discounted $95 USD early registration ends October 19.

Live online 6-session webinar series: Intermediate PLS-SEM using WarpPLS 6.0 software. Webinar sessions on Fridays begin mid-November.

Visit Eventbrite registration site: https://goo.gl/QhXK9z

Webinar series agenda: (1) Explore different applications of full latent growth; (2) Explore conditional probabilistic queries; (3) Understand and use effective second-order latent variable models; (4) Conduct and report both composite-based and factor-based PLS-SEM analyses; (5) Use consistent PLS factor-based algorithms; (6) Test and control for endogeneity; (7) Understand and use more refined data imputation algorithms other than mean replacement; (8) Explore categorical-to-numeric and numeric-to-categorical conversion; (9) Explore power and minimum sample size requirements with PLS-SEM; and other contemporary intermediate topics.

Includes a certificate of completion signed by Dr. Ned Kock (developer of WarpPLS) and Dr. Geoffrey Hubona (associate professor of MIS and webinar series instructor). Also includes: 3-month fully-featured version of WarpPLS 6.0 software; all webinar series videos for download; all materials, data sets, project files, webinar series slides and readings.

Webinar series: Introduction to PLS-SEM using WarpPLS 6.0

Check out the online webinar series - Introduction to PLS-SEM using WarpPLS 6.0:

https://goo.gl/PWxZsF

The live webinar series will be presented in six weekly 90-minute onine sessions from 11:30AM EDT to 1:00PM EDT on (mostly) consecutive 2018 Fridays: August 17th and 24th; and September 7th, 14th, 21st and 28th. The audio and video for all of the live webinar sessions will be recorded and those recordings will be made available for permanent download by each registered webinar participant. Each participant who successfully completes the 6-session webinar series will also receive an Introduction to PLS-SEM using WarpPLS Certificate of Completion signed by both Dr. Ned Kock, the original developer of WarpPLS, and by Dr. Geoffrey Hubona, the instructor of this webinar series.

Single missing data imputation in PLS-based structural equation modeling

An important source of bias in structural equation modeling (SEM) employing the partial least squares method (PLS) is missing data. Deletion methods, such as listwise and pairwise deletion, have traditionally been used to deal with missing data. These methods are perceived as leading to selective loss of data and significant related biases. Missing data imputation methods, on the other hand, do not resort to deletion.  Our study suggests that single missing data imputation methods perform better with PLS-SEM than expected based on past research on their performance with other multivariate analysis techniques such as multiple regression and covariance-based SEM:

Kock, N. (2018). Single missing data imputation in PLS-based structural equation modeling. Journal of Modern Applied Statistical Methods, 17(1), 1-23.

http://cits.tamiu.edu/kock/pubs/journals/2018/Kock_2018_JMASM_MissDataImputationPLS.pdf

A thank you note to the participants in the 2018 PLS Applications Symposium

This is just a thank you note to those who participated, either as presenters or members of the audience, in the 2018 PLS Applications Symposium:

http://plsas.net/

As in previous years, it seems that it was a good idea to run the Symposium as part of the Western Hemispheric Trade Conference. This allowed attendees to take advantage of a subsidized registration fee, and also participate in other Conference sessions and the Conference's social event.

I have been told that the proceedings will be available soon from the Western Hemispheric Trade Conference web site, which can be reached through the Symposium web site (link above).

Also, the full-day workshop on PLS-SEM using the software WarpPLS was well attended. This workshop was fairly hands-on and interactive. Some participants had quite a great deal of expertise in PLS-SEM and WarpPLS. It was a joy to conduct the workshop!

As soon as we define the dates, we will be announcing next year’s PLS Applications Symposium. Like this years’ Symposium, it will take place in Laredo, Texas, probably in mid-April as well.

Thank you and best regards to all!

-----------------------------------------------------------

Ned Kock

Symposium Chair

http://plsas.net

PLS Applications Symposium; 11 - 13 April 2018; Laredo, Texas

PLS Applications Symposium; 11 - 13 April 2018; Laredo, Texas
(Abstract submissions accepted until 15 February 2018)

*** Only abstracts are needed for the submissions ***

The partial least squares (PLS) method has increasingly been used in a variety of fields of research and practice, particularly in the context of PLS-based structural equation modeling (SEM). The focus of this Symposium is on the application of PLS-based methods, from a multidisciplinary perspective. For types of submissions, deadlines, and other details, please visit the Symposium’s web site:

http://plsas.net

*** Workshop on PLS-SEM ***

On 11 April 2018 a full-day workshop on PLS-SEM will be conducted by Dr. Ned Kock and Dr. Geoffrey Hubona, using the software WarpPLS. Dr. Kock is the original developer of this software, which is one of the leading PLS-SEM tools today; used by thousands of researchers from a wide variety of disciplines, and from many different countries. Dr. Hubona has extensive experience conducting research and teaching topics related to PLS-SEM, using WarpPLS and a variety of other tools. This workshop will be hands-on and interactive, and will have two parts: (a) basic PLS-SEM issues, conducted in the morning (9 am - 12 noon) by Dr. Hubona; and (b) intermediate and advanced PLS-SEM issues, conducted in the afternoon (2 pm - 5 pm) by Dr. Kock. Participants may attend either one, or both of the two parts.

The following topics, among others, will be covered - Running a Full PLS-SEM Analysis - Conducting a Moderating Effects Analysis - Viewing Moderating Effects via 3D and 2D Graphs - Creating and Using Second Order Latent Variables - Viewing Indirect and Total Effects - Viewing Skewness and Kurtosis of Manifest and Latent Variables - Viewing Nonlinear Relationships - Solving Collinearity Problems - Conducting a Factor-Based PLS-SEM Analysis - Using Consistent PLS Factor-Based Algorithms - Exploring Statistical Power and Minimum Sample Sizes - Exploring Conditional Probabilistic Queries - Exploring Full Latent Growth - Conducting Multi-Group Analyses - Assessing Measurement Invariance - Creating Analytic Composites.

-----------------------------------------------------------
Ned Kock
Symposium Chair
http://plsas.net

Data labels

In WarpPLS data labels can be added through the menu options “Add data labels from clipboard” and “Add data labels from file”. Data labels are text identifiers that are entered by you through these options, one column at a time.

Like the original numeric dataset, the data labels are stored in a table. Each column of this table refers to one data label variable, and each row to the corresponding row of the original numeric dataset.

Data labels can be shown on graphs (as illustrated above), either next to each data point that they refer to, or as part of the legend for a graph. The short video linked below illustrates this.

https://youtu.be/i5-_WIMXVl4

Once they have been added, data labels can be viewed or saved using the “View or save data labels” option.

Data labels can also be used to discover moderating effects, as discussed in the blog post linked below. They can also be used in multi-level analyses.

http://warppls.blogspot.com/2014/02/using-data-labels-to-discover.html

The use of data labels to discover moderating effects can be done in conjunction with the “Explore full latent growth” option, which provides a powerful alternative for the identification of moderating effects:

https://warppls.blogspot.com/2017/10/full-latent-growth.html