psymetrics

The goal of psymetrics is to provide tools for extracting and visualizing psychometric model fit indices. It is compatible with models created using packages like lavaan, psych, and mirt.

Installation

You can install the development version of psymetrics from GitHub with:

# install.packages("pak")
pak::pak("brianmsm/psymetrics@v0.1.3")

Getting Fit Indices

Here is an example of how to use the psymetrics package with a model created using lavaan.

library(psymetrics)
library(lavaan)
#> This is lavaan 0.6-18
#> lavaan is FREE software! Please report any bugs.

# Define a simple CFA model
model <- 'visual  =~ x1 + x2 + x3
          textual =~ x4 + x5 + x6
          speed   =~ x7 + x8 + x9'

# Fit the model using lavaan
fit <- cfa(model, data = HolzingerSwineford1939, estimator = "MLR")

# Extract and print fit indices
model_fit(fit)
#> NOBS | ESTIMATOR | NPAR | Chi2(24) | p (Chi2) |  CFI  |  TLI  | RMSEA |   RMSEA  CI    | SRMR 
#> ----------------------------------------------------------------------------------------------
#> 301  |    MLR    |  21  |  87.132  |  < .001  | 0.925 | 0.888 | 0.093 | [0.073, 0.115] | 0.065

# You can also request specific types of indices, such as 'robust'
model_fit(fit, type = "robust")
#> NOBS | ESTIMATOR | NPAR | Chi2(24) | p (Chi2) |  CFI  |  TLI  | RMSEA |   RMSEA  CI    | SRMR 
#> ----------------------------------------------------------------------------------------------
#> 301  |    MLR    |  21  |  87.132  |  < .001  | 0.930 | 0.895 | 0.092 | [0.072, 0.114] | 0.065

# Or specify which indices to extract
model_fit(fit, metrics = c("cfi", "tli"))
#> cfi and tli were adjusted to their scaled version.
#> If you want to control the specific metric type used, specify it explicitly
#> (e.g., `cfi.robust`) or modify the type argument.
#> NOBS | ESTIMATOR | NPAR |  CFI  |  TLI 
#> ---------------------------------------
#> 301  |    MLR    |  21  | 0.925 | 0.888

This example demonstrates how to extract and print various fit indices from a confirmatory factor analysis (CFA) model using psymetrics. You can choose between standard, scaled, or robust fit indices, and even specify custom sets of indices to extract.

Comparing Fit Indices

fit_1 <- cfa(model, data = HolzingerSwineford1939, estimator = "MLR")
fit_2 <- cfa(model, data = HolzingerSwineford1939, estimator = "ULSM")

fit_table <- compare_model_fit(fit_1, fit_2)
fit_table
#> MODEL | NOBS | ESTIMATOR | NPAR | Chi2(24) | p (Chi2) |  CFI  |  TLI  | RMSEA |   RMSEA  CI    | SRMR 
#> ------------------------------------------------------------------------------------------------------
#> fit_1 | 301  |    MLR    |  21  |  87.132  |  < .001  | 0.925 | 0.888 | 0.093 | [0.073, 0.115] | 0.065
#> fit_2 | 301  |   ULSM    |  21  |  90.600  |  < .001  | 0.931 | 0.897 | 0.096 | [0.073, 0.120] | 0.059

In this example, compare_model_fit is used to compare the fit indices of two different models. This function allows you to easily see the differences in model fit across different estimation methods or model specifications.

Print the fit indices in HTML format

This is useful when you want to embed the output directly in HTML reports or web pages.

print(fit_table, format = "html")

MODEL	NOBS	ESTIMATOR	NPAR	Chi2(24)	p (Chi2)	CFI	TLI	RMSEA	RMSEA CI	SRMR
fit_1	301	MLR	21	87.132	< .001	0.925	0.888	0.093	[0.073, 0.115]	0.065
fit_2	301	ULSM	21	90.600	< .001	0.931	0.897	0.096	[0.073, 0.120]	0.059

Print the fit indices in Markdown format

This is ideal for including the output in Markdown documents, such as GitHub READMEs or R Markdown reports.

print(fit_table, format = "markdown")

#> |MODEL | NOBS | ESTIMATOR | NPAR | Chi2(24) | p (Chi2) |   CFI |   TLI | RMSEA |      RMSEA  CI |  SRMR |
#> |:-----|:----:|:---------:|:----:|:--------:|:--------:|:-----:|:-----:|:-----:|:--------------:|:-----:|
#> |fit_1 |  301 |       MLR |   21 |   87.132 |   < .001 | 0.925 | 0.888 | 0.093 | [0.073, 0.115] | 0.065 |
#> |fit_2 |  301 |      ULSM |   21 |   90.600 |   < .001 | 0.931 | 0.897 | 0.096 | [0.073, 0.120] | 0.059 |