Timeline for Is it reasonable/possible to use pre-scores as predictors of change?
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 17 at 18:49 | comment | added | EdM |
A problem is that the change score is necessarily correlated with the pre value. See this page and this page, for example.
|
|
| Jan 17 at 18:17 | answer | added | Christian Geiser | timeline score: 1 | |
| Jan 17 at 18:13 | comment | added | Christian Geiser | As mentioned by @ErikRuzek, a latent difference score approach would be preferred because the observed difference (change) score variable typically contains a lot of measurement error variance (unreliability). This can lead to substantial bias in the estimated b coefficient. The latent change score approach corrects for error. See also: youtu.be/0QUuP2BoMlk | |
| Jan 17 at 16:46 | comment | added | Erik Ruzek | Take a look at latent difference scores, which is a SEM technique. In that framework, you can predict the latent difference/change from T0 to T1 by levels of T0. See doi.org./10.1177/0265407517718387 and stats.stackexchange.com/questions/595777/… | |
| Jan 17 at 15:41 | comment | added | Peter Flom | Why not do a multilevel analysis? | |
| Jan 17 at 14:18 | history | edited | user405152 | CC BY-SA 4.0 |
edited body
|
| S Jan 17 at 14:16 | review | First questions | |||
| Jan 17 at 15:46 | |||||
| S Jan 17 at 14:16 | history | asked | user405152 | CC BY-SA 4.0 |