|
Message/Author |
|
|
In regards to setting the target loadings, Asparouhov & Muthén (2009) state "Not all entries in matrix B need to be specified. For identification purposes at least m - 1 entries have to be specified in each column for oblique rotation..." My question is whether it is OK to specify not just m-1 but all entries as in the example below where I set all the cross-loadings to ~0. ANALYSIS: rotation = target; MODEL: Physic by agg2 agg3 agg9 agg18 agg20 agg21 agg22 agg26 agg28r agg1~0 agg5~0 agg8~0 agg25~0 agg29~0 agg6~0 agg11~0 agg13~0 agg14~0 agg15~0 agg17~0 agg23r~0 agg4~0 agg7~0 agg10~0 agg12~0 agg16~0 agg24~0 agg27~0 (*1); Thank you. |
|
|
I think so. The more targets the better the rotation identification (and possibly smaller standard errors). |
|
Back to top |
|
|