Timeline for Structural equation modelling: model selection
Current License: CC BY-SA 3.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 9, 2014 at 13:13 | comment | added | Robbie | Thanks for your elaborate answer. The problem with SEM is that forward as well as backward selection do not seem to be appropriate according the theory. SEM basically assumes that one has an a priori defined model that should fit the data. Any changes to this a priori hypothesized model should be as minimal as possible. The problem rises with comparing these adjusted models. There are several measures of model fit which can be compared but also AICs and BICs. A model with a lower AIC doesn't necessarily have to be a better fit when looking at the chi-square, RMSEA or CFI. | |
| Dec 5, 2014 at 6:51 | history | answered | pe-perry | CC BY-SA 3.0 |