2
$\begingroup$

I first performed an Exploratory Factor Analysis (EFA) to identify the number of factors and the pattern of loadings. Then, using the same dataset (5165 observations), I conducted a Confirmatory Factor Analysis (CFA) to test the factor structure identified in the EFA.

I know that, ideally, EFA and CFA should be performed on separate samples (or on a split-sample) to avoid overfitting. However, I do not have a second, independent sample available. It is acceptable to perform both EFA and CFA on the same dataset?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
2
$\begingroup$

My position is that it is mostly pointless to run a CFA on the same data (sample) that the EFA solution was derived from because doing so does not allow you to adequately “confirm” (test) the factor solution. As you wrote, proper testing of an exploratory factor solution requires new or additional data. The same data set cannot be used for both exploration (discovery) and confirmation (testing). Goodness-of-fit tests in CFA are essentially meaningless when a factor solution is based on a previous EFA that was run on the same data set since the same information was already used to find this solution.

Improve this answer
$\endgroup$

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.