Learn R Programming

nFactors (version 2.3.1)

nFactors-parameters: Argument and Value Parameters Common to the Different Functions Available in Package nFactors

Description

This help file describes the argument and value parameters used in the different functions available in package nFactors. Arguments:
  1. adequacy:
{ logical: if TRUE print the recovered population matrix from the factor structure (structureSim)} alpha:{ numeric: statistical significance level (nBartlett, nBentler)} aparallel:{ numeric: results of a parallel analysis (nScree) } cent:{ depreciated numeric (use quantile instead): quantile of the distribution (moreStats, parallel)} communalities:{ character: initial values for communalities ("component", "ginv", "maxr", or "multiple") (iterativePrincipalAxis, principalAxis)} cor:{ logical: if TRUE computes eigenvalues from a correlation matrix, else from a covariance matrix (eigenComputes, nBartlett, nBentler, nCng, nMreg, nScree, nSeScree)} correction:{ logical: if TRUE use a correction for the degree of freedom after the first eigenvalue (nBartlett)} criteria:{ numeric: by default fixed at $\hat{\lambda}$. When the $\lambda$s are computed prom a principal components analysis on a correlation matrix, it correspons to the usual Kaiser $\lambda >= 1$ rule. On a covariance matrix or from a factor analysis, it is simply the mean. To apply the $\lambda >= 0$ sometimes used with factor analysis, fixed the criteria to $0$ (nScree)} details:{ logical: if TRUE also return detains about the computation for each eigenvalues (nBartlett, nBentler, nCng, nMreg, structureSim)} diagCommunalities:{ logical: if TRUE, the correlation between the initial solution and the estimated one will use a correlation of one in the diagonal. If FALSE (default) the diagonal is not used in the computation of this correlation or covariance matrix (rRecovery)} eig:{ depreciated parameter (use x instead): Eigenvalues to analyse (nScree, plotParallel)} Eigenvalue:{ depreciated parameter (use x instead): eigenvalues to analyse (plotuScree)} fload:{ matrix: loadings of the factor structure (structureSim)} graphic:{ logical: specific plot (bentlerParameters, structureSim)} index:{ numeric: vector of the index of the selected indices (plot.structureSim, print.structureSim, summary.structureSim} iterations:{ numeric: maximum number of iterations to obtain a solution (iterativePrincipalAxis)} legend:{ Logical indicator of the presence or not of a legend (plotnScree, plotParallel) } loadings:{ numeric: loadings from a factor analysis solution (rRecovery, generateStructure)} log:{ logical: if TRUE does the minimization on the log values (bentlerParameters, nBentler)} main:{ character: main title (plotnScree, plotParallel, plotuScree, boxplot.structureSim, plot.structureSim) } maxPar:{ numeric: maximums for the coefficient of the linear trend to minimize (bentlerParameters, nBentler)} minPar:{ numeric: minimums for the coefficient of the linear trend to minimize (bentlerParameters, nBentler)} method:{ character: actually only "giv" is supplied to compute the approximation of the communalities by maximum correlation (corFA, nCng, nMreg, nScree, nSeScree)} mjc:{ numeric: number of major factors (factors with practical significance) (generateStructure) } pmjc:{ numeric: number of variables that load significantly on each major factor (generateStructure)} model:{ character: "components" or "factors" (nScree, parallel, plotParallel, plotuScree, structureSim, eigenBootParallel, eigenBootParallel)} N:{ numeric: number of subjects (nBartlett, bentlerParameters, nBentler)} nboot:{ numeric: number of bootstrap samples (eigenBootParallel) } nFactors:{ numeric: number of components/factors to retained (componentAxis, iterativePrincipalAxis, principalAxis, bentlerParameters, boxplot.structureSim)} nScree:{ results of a previous nScree analysis (plotnScree)} option:{ character: "permutation" or "bootstrap" (eigenBootParallel)} object:{ nScree: an object of the class nScree is.nScree, summary.nScree } object:{ structureSim: an object of the class structureSim (is.structureSim, summary.structureSim)} parallel:{ numeric: vector of the result of a previous parallel analysis (plotParallel)} pmjc:{ numeric: number of major loadings on each factor factors (generateStructure) } quantile:{ numeric: quantile that will be reported (parallel, moreStats, eigenBootParallel, structureSim) } R:{ numeric: correlation or covariance matrix (componentAxis, iterativePrincipalAxis, principalAxis, principalComponents, rRecovery, corFA)} r2limen:{ numeric: R2 limen value for the R2 index of Nelson (structureSim, nSeScree)} rep:{ numeric: number of replications of the correlation or the covariance matrix (default is 100) (parallel)} reppar:{ numeric: number of replication for the parallel analysis (structureSim)} repsim:{ numeric: number of replication of the matrix correlation simulation (structureSim)} resParx:{ numeric: restriction on the $\alpha$ coefficient (x) to graph the function to minimize (bentlerParameters)} resolution:{ numeric: resolution of the 3D graph (number of points from $\alpha$ and from $\beta$).} resPary:{ numeric: restriction on the $\beta$ coefficient (y) to graph the function to minimize (bentlerParameters)} sd:{ numeric: vector of standard deviations of the simulated variables (for a parallel analysis on a covariance matrix) parallel)} show:{ logical: if TRUE print the quantile choosen (moreStats) } subject:{ numeric: number of subjects (default is 100) (parallel)} tolerance:{ numeric: minimal difference in the estimated communalities after a given iteration (iterativePrincipalAxis)} typePlot:{ character: plot the minimized function according to a 3D plot: "wireframe", "contourplot" or "levelplot" (bentlerParameters)} unique:{ numeric: loadings on the non significant variables on each major factor (generateStructure) } upper:{ logical: if TRUE the upper diagonal is replaced with the lower diagonal. If FALSE, lower diagonal is replaced with upper diagonal (diagReplace)} use:{ character: how to deal with missing values, same as the parameter from the corr function (eigenBootParallel) } var:{ numeric: number of variables (default is 10) (parallel, generateStructure) } vLine:{ character: color of the vertical indicator line in the eigen boxplot (boxplot.structureSim)} x:{ numeric: a vector of eigenvalues, a matrix of correlations or of covariances or a data.frame of data (eigenFrom, nBartlett, nCng, nMreg)} xlab:{ character: label of the x axis (plotnScree, plotParallel, plotuScree, boxplot.structureSim)} x:{ data.frame: data from which a correlation or covariance matrix will be obtained (eigenBootParallel)} x:{ DEPRECIATED: (plotParallel)} x:{ nScree: an object of the class nScree (plot.nScree, print.nScree)} x:{ numeric: matrix (makeCor)} x:{ numeric: matrix or data.frame (moreStats)} x:{ structureSim: an object of the class structureSim (boxplot.structureSim, plot.structureSim, print.structureSim)} ylab:{ character: label of the y axis (plotnScree, plotParallel, plotuScree, boxplot.structureSim) }

Arguments

emph

Values

enumerate

  1. cor:

code

componentAxis, iterativePrincipalAxis, principalAxis, principalComponents

item

  • details:
  • difference:
  • iterations:
  • loadings:
  • nFactors:
  • R:
  • recoveredR:
  • tolerance:
  • values:
  • values:
  • values:
  • values:
  • values:
  • values:
  • values:
  • values:
  • varExplained:
  • varExplained:

References

Raiche, G., Riopel, M. and Blais, J.-G. (2006). Non graphical solutions for the Cattell's scree test. Paper presented at the International Annual meeting of the Psychometric Society, Montreal. [http://www.er.uqam.ca/nobel/r17165/RECHERCHE/COMMUNICATIONS/]

See Also

Other packages are also very useful for principal components and factor analysis. The R psychometric view is instructive at this point. See http://cran.stat.sfu.ca/web/views/Psychometrics.html for further details.