qgraph.loadings
This function is a wrapper function for qgraph designed to visualize factor loadings.
qgraph.loadings( fact, ...)
fact |
A matrix containing factor loadings (items per row, factors per column) or an "loadings" object |
... |
Additional optional arguments passed to |
If "default" a standard layout for factor models will be made. If this is "circle" the default layout is circled (factors in the centre, items at the edge). No other layouts are currently supported.
A vector where the first value indicates the size of manifest variables and the second value indicates the size of latent variables.
"reflective" to have arrows go to manifest variables, "formative" to have arrows go to latent variables or "none" (default) for no arrows
Logical, if TRUE then for each manifest variable the strongest loading is omitted (default to FALSE).
An optional list containing the measurement model, see qgraph
When there is only one factor, this is it's name. If there are more factors, the names in the groups list are used only if the factors can be identified.
Values for the residuals
Size of the residuals, defaults to 0.1
Correlation matrix of the factors
Sacha Epskamp (mail@sachaepskamp.com)
Sacha Epskamp, Angelique O. J. Cramer, Lourens J. Waldorp, Verena D. Schmittmann, Denny Borsboom (2012). qgraph: Network Visualizations of Relationships in Psychometric Data. Journal of Statistical Software, 48(4), 1-18. URL http://www.jstatsoft.org/v48/i04/.
## Not run: # Load big5 dataset: data(big5) data(big5groups) big5efa <- factanal(big5,factors=5,rotation="promax",scores="regression") big5loadings <- loadings(big5efa) qgraph.loadings(big5loadings,groups=big5groups,rotation="promax",minimum=0.2, cut=0.4,vsize=c(1.5,15),borders=FALSE,vTrans=200) # Tree layout: qgraph.loadings(big5loadings,groups=big5groups,rotation="promax",minimum=0.2, cut=0.4,vsize=c(1.5,15),borders=FALSE,vTrans=200, layout="tree",width=20,filetype="R") ## End(Not run)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.