constructPca: Principal component analysis (PCA) of inter-construct...

In OpenRepGrid: Tools to Analyze Repertory Grid Data

Principal component analysis (PCA) of inter-construct correlations.

Description

Various methods for rotation and methods for the calculation of the correlations are available. Note that the number of factors has to be specified. For more information on the PCA function itself type ?principal.

Usage

constructPca(
  x,
  nfactors = 3,
  rotate = "varimax",
  method = "pearson",
  trim = NA
)

Arguments

x	repgrid object.
nfactors	Number of components to extract (default is 3).
rotate	"none", "varimax", "promax" and "cluster" are possible rotations (default is none).
method	A character string indicating which correlation coefficient is to be computed. One of "pearson" (default), "kendall" or "spearman", can be abbreviated. The default is "pearson".
trim	The number of characters a construct is trimmed to (default is 7). If NA no trimming occurs. Trimming simply saves space when displaying correlation of constructs with long names.

Value

Returns an object of class constructPca.

References

Fransella, F., Bell, R. & Bannister, D. (2003). A Manual for Repertory Grid Technique (2. Ed.). Chichester: John Wiley & Sons.

See Also

To extract the PCA loadings for further processing see constructPcaLoadings.

Examples

## Not run: 

   constructPca(bell2010)
   
   # data from grid manual by Fransella et al. (2003, p. 87)
   # note that the construct order is different
   constructPca(fbb2003, nfactors=2)

   # no rotation
   constructPca(fbb2003, rotate="none")
   
   # use a different type of correlation (Spearman)
   constructPca(fbb2003, method="spearman")
   
   # save output to object           
   m <- constructPca(fbb2003, nfactors=2)
   m
   
   # different printing options
   print(m, digits=5)
   print(m, cutoff=.3)
   

## End(Not run)

OpenRepGrid documentation built on May 31, 2023, 5:33 p.m.