Build a facet statistics report (preferred alias)
Source:R/api-reports.R
facet_statistics_report.RdBuild a facet statistics report (preferred alias)
Arguments
- fit
Output from
fit_mfrm().- diagnostics
Optional output from
diagnose_mfrm().- metrics
Numeric columns in
diagnostics$measuresto summarize.- ruler_width
Width of the fixed-width ruler used for
M/S/Q/Xmarks.- distribution_basis
Which distribution basis to keep in the appended precision summary:
"both"(default),"sample", or"population".- se_mode
Which standard-error mode to keep in the appended precision summary:
"both"(default),"model", or"fit_adjusted".
Details
summary(out) is supported through summary().
plot(out) is dispatched through plot() for class
mfrm_facet_statistics (type = "means", "sds", "ranges").
Interpreting output
facet-level means/SD/ranges of selected metrics (
Estimate, fit indices,SE).fixed-width ruler rows (
M/S/Q/X) for compact profile scanning.
Typical workflow
Run
facet_statistics_report(fit).Inspect summary/ranges for anomalous facets.
Cross-check flagged facets with fit and chi-square diagnostics. The returned bundle now includes:
precision_summary: facet precision/separation indices byDistributionBasisandSEModevariability_tests: fixed/random variability tests by facetse_modes: compact list of available SE modes by facet
Examples
# \donttest{
toy <- load_mfrmr_data("example_core")
fit <- fit_mfrm(toy, "Person", c("Rater", "Criterion"), "Score", method = "JML", maxit = 300)
out <- facet_statistics_report(fit)
summary(out)
#> mfrmr Facet Profile Summary
#> Class: mfrm_facet_statistics
#> Components: 6
#>
#> Facet-profile overview
#> Facets Rows Metrics PrecisionRows VariabilityRows
#> 3 12 4 12 3
#>
#> Facet-profile rows: precision_summary
#> Facet Levels DistributionBasis SEMode SEColumn ObservedMean
#> Criterion 4 population fit_adjusted RealSE 0.000
#> Criterion 4 population model ModelSE 0.000
#> Criterion 4 sample fit_adjusted RealSE 0.000
#> Criterion 4 sample model ModelSE 0.000
#> Person 48 population fit_adjusted RealSE 0.001
#> Person 48 population model ModelSE 0.001
#> Person 48 sample fit_adjusted RealSE 0.001
#> Person 48 sample model ModelSE 0.001
#> Rater 4 population fit_adjusted RealSE 0.000
#> Rater 4 population model ModelSE 0.000
#> ObservedSD RMSE TrueSD ObservedVariance ErrorVariance TrueVariance Separation
#> 0.249 0.099 0.229 0.062 0.010 0.052 2.316
#> 0.249 0.097 0.229 0.062 0.010 0.053 2.353
#> 0.288 0.099 0.270 0.083 0.010 0.073 2.736
#> 0.288 0.097 0.271 0.083 0.010 0.073 2.777
#> 1.088 0.365 1.025 1.184 0.133 1.050 2.809
#> 1.088 0.347 1.031 1.184 0.120 1.063 2.974
#> 1.099 0.365 1.037 1.209 0.133 1.076 2.842
#> 1.099 0.347 1.043 1.209 0.120 1.089 3.009
#> 0.271 0.099 0.253 0.074 0.010 0.064 2.564
#> 0.271 0.097 0.253 0.074 0.009 0.064 2.596
#> Strata Reliability EstimateAvailable SEAvailable ExcludedEstimates
#> 3.421 0.843 4 4 0
#> 3.470 0.847 4 4 0
#> 3.981 0.882 4 4 0
#> 4.037 0.885 4 4 0
#> 4.079 0.888 48 48 0
#> 4.299 0.898 48 48 0
#> 4.123 0.890 48 48 0
#> 4.346 0.901 48 48 0
#> 3.752 0.868 4 4 0
#> 3.795 0.871 4 4 0
#> SummaryNote MeanSE MedianSE
#> Computed over 4 of 4 levels with finite estimates and SEs. 0.099 0.098
#> Computed over 4 of 4 levels with finite estimates and SEs. 0.097 0.097
#> Computed over 4 of 4 levels with finite estimates and SEs. 0.099 0.098
#> Computed over 4 of 4 levels with finite estimates and SEs. 0.097 0.097
#> Computed over 48 of 48 levels with finite estimates and SEs. 0.360 0.349
#> Computed over 48 of 48 levels with finite estimates and SEs. 0.344 0.330
#> Computed over 48 of 48 levels with finite estimates and SEs. 0.360 0.349
#> Computed over 48 of 48 levels with finite estimates and SEs. 0.344 0.330
#> Computed over 4 of 4 levels with finite estimates and SEs. 0.099 0.099
#> Computed over 4 of 4 levels with finite estimates and SEs. 0.097 0.097
#> MeanInfit MeanOutfit FixedChiSq FixedDF FixedProb RandomVar RandomChiSq
#> 0.994 1.019 25.914 3 0 0.073 2.997
#> 0.994 1.019 25.914 3 0 0.073 2.997
#> 0.994 1.019 25.914 3 0 0.073 2.997
#> 0.994 1.019 25.914 3 0 0.073 2.997
#> 1.000 1.019 384.048 47 0 1.089 45.462
#> 1.000 1.019 384.048 47 0 1.089 45.462
#> 1.000 1.019 384.048 47 0 1.089 45.462
#> 1.000 1.019 384.048 47 0 1.089 45.462
#> 0.993 1.019 30.899 3 0 0.089 2.999
#> 0.993 1.019 30.899 3 0 0.089 2.999
#> RandomDF RandomProb
#> 2 0.223
#> 2 0.223
#> 2 0.223
#> 2 0.223
#> 46 0.495
#> 46 0.495
#> 46 0.495
#> 46 0.495
#> 2 0.223
#> 2 0.223
#>
#> Settings
#> Setting Value
#> metrics Estimate, Infit, Outfit, SE
#> ruler_width 41
#> marker_legend mean, +/-1 SD, +/-2 SD, +/-3 SD
#> distribution_basis both
#> se_mode both
#>
#> Notes
#> - Facet profile summary including distribution basis, SE mode, and variability
#> tests.
p_fs <- plot(out, draw = FALSE)
p_fs$data$plot
#> [1] "means"
# }