Generalizability Theory for LLM Subjective Tasks

---

Documentation for package ‘Gtheory4LLM’ version 0.2.0

• DESCRIPTION file.
• User guides, package vignettes and other documentation.
• Package NEWS.

Help Pages

Gtheory4LLM-package	Generalizability Theory for LLM Subjective Tasks
coef.gt_fit	Standard Extractors for Fitted Generalizability Models
drug_review	LLM Drug-Review Sentiment and Four Aspect Annotations
drug_review_4aspect	LLM Drug-Review Sentiment and Four Aspect Annotations
Gtheory4LLM	Generalizability Theory for LLM Subjective Tasks
Gtheory4LLM-datasets	Three LLM Annotation Datasets: Design, Coding, and Sources
gtheory_datasets	Three LLM Annotation Datasets: Design, Coding, and Sources
gtheory_drug_review	LLM Drug-Review Sentiment and Four Aspect Annotations
gtheory_hate_speech	LLM Hate-Speech Annotations of HateXplain Texts
gtheory_mental_health	LLM Mental-Health Text Annotations in Five Outcome Sets
gt_components	Extract Source Covariances or Correlations
gt_component_vcov	Standard Extractors for Fitted Generalizability Models
gt_control	Configure Gaussian and Discrete Fitting and Acceptance Checks
gt_design	Declare a Generalizability-Theory Random-Source Design
gt_diagnostics	Inspect Numerical Acceptance and Backend Diagnostics
gt_dstudy	Evaluate Balanced Measurement Allocations
gt_example	Load Modeling Tables from Three LLM-Annotated Datasets
gt_family	Specify a Gaussian, Binary, Ordinal, or Unordered Categorical Outcome
gt_fit	Fit Univariate or Joint Multivariate Generalizability Models
gt_fit_methods	Standard Extractors for Fitted Generalizability Models
gt_preflight	Inspect Data, Source Dimensions, and Backend Limits Before Fitting
gt_reliability	Compute Balanced G and Phi Coefficients
gt_score	Declare Composite-Score Weights
hate_speech	LLM Hate-Speech Annotations of HateXplain Texts
logLik.gt_fit	Standard Extractors for Fitted Generalizability Models
mental_health_3group	LLM Mental-Health Text Annotations in Five Outcome Sets
mental_health_3L	LLM Mental-Health Text Annotations in Five Outcome Sets
mental_health_6flag	LLM Mental-Health Text Annotations in Five Outcome Sets
mental_health_7L	LLM Mental-Health Text Annotations in Five Outcome Sets
mental_health_nominal	LLM Mental-Health Text Annotations in Five Outcome Sets
nobs.gt_fit	Standard Extractors for Fitted Generalizability Models
plot.gt_dstudy	Evaluate Balanced Measurement Allocations
print.gt_diagnostics	Inspect Numerical Acceptance and Backend Diagnostics
print.gt_diagnostic_stage	Inspect Numerical Acceptance and Backend Diagnostics
print.gt_diagnostic_stages	Inspect Numerical Acceptance and Backend Diagnostics
print.gt_dstudy	Evaluate Balanced Measurement Allocations
print.gt_fit	Fit Univariate or Joint Multivariate Generalizability Models
print.gt_preflight	Inspect Data, Source Dimensions, and Backend Limits Before Fitting
print.gt_reliability	Compute Balanced G and Phi Coefficients
print.summary.gt_fit	Print a Concise Generalizability Model Summary
summary.gt_fit	Fit Univariate or Joint Multivariate Generalizability Models
vcov.gt_fit	Standard Extractors for Fitted Generalizability Models