Dear everyone,
My hypothesize model can be described as follows: consists of two latent exogenous, one latent endogenous and one dichotomous dependent (yes/no) (sorry I used the term "dependent variable" for a variable that is not affected by any variables in the model and it caused only by the exogenous and endogenous variables); the endogenous variable is caused directly by each of the exogenous variables, while the dependent is caused directly by each of the exogenous and endogenous; the two exogenous are correlated; and each of the exogenous and endogenous consist of six sub-factors with number of items (7-point scale) ranging between 5 and 15. Thus, the model is too large and the sample size of 329, I think, is inadequate for the model.
My remedy is to use the parceling approach. For each subfactor, I will parcel all the items into a single parcel then each parcel will represent the subfactor; thus, each of the exogenous and endogenous will have six indicators where the indicators are the parcels.
My questions: (1) Is it required that the items should be significantly loaded to the corresponding subfactor before I will do the parceling? (2) What estimation approach is appropriate for my model considering that the dependent is dichotomous? I am using AMOS.
Thank you in advance for your help.
Eins |
| Free forum by Nabble | Edit this page |