juhalt.r-universe.dev

[juhalt] solomonR 0.8.2

josh.uhalt@gmail.com (Joshua Uhalt) — Fri, 09 Oct 2026 13:36:25 GMT

Tools for planning, analyzing, teaching, and reporting Solomon four-group experiments, introduced by Solomon (1949) . The historical analyses are reproduced and labeled as such, from Solomon's improvement scores to the Tests A-I sequence of Walton Braver and Braver (1988) and its published revisions. Contemporary analyses include one generalized linear model for all the groups, of four-group designs and of designs with several treatments, with robust or cluster-robust standard errors, for continuous, binary, and count outcomes; randomization inference; full-information maximum likelihood, following van Engelenburg (1999) ; observed- and latent-variable structural equation models with 'lavaan'; and equivalence tests of pretest sensitization. Also includes design checks, power and sample-size planning, simulated teaching data, published data sets, and reports in the style of the American Psychological Association, with method-specific references.

[juhalt] contentvalidR 0.10.1

josh.uhalt@gmail.com (Joshua Uhalt) — Tue, 29 Sep 2026 02:36:35 GMT

Provides quantitative tools for substantive and content-oriented scale pretesting. Implements item-sort indices from Anderson and Gerbing (1991) , exact item-sort inference following Howard and Melloy (2016) , empirical interpretation benchmarks from Colquitt et al. (2019) , and the construct-rating procedure of Hinkin and Tracey (1999) with HTC/HTD indices and repeated-measures item screening. The expert-panel workflow combines Aiken's V with score confidence intervals, Lawshe content validity ratios with exact inference, content validity indices with modified kappa and score intervals, item-objective congruence, and panel-level agreement using Krippendorff's alpha as described by Hayes and Krippendorff (2007) . Also provides judge and rater heterogeneity analysis following the generalizability-theory treatment of content-validity ratings in Crocker, Llabre and Miller (1988) , content-domain coverage and expert-perceived content structure following Sireci and Geisinger (1992) , consensus and stability across Delphi rounds with between-round weighted kappa following Holey et al. (2007) , comparison across successive pretest rounds, and exact expert-panel planning. Where published methods compete, users choose among them through arguments with evidence-based defaults. User-facing workflows emphasize interpretable summaries and transparent review recommendations rather than isolated coefficients.

[juhalt] nomologR 0.9.0

josh.uhalt@gmail.com (Joshua Uhalt) — Mon, 28 Sep 2026 18:10:23 GMT

Provides an evidence-guided workflow for empirical scale development and construct validation, designed for graduate students and researchers. The package helps users examine item performance, dimensionality, measurement models, reliability, convergent and discriminant evidence, measurement invariance, and theory-specified nomological networks in the sense of Cronbach and Meehl (1955) . Methods are documented from historical to contemporary practice with literature references, and simulated teaching datasets with known population models accompany the examples. Following calls for transparent measurement practice such as Flake, Pek, and Hehman (2017) , it emphasizes transparent diagnostics, reproducible decision logging, and teaching-oriented guidance rather than automatic item deletion or binary declarations that a measure is valid.