Skip to contents

Summarize an mfrm_diagnostics object in a user-friendly format

Source: R/api-methods.R
summary.mfrm_diagnostics.Rd

Summarize an mfrm_diagnostics object in a user-friendly format

Usage

# S3 method for class 'mfrm_diagnostics'
summary(object, digits = 3, top_n = 10, ...)

Arguments

object

Output from diagnose_mfrm().

digits

Number of digits for printed numeric values.

top_n

Number of highest-absolute-Z fit rows to keep.

...

Reserved for generic compatibility.

Value

An object of class summary.mfrm_diagnostics with:

  • overview: design-level counts and residual-PCA mode

  • overall_fit: global fit block

  • reliability: facet-level separation/reliability summary

  • top_fit: top |ZSTD| rows

  • flags: compact flag counts for major diagnostics

  • notes: short interpretation notes

Details

This method returns a compact diagnostics summary designed for quick review:

  • design overview (observations, persons, facets, categories, subsets)

  • global fit statistics

  • approximate reliability/separation by facet

  • top facet/person fit rows by absolute ZSTD

  • counts of flagged diagnostics (unexpected, displacement, interactions)

Interpreting output

  • overview: analysis scale, subset count, and residual-PCA mode.

  • overall_fit: global fit indices.

  • reliability: facet separation/reliability block, including model and real bounds when available.

  • top_fit: highest |ZSTD| elements for immediate inspection.

  • flags: compact counts for key warning domains.

Typical workflow

  1. Run diagnostics with diagnose_mfrm().

  2. Review summary(diag) for major warnings.

  3. Follow up with dedicated tables/plots for flagged domains.

See also

diagnose_mfrm(), summary.mfrm_fit()

Examples

toy <- load_mfrmr_data("example_core")
fit <- fit_mfrm(toy, "Person", c("Rater", "Criterion"), "Score", method = "JML", maxit = 25)
diag <- diagnose_mfrm(fit, residual_pca = "none")
summary(diag)
#> Many-Facet Rasch Diagnostics Summary
#>   Observations: 768 | Persons: 48 | Facets: 2 | Categories: 4 | Subsets: 1
#>   Residual PCA mode: none
#>   Method: JML | Precision tier: exploratory
#> 
#> Overall fit
#>  Infit Outfit InfitZSTD OutfitZSTD DF_Infit DF_Outfit
#>  0.994  1.019    -0.063      0.391  420.865       768
#> 
#> Precision basis
#>  Method Converged PrecisionTier SupportsFormalInference HasFallbackSE
#>     JML      TRUE   exploratory                   FALSE         FALSE
#>                  PersonSEBasis              NonPersonSEBasis
#>  Observation-table information Observation-table information
#>                              CIBasis
#>  Normal interval from exploratory SE
#>                                                             ReliabilityBasis
#>  Exploratory variance summary with model-based and fit-adjusted error bounds
#>  HasFitAdjustedSE HasSamplePopulationCoverage
#>              TRUE                        TRUE
#>                                                                                     RecommendedUse
#>  Use for screening and calibration triage; confirm formal SE, CI, and reliability with an MML fit.
#> 
#> Precision audit checks to review
#>           Check Status
#>  Precision tier review
#>                                                                                                            Detail
#>  This run uses the package's exploratory precision path; prefer MML for formal SE, CI, and reliability reporting.
#> 
#> Facet precision and spread
#>      Facet Levels Separation Strata Reliability RealSeparation RealStrata
#>  Criterion      4      2.771  4.028       0.885          2.729      3.972
#>     Person     48      3.012  4.350       0.901          2.845      4.126
#>      Rater      4      3.052  4.403       0.903          3.015      4.354
#>  RealReliability MeanInfit MeanOutfit
#>            0.882     0.994      1.019
#>            0.890     1.000      1.019
#>            0.901     0.994      1.019
#> 
#> Largest |ZSTD| rows
#>      Facet        Level Infit Outfit InfitZSTD OutfitZSTD  AbsZ
#>     Person         P023 1.558  2.442     0.882      3.060 3.060
#>     Person         P018 0.526  0.528    -1.165     -1.507 1.507
#>  Criterion Organization 0.867  0.859    -0.968     -1.422 1.422
#>     Person         P048 0.569  0.562    -0.979     -1.365 1.365
#>     Person         P037 0.570  0.563    -1.016     -1.361 1.361
#>  Criterion      Content 1.008  1.134     0.105      1.290 1.290
#>     Person         P030 1.389  1.396     0.931      1.117 1.117
#>     Person         P035 0.617  0.629    -0.864     -1.097 1.097
#>     Person         P044 1.301  1.371     0.745      1.060 1.060
#>     Person         P004 1.331  1.331     0.792      0.967 0.967
#> 
#> Flag counts
#>                       Metric Count
#>         Unexpected responses   100
#>  Flagged displacement levels     0
#>             Interaction rows    20
#>            Inter-rater pairs     6
#> 
#> Notes
#>  - Precision outputs are exploratory for this run; prefer MML for formal SE, CI, and reliability reporting.
#>  - Unexpected responses were flagged under current thresholds.
#>  - SE/ModelSE, CI, and reliability conventions depend on the estimation path; see diagnostics$approximation_notes for MML-vs-JML details.
#>  - Precision audit flagged 1 review/warn checks.