<abstract xmlns="http://www.w3.org/1999/xhtml"><p>A common problem with using different statistical packages for the same data and method is the risk of getting dissimilar results. While the reasons behind this outcome are often known and accepted, the negative consequences might be significant. In a teaching environment, usually involving toy models, with no practical implications, only a reputation risk is at stake. Nevertheless, students should be aware of such incongruities, their causes and possible solutions. Starting from these considerations, our paper addresses the differences that arise between R and WarpPLS while applying the Partial Least Squares Path Modelling (PLS-PM) method. To this end we estimate a PLS-PM model for analysing health-positioning data, compare the results and explain how the two statistical packages differ and complement each other in an attempt to derive the best fit for the data.</p></abstract>

A common problem with using different statistical packages for the same data and method is the risk of getting dissimilar results. While the reasons behind this outcome are often known and accepted, the negative consequences might be significant. In a teaching environment, usually involving toy models, with no practical implications, only a reputation risk is at stake. Nevertheless, students should be aware of such incongruities, their causes and possible solutions. Starting from these considerations, our paper addresses the differences that arise between R and WarpPLS while applying the Partial Least Squares Path Modelling (PLS-PM) method. To this end we estimate a PLS-PM model for analysing health-positioning data, compare the results and explain how the two statistical packages differ and complement each other in an attempt to derive the best fit for the data.

Should Students Trust their Instructors in Statistics? Differences in PLS Path Modelling while using WarpPLS and R

Proceedings of the International Conference on Applied Statistics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

A common problem with using different statistical packages for the same data and method is the risk of getting dissimilar results. While the reasons behind...

Should Students Trust their Instructors in Statistics? Differences in PLS Path Modelling while using WarpPLS and R

Data publikacji: 13 lut 2020

Zakres stron: 226 - 239

DOI: https://doi.org/10.2478/icas-2019-0020

Słowa kluczowe
statistical packages, R, WarpPLS, SEM, health-positioning data

© 2019 Elena Druică et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Should Students Trust their Instructors in Statistics? Differences in PLS Path Modelling while using WarpPLS and R

Data publikacji: 13 lut 2020

Zakres stron: 226 - 239

DOI: https://doi.org/10.2478/icas-2019-0020

Słowa kluczowestatistical packages, R, WarpPLS, SEM, health-positioning data

© 2019 Elena Druică et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Słowa kluczowe
statistical packages, R, WarpPLS, SEM, health-positioning data