Timeline for P values non-significant but Monte Carlo confidence interval does not contain zero for indirect effects
Current License: CC BY-SA 4.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 12 at 9:58 | comment | added | Terrence | Yes, MLM is the shortcut for a nonnormality correction. MLR is too, but using a diffferent method that cooperates with FIML estimation of incomplete data. As I said, MLM is more efficient. | |
| Jun 12 at 7:06 | comment | added | Dale | Hi Terrence, thank you for the explanation and suggestion. I greatly appreciate your help! My data was not normally distributed, so I used MLR. But my data has 'complete data' after implementing multiple imputations. In this case, would you still recommend using MLM? | |
| Jun 11 at 20:42 | history | answered | Terrence | CC BY-SA 4.0 |