Search found 1284 matches
- Fri Aug 11, 2023 11:02 am
- Forum: Method and application
- Topic: Higher-order model: explained variance
- Replies: 3
- Views: 1631
Re: Higher-order model: explained variance
First, for a formative construct in PLS, regardless of it being higher-order or not, you will always have an r-squared of 1 (or at least very close to one). This is, because the indicators define (compose) the construct and thus they should and will explain all the variance of the construct because ...
- Tue Aug 08, 2023 7:22 am
- Forum: Method and application
- Topic: Consistent Bootstrapping
- Replies: 3
- Views: 2473
Re: Consistent Bootstrapping
I have updated the link. It was moved to a different section of the website during some restructuring process.
- Sun Aug 06, 2023 7:49 pm
- Forum: Literature
- Topic: Need some help with higher order literature
- Replies: 2
- Views: 3807
Re: Need some help with higher order literature
In Becker et al. (2023) we have a section on higher-order constructs where we summarize the latest advice on this topic. In addition, Sarstedt et al. (2019) is also a quite good an comprehensive source on this topic. Becker, J.-M., Cheah, J.-H., Gholamzade, R., Ringle, C.M. and Sarstedt, M. (2023), ...
- Sun Aug 06, 2023 7:45 pm
- Forum: SmartPLS 4 - Questions and answers
- Topic: Can SmartPLS4 create an interaction effect with the product indicator approach?
- Replies: 3
- Views: 2219
Re: Can SmartPLS4 create an interaction effect with the product indicator approach?
It was one of the first approaches that was proposed and it is also used in CB-SEM sometimes. However, latest PLS literature recommends the two-stage because it has been show in simulation studies that it is the overall best approach in a variety of models. To quote Becker et al. (2023) p.334: "...
- Fri Aug 04, 2023 8:11 pm
- Forum: SmartPLS 4 - Questions and answers
- Topic: Can SmartPLS4 create an interaction effect with the product indicator approach?
- Replies: 3
- Views: 2219
Re: Can SmartPLS4 create an interaction effect with the product indicator approach?
Why do you want to use the product-indicator approach? According to the literature the two-stage approach is almost always preferable over the product-indicator approach in PLS. Anyways you can also create the product indicators yourself outside of SmartPLS and import a datafile if you need them. Ho...
- Fri Aug 04, 2023 8:07 pm
- Forum: SmartPLS 4 - Questions and answers
- Topic: How to improve model fit indices in SmartPLS CB-SEM
- Replies: 2
- Views: 2685
Re: How to improve model fit indices in SmartPLS CB-SEM
If you specify the same model, you should get the same results. Otherwise, please contact our support (https://www.smartpls.com/support) and send the Amos and SmartPLS project files.
- Thu Jul 20, 2023 10:32 am
- Forum: Method and application
- Topic: Direct effect not significant, Indirect effect not significant, result total effect significant
- Replies: 3
- Views: 1754
Re: Direct effect not significant, Indirect effect not significant, result total effect significant
BTW: This is a really good paper on why dichotomization into significant and not significant is not a good idea: https://doi.org/10.1016/j.jbusres.2023.114086 Rigdon, E. E. (2023). How improper dichotomization and the misrepresentation of uncertainty undermine social science research. Journal of Bus...
- Thu Jul 20, 2023 10:21 am
- Forum: Method and application
- Topic: Direct effect not significant, Indirect effect not significant, result total effect significant
- Replies: 3
- Views: 1754
Re: Direct effect not significant, Indirect effect not significant, result total effect significant
Significance is a strange concept that is also often criticized because of its dichotomous nature. Yes/no In laymen terms (and not 100% correct): What you actually want to know is whether your effect is strong enough given the sampling uncertainty that you have to conclude that is is likely differen...
- Thu Jul 20, 2023 10:10 am
- Forum: SmartPLS 4 - Questions and answers
- Topic: problem in creating groups
- Replies: 1
- Views: 1795
Re: problem in creating groups
If your categorical / grouping variable is missing in the generated data file, you need to select it under "Other" to have it also available in the generated data file.
If the problem persist, please contact our technical support: https://www.smartpls.com/support
If the problem persist, please contact our technical support: https://www.smartpls.com/support
- Thu Jul 20, 2023 10:07 am
- Forum: SmartPLS 4 - Questions and answers
- Topic: How to use indicators with different scale types on one variable?
- Replies: 2
- Views: 1909
Re: How to use indicators with different scale types on one variable?
In general, the PLS algorithm assumes metric or quasi metric data. If you do not have such data for all indicators, it does not make much sense to combine them into a construct, because the constructs will also have a metric representation. If you think that your ordinal scale satisfies quasi metric...
- Thu Jun 22, 2023 8:06 pm
- Forum: SmartPLS 4 - Requested features
- Topic: Reduce file size of Bootstrapped Results
- Replies: 2
- Views: 5101
Re: Reduce file size of Bootstrapped Results
Thank you for the suggestion. In the next release there will be an option "Generate results per sample" in Bootstrapping and Permutation. Without this option we will not save all the results, but only the overview statistics.
- Sun Jun 18, 2023 7:19 pm
- Forum: Method and application
- Topic: Single indicator for the variable observed
- Replies: 3
- Views: 5207
Re: Single indicator for the variable observed
Single indicator construct have a fixed weight and loading of 1. As Christian has said previously: You can ignore the outer relationship of the single indicator construct. The latent variable and the indicator are identical. Thus, there is no variance and therefore also no t or p-values to calculate...
- Sun Jun 18, 2023 7:17 pm
- Forum: Method and application
- Topic: SmartPLS moderation and MGA interpretation
- Replies: 6
- Views: 6394
Re: SmartPLS moderation and MGA interpretation
The groups do not need to be equal. However, it can cause problems if the groups are very imbalanced and one group is extremely small (<=10%).
In addition, if you do MGA, your smallest group should still fulfill the minimum sample size requirements.
In addition, if you do MGA, your smallest group should still fulfill the minimum sample size requirements.
- Sun Jun 18, 2023 7:14 pm
- Forum: SmartPLS 4 - Questions and answers
- Topic: NaN values in outerloadings of single indicator construct categorical variable.
- Replies: 1
- Views: 3135
Re: NaN values in outerloadings of single indicator construct categorical variable.
Yes. Single indicator construct have a fixed weight and loading of 1. Thus, there is no variance and therefore also no t or p-values to calculate. The t and p-value are just not defined and therefore reporting them is also not meaningful. We have updated this in the recent version of SmartPLS to bet...
- Sun Jun 18, 2023 7:11 pm
- Forum: SmartPLS 4 - Questions and answers
- Topic: AIC in Smart PLS 4 and Model Selection Crieria
- Replies: 1
- Views: 2252
Re: AIC in Smart PLS 4 and Model Selection Crieria
Yes, based on the literature, the BIC and the and GM (Geweke–Meese criterion) are best for model selection and all other criteria are not well suited. SmartPLS does not include the Geweke–Meese criterion (GM), which is based on the model-complexity adjusted mean square error (MSE) from a saturated (...