Skip to contents

Fit a confirmatory factor model with matched correlation-structure WLS when sampling covariance is available, or explicitly fit the pooled matrix descriptively.

Usage

cfa_from_synthesis(
  mars_object,
  model,
  num_obs = NULL,
  method_null = "sem",
  synthesis_method = c("model", "average", "weighted"),
  synthesis_transform = c("none", "fisher_z"),
  missing_corr = c("available", "pairwise", "em"),
  attenuation = c("none", "correct"),
  reliability = NULL,
  reliability_missing = c("error", "skip", "impute_mean", "assume_1"),
  pd_adjust = c("none", "eigen_clip", "nearpd"),
  pd_tol = 1e-08,
  fit_method = c("auto", "wls", "descriptive"),
  se_method = c("delta", "simulation", "bootstrap"),
  vcov_source = c("model", "robust"),
  se_draws = 1000L,
  se_seed = NULL,
  ...
)

# S3 method for class 'cfa_mars'
print(x, ...)

Arguments

mars_object

A fitted object returned by mars.

model

Lavaan-style latent model syntax.

num_obs

Optional size for internal conditional calculations. It does not enable fit tests for synthesized correlations.

method_null

Null model method passed to path_model.

synthesis_method

Correlation synthesis method: "model", "average", or "weighted".

synthesis_transform

Optional pooling transform for "average"/"weighted": "none" or "fisher_z".

missing_corr

Missing-correlation handling for synthesized matrices. One of "available", "pairwise", or "em".

attenuation

Attenuation-correction mode for synthesized correlations. One of "none" or "correct".

reliability

Reliability input used when attenuation = "correct".

reliability_missing

Strategy for missing reliability values. One of "error", "skip", "impute_mean", or "assume_1".

pd_adjust

Positive-definite repair for synthesized correlations: "none", "eigen_clip", or "nearpd".

pd_tol

Minimum eigenvalue tolerance used by pd_adjust = "eigen_clip".

fit_method

"auto" selects "wls" when matched pooled-correlation sampling covariance is available, otherwise "descriptive". Explicit WLS requires finite symmetric positive-definite sampling covariance. Singular weights cause an error; they are not silently regularized.

se_method

"delta" uses expected WLS information for a WLS fit, or propagates the full correlation covariance through observed-variable descriptive regression coefficients. Descriptive latent delta SEs are withheld. "simulation" refits draws from the joint normal approximation to the pooled correlations; "bootstrap" refits named correlation draws or resamples independent studies/clusters and refits the original synthesis. Resampling requires at least 50 admissible fits and an 80 percent success rate. Failure counts and source-bootstrap diagnostics are returned.

vcov_source

Source of pooled-correlation uncertainty. "model" uses the model-based covariance and "robust" uses the selected cluster-robust covariance stored in the MARS fit.

se_draws

Number of draws/resamples used when se_method = "simulation" or "bootstrap".

se_seed

Optional random seed for se_method.

...

Additional arguments passed to downstream methods.

x

An object of class "cfa_mars".

Value

A path object with additional class cfa_mars.

Details

See path_model() for the WLS objective, unit-variance constraints, expected-information uncertainty, global tests and supported syntax. The default provides WLS loading SEs when matched uncertainty is available. Descriptive latent delta SEs and single-sample global fit tests are withheld. Outputs distinguish marker-scaled raw loadings from standardized loadings; a raw loading above one is not by itself an inadmissible solution.

Examples

d <- data.frame(ID=1:5,N=200,x2_x1=.56,x3_x1=.42,x4_x1=.63,
                x3_x2=.48,x4_x2=.72,x4_x3=.54)
fit <- mars(d,studyID="ID",effectID="numID",sample_size="N",
  effectsize_type="cor",varcov_type="weighted",estimation_method="FE",
  variable_names=c("x2_x1","x3_x1","x4_x1","x3_x2","x4_x2","x4_x3"))
cfa <- cfa_from_synthesis(fit,"F =~ x1+x2+x3+x4")
cfa$standardized_loadings
#>   factor indicator   loading standardized_loading standardized_se
#> 1      F        x1 1.0000000            0.6999989      0.01887115
#> 2      F        x2 1.1428589            0.8000000      0.01529688
#> 3      F        x3 0.8571438            0.5999997      0.02263121
#> 4      F        x4 1.2857163            0.9000000      0.01261573
#>   standardized_ci_lower standardized_ci_upper
#> 1             0.6630121             0.7369857
#> 2             0.7700187             0.8299813
#> 3             0.5556434             0.6443561
#> 4             0.8752737             0.9247264
cfa$fit_measures$Model
#>         Chi2           df       pvalue 
#> 3.427431e-09 2.000000e+00 1.000000e+00