mvuorre / funky-firefly Goto Github PK

Find a good dataset that is sufficiently simple yet detailed enough to be useful. Optimally, this would include something like two one outcome and an additional covariate, so that we can model the outcome on the lagged outcome and another (time varying) covariate. Some basic longitudinal study, maybe a short experience sampling study, would be cool.

For my interests, it would be A+ if this involved (any kind of) well-being outcomes and some technology related predictor(s).

• Choose a dataset for the example analysis

We'll start with this (https://journals.sagepub.com/doi/pdf/10.1177/00936502211038196) but can swap if it turns out not suitable.

• Introduction
• Practical example / tutorial (
  • depends on #1, #2, #3
• Simulation study
• Conclusion
• Appendix A: A little bit of math (potentially best to keep math out of text, but give details here)

This might not be needed, the point of the manuscript is to make it easy and accessible anyway.

• Specify model

• Matti: Lead author (submission and correspondence, repo maintenance, etc)
• Matti: Introduction, Example analysis, Discussion
• @JoranTiU: Simulation study?

https://github.com/mvuorre/latent-mean-centering-ms/blob/224043dab2e9dc5c489d19680dd52d75d629c060/Generation_Code.r#L38

The data generation code (I turned it into a function) doesn't work currently as some variables are missing. @JoranTiU can you help with this?

My aim is to turn it into a function where we can vary the number of individuals and number of timepoints. We should be able to examine how the n_individuals and n_timepoints affect estimation in a typical observed mean centering vs latent mean centering models.

• Write function to simulate data from a simple two predictor multilevel model (e.g. model 4 in McNeish and Hamaker)
• Fix #6 (if needed after above)