Search found 1282 matches

by jmbecker
Tue Dec 05, 2023 1:25 pm
Forum: SmartPLS 4 - Questions and answers
Topic: Which one is my Beta value, standard error?
Replies: 1
Views: 2182

Re: Which one is my Beta value, standard error?

In the bootstrapping the original sample estimate is the beta from the original model. The standard deviation of the bootstrap distribution is the estimated standard error of the parameter. Accordingly, you may calculate t values from dividing the original estimate (the beta) by the standard deviati...
by jmbecker
Mon Dec 04, 2023 2:16 pm
Forum: SmartPLS 4 - Questions and answers
Topic: Subtraction of two latent variables
Replies: 1
Views: 1983

Re: Subtraction of two latent variables

You can use the latent variable scores from the PLS algorithm estimation to calculate your difference score. However, there is quite some body of literature showing that difference scores are suboptimal and quite constrained and that you can actually better model the variables separately. This has n...
by jmbecker
Tue Nov 28, 2023 2:37 pm
Forum: Method and application
Topic: CONFIDENCE INTERVALS FOR MEDIATED PROPORTIONS
Replies: 8
Views: 3493

Re: CONFIDENCE INTERVALS FOR MEDIATED PROPORTIONS

In the main menu of SmartPLS you find the "Preferences" and there you can set how many decimals you want to display in the reports.
by jmbecker
Mon Nov 27, 2023 8:45 am
Forum: Method and application
Topic: CONFIDENCE INTERVALS FOR MEDIATED PROPORTIONS
Replies: 8
Views: 3493

Re: CONFIDENCE INTERVALS FOR MEDIATED PROPORTIONS

You cannot simply divide the confidence interval bounds. You need to do the division for each subsample. If you have used, for example, 10000 bootstrap samples, you need to copy all these 10000 samples (for example to Excel) and then divide the total indirect effect by the total effect. For these 10...
by jmbecker
Thu Nov 23, 2023 7:11 pm
Forum: Method and application
Topic: CONFIDENCE INTERVALS FOR MEDIATED PROPORTIONS
Replies: 8
Views: 3493

Re: CONFIDENCE INTERVALS FOR MEDIATED PROPORTIONS

In the Bootstrapping Output you can get the results for each bootstrapping subsample (check the box in the settings where it says "generate results per sample"). The you will get the results for all path coefficients, total effects, etc. under Algorithm > Samples > ... You can copy these t...
by jmbecker
Thu Nov 23, 2023 2:40 pm
Forum: SmartPLS 4 - Questions and answers
Topic: Interpret Moderation Analysis
Replies: 1
Views: 2572

Re: Interpret Moderation Analysis

The p-values for the interaction terms (Age x ... --> BI) are all above 0.05. Most researchers would conclude from that there is no significant interaction (i.e., no moderation); i.e. rejecting your hypothesis. The more substantive interpretation of the simple slopes graph would be that the TOI effe...
by jmbecker
Mon Nov 13, 2023 7:52 am
Forum: Method and application
Topic: Is it appropiate to run pls sem individually on each independent variable to see the impact on 2 Dvs and 2 serial mediat
Replies: 2
Views: 1443

Re: Is it appropiate to run pls sem individually on each independent variable to see the impact on 2 Dvs and 2 serial me

Usually, I would include both DVs into one model, if there are no other data problems that would complicate such an analysis. The model can build on the larger nomological network to estimate the composite scores and relations, which should make it more reliable. However, if it is just the same pred...
by jmbecker
Wed Oct 25, 2023 1:06 pm
Forum: Method and application
Topic: IPMA analysis & non-significant structural path
Replies: 2
Views: 1443

Re: IPMA analysis & non-significant structural path

You should first evaluate your measurement and structural model with the usual steps. It only makes sense to run IPMA on a valid model. You usually do not delete insignificant paths. The idea of the analysis is to map importance and performance of your predictors. Non-significant predictors are not ...
by jmbecker
Wed Oct 25, 2023 1:02 pm
Forum: Method and application
Topic: Moderation and mediation
Replies: 3
Views: 1554

Re: Moderation and mediation

Usually you want to keep them separated but all include them in one model.

However, sometimes it also may make sense to estimate different models. It really depends on what you want to test and what you want to understand.
by jmbecker
Wed Oct 25, 2023 1:00 pm
Forum: SmartPLS 4 - Questions and answers
Topic: predicted values of y in SmartPLS 4
Replies: 2
Views: 1814

Re: predicted values of y in SmartPLS 4

Sure. You can use the estimated LV scores for the independent construct and calculate within-sample predictions for the dependent construct using the path coefficients.

You can also create out-of-sample predictions using k-fold cross-validation using PLSPredict.
by jmbecker
Sat Oct 14, 2023 7:10 pm
Forum: Method and application
Topic: MGA for more than two groups
Replies: 4
Views: 1735

Re: MGA for more than two groups

The OTG approach does not work properly. I think they also refer to sources have have found this. In addition, the question is also whether such an omnibus test is actually helpful. Do you want to know that your three groups are on average somehow different, or do you want to know between which grou...
by jmbecker
Sat Oct 14, 2023 6:58 pm
Forum: Method and application
Topic: p-value adjustment: 0.05 to 0.0169524 when executing the permutation test
Replies: 5
Views: 1789

Re: p-value adjustment: 0.05 to 0.0169524 when executing the permutation test

First, whether you use Sidak or Bonferroni is your choice that you need to justify. I have not seen clear evidence that the one is always superior over the other. I was using Bonferoni, because it simplified the example as it is much simpler to calculate. What you put in the significance field in Sm...
by jmbecker
Sat Oct 14, 2023 6:49 pm
Forum: SmartPLS 4 - Questions and answers
Topic: p-value in CB-SEM Model fit table
Replies: 2
Views: 1709

Re: p-value in CB-SEM Model fit table

The p-value in the fit table in CB-SEM is the chi-square test of model fit. This indicates that the model-implied and observed covariance/correlation matrix significantly differ. Is this a problem? It depends on the viewpoint. Certainly, you want a good fitting model. However, this test is very sens...
by jmbecker
Fri Oct 13, 2023 7:11 am
Forum: Method and application
Topic: p-value adjustment: 0.05 to 0.0169524 when executing the permutation test
Replies: 5
Views: 1789

Re: p-value adjustment: 0.05 to 0.0169524 when executing the permutation test

To be honest, I don't understand what you mean with "the significance level automatically changes from 0.017 to 0.02." If you run a (preferably permutation-based MGA), you will get a p-value for the difference in parameter between groups. You usually conclude that the difference is signifi...
by jmbecker
Fri Oct 13, 2023 6:56 am
Forum: Method and application
Topic: MGA for more than two groups
Replies: 4
Views: 1735

Re: MGA for more than two groups

I think this would be the perfect reference for you: https://www.sciencedirect.com/science/article/pii/S0148296322010049 Cheah, J. H., Amaro, S., & Roldán, J. L. (2023). Multigroup analysis of more than two groups in PLS-SEM: A review, illustration, and recommendations. Journal of Business Resea...