|
 |
EFA with categorical indicators |
 
|
Message/Author |
|
|
Hi, I have a quick question I was hoping you could please help me with. I have run an EFA on ordinal items from several different scales. The items are measured using different Likert scales (e.g., some are 5 point, some are 7 point etc.) and most of the items are positively skewed. I have used both WLSMV and ULSMV estimators and get the same results. I am finding that the items from each scale are sticking together and all loading onto their own factor (e.g., all the items from Scale 1 are loading onto one factor and all of the items for Scale 2 are loading onto a separate factor). Could this be a result of using different Likert scales (e.g., some 5 point and some 7 point)? Thank you in advance for your help, Chantal |
|
|
I don't think that would be the reason. |
|
Rong Jin posted on Wednesday, October 26, 2011 - 10:47 am
|
|
|
Linda: I am using EFA to analyze ordinal data. I wonder what warning messages reveal a improper solution? thank you, |
|
|
I'm not sure how to answer you. There are a variety of messages you can get for different reasons. If you have a question about a particular message, let me know. |
|
Back to top |
|
|