Dear R Users, I'm wondering how is it possible to get |factor loadings| <1 in factor analysis model (factanal) performing maximum-likelihood estimation. Is it caused by some constraints? If so, what kind of constraints are placed and when (during the estimation or after)? Robert
factor analysis - constraints
2 messages · Robert Ruser, Peter Dalgaard
On Apr 19, 2011, at 13:58 , Robert Ruser wrote:
Dear R Users, I'm wondering how is it possible to get |factor loadings| <1 in factor analysis model (factanal) performing maximum-likelihood estimation. Is it caused by some constraints? If so, what kind of constraints are placed and when (during the estimation or after)?
factanal() works with the correlation matrix, so you cannot have a valid factor model otherwise. Non-negative uniquenesses (aka specific variances) are ensured by constraints in the estimation algorithm. You do not infrequently see cases where the uniqueness is being set to its limit of 0.005 (Heywood cases)
Robert
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Peter Dalgaard Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd.mes at cbs.dk Priv: PDalgd at gmail.com