gpcm_capability_matrix: Bounded GPCM Support Matrix

In mfrmr: Estimation and Diagnostics for Many-Facet Measurement Models

Bounded GPCM Support Matrix

Description

Public capability map for the current GPCM scope in mfrmr.

Use this helper when you need to answer a practical question quickly: which GPCM workflows are supported in this release, which are available only with explicit caveats, and which helpers remain blocked or deferred, plus the route to use instead when the requested helper is outside the current boundary.

The matrix is intentionally conservative. It is a release-scope statement, not a promise that every lower-level helper can be combined with GPCM. If a helper is not yet covered by the current validation boundary, it is listed as blocked or deferred even when related components already exist.

Usage

gpcm_capability_matrix(
  status = c("all", "supported", "supported_with_caveat", "blocked", "deferred")
)

Arguments

status

Which rows to return: "all" (default), "supported", "supported_with_caveat", "blocked", or "deferred".

Details

The current release treats GPCM as a bounded supported scope inside the core R package:

• fitting and core summaries are supported,

• posterior-scoring and information helpers are supported,

• residual-based diagnostics and strict marginal follow-up are supported as exploratory screens,

• direct slope-aware simulation-spec generation and parameter-recovery simulation are supported with caveats,

• fair_average_table() is supported with an explicit slope-aware element-conditional caveat,

• estimate_bias() is supported as conditional screening evidence with slope-aware information and profile-likelihood follow-up columns,

• summary-table appendix export is available for supported direct outputs,

• APA writer, visual summaries, QC pipelines, manifests, replay scripts, and fit-based export bundles are available only as caveated sensitivity-reporting surfaces with an explicit gpcm_boundary,

• package-native scorefile export is available with score-side caveats,

• role-based design evaluation and population forecasting are available as caveated bounded-GPCM sensitivity evidence,

• role-based diagnostic and signal-detection design screening helpers are available as caveated bounded-GPCM sensitivity evidence,

• full FACETS output-contract score-side review remains outside the validated GPCM boundary.

Why some helpers remain blocked:

• full FACETS output-contract score-side review depends on Rasch-family measure-to-score semantics plus delta-method SE machinery that are not yet generalized to the free-discrimination GPCM branch;

• APA writer, fit-based report/export bundles, visual summaries, and QC pipelines stay caveated because they must not turn unsupported score-side semantics into narrative or pass/fail outputs;

• diagnostic, signal-detection, design-forecast, and linking helpers stay caveated because their simulation/refit summaries must not become operational screening, scoring, or arbitrary-facet planning claims.

This boundary is aligned with the package's current validation evidence, including the targeted GPCM recovery snapshot and the public workflow checks.

Value

A data.frame with one row per public helper family and columns:

• Area

• Helpers

• Status

• PrimaryUse

• Boundary

• Evidence

• RecommendedRoute

• NextValidationStep

Typical workflow

1. Call gpcm_capability_matrix() before using GPCM in a new workflow.

2. Stay on rows marked supported or supported_with_caveat for the current release.

3. For blocked and deferred rows, read RecommendedRoute before choosing a substitute workflow.

4. Treat blocked rows as explicit non-support, not as temporary omissions.

5. Treat deferred rows as future-extension targets rather than part of the current user-facing support.

See Also

fit_mfrm(), diagnose_mfrm(), compute_information(), predict_mfrm_units(), sample_mfrm_plausible_values(), reporting_checklist(), mfrmr_workflow_methods, mfrmr-package

Examples

gpcm_capability_matrix()
gpcm_capability_matrix("supported")
gpcm_capability_matrix("blocked")

mfrmr documentation built on June 13, 2026, 1:07 a.m.