latentFactoR (version 0.0.4)

estimate_dimensions: Estimates Dimensions using Several State-of-the-art Methods

Description

Estimates dimensions using Exploratory Graph Analysis (EGA), Empirical Kaiser Criterion (EKC), Factor Forest (factor_forest), Exploratory Factor Analysis with out-of-sample prediction (fspe), Next Eigenvalue Sufficiency Test (NEST), and parallel analysis (fa.parallel)

Usage

estimate_dimensions(
  data,
  sample_size,
  EGA_args = list(corr = "cor_auto", uni.method = "louvain", model = "glasso",
    consensus.method = "most_common", plot.EGA = FALSE),
  FF_args = list(maximum_factors = 8),
  FSPE_args = list(maxK = 8, rep = 1, method = "PE", pbar = FALSE),
  NEST_args = list(iterations = 1000, maximum_iterations = 500, alpha = 0.05, convergence
    = 1e-05),
  PA_args = list(fm = "minres", fa = "both", cor = "cor", n.iter = 20, sim = FALSE, plot
    = FALSE)
)

Value

Returns a list containing:

dimensions

Dimensions estimated from each method

A list of each methods output (see their respective functions for their outputs)

Arguments

data

Matrix or data frame. Either a dataset with all numeric values (rows = cases, columns = variables) or a symmetric correlation matrix

sample_size

Numeric (length = 1). If input into data is a correlation matrix, then specifying the sample size is required

EGA_args

List. List of arguments to be passed along to EGA. Defaults are listed

FF_args

List. List of arguments to be passed along to factor_forest. Defaults are listed

FSPE_args

List. List of arguments to be passed along to fspe. Defaults are listed

NEST_args

List. List of arguments to be passed along to NEST. Defaults are listed

PA_args

List. List of arguments to be passed along to fa.parallel. Defaults are listed

Author

Maria Dolores Nieto Canaveras <[e-mail]>, Alexander P. Christensen <[e-mail]>, Hudson Golino <[e-mail]>, Luis Eduardo Garrido <[e-mail]>

Examples

# Generate factor data
two_factor <- simulate_factors(
  factors = 2, # factors = 2
  variables = 6, # variables per factor = 6
  loadings = 0.55, # loadings between = 0.45 to 0.65
  cross_loadings = 0.05, # cross-loadings N(0, 0.05)
  correlations = 0.30, # correlation between factors = 0.30
  sample_size = 1000 # number of cases = 1000
)

if (FALSE) {
# Estimate dimensions
estimate_dimensions(two_factor$data)}