The bivariate latent change score models are useful to explore the dynamic relationship between two variables. However, it can be difficult to interpret the results when both level-to-change and change-to-change relationships are included and their effects are in different directions, just like the following picture:
In this situation, I find that a plot of predicted trajectories, just like what Brake et al (2018) does, is helpful to interpret this complex dynamic relationships. I hope that this function can be included in the LCSM package.
Brake, Hendrik J. van de, Frank Walter, Floor A. Rink, Peter J. M. D. Essens, and Gerben S. van der Vegt. 2018. ‘The Dynamic Relationship between Multiple Team Membership and Individual Job Performance in Knowledge-Intensive Work’. Journal of Organizational Behavior 39 (9): 1219–31. https://doi.org/10.1002/job.2260.
The bivariate latent change score models are useful to explore the dynamic relationship between two variables. However, it can be difficult to interpret the results when both level-to-change and change-to-change relationships are included and their effects are in different directions, just like the following picture:![image](https://github.com/milanwiedemann/lcsm/assets/42795195/c2b573c0-4552-4247-bd80-1a4b81e11972)
In this situation, I find that a plot of predicted trajectories, just like what Brake et al (2018) does, is helpful to interpret this complex dynamic relationships. I hope that this function can be included in the LCSM package.![image](https://github.com/milanwiedemann/lcsm/assets/42795195/c5c8de69-66e0-468e-80bf-558f167aa2fc)
Brake, Hendrik J. van de, Frank Walter, Floor A. Rink, Peter J. M. D. Essens, and Gerben S. van der Vegt. 2018. ‘The Dynamic Relationship between Multiple Team Membership and Individual Job Performance in Knowledge-Intensive Work’. Journal of Organizational Behavior 39 (9): 1219–31. https://doi.org/10.1002/job.2260.
Thank you!