Standard Evaluation Interfaces for Common ‘dplyr’ Tasks (seplyr)
The ‘seplyr’ (standard evaluation data.frame ‘dplyr’) package supplies standard evaluation adapter methods for important common ‘dplyr’ methods that currently have a non-standard programming interface. This allows the analyst to use ‘dplyr’ to perform fundamental data transformation steps such as arranging rows, grouping rows, aggregating selecting columns without having to use learn the details of ‘rlang’/’tidyeval’ non-standard evaluation and without continuing to rely on now deprecated ‘dplyr’ ‘underscore verbs.’ In addition the ‘seplyr’ package supplies several new ‘key operations bound together’ methods. These include ‘group_summarize()’ (which combines grouping, arranging and calculation in an atomic unit), ‘add_group_summaries()’ (which joins grouped summaries into a ‘data.frame’ in a well documented manner), and ‘add_group_indices()’ (which adds per-group identifies to a ‘data.frame’ without depending on row-order).

Bland-Altman Method Comparison (blandr)
Carries out Bland Altman analyses (also known as a Tukey mean-difference plot) as described by JM Bland and DG Altman in 1986 <doi:10.1016/S0140-6736(86)90837-8>. This package was created in 2015 as existing Bland-Altman analysis functions did not calculate confidence intervals. This package was created to rectify this, and create reproducible plots.

Supporting Graphs for Analysing Time Series (sugrrants)
Provides ‘ggplot2’ graphics for analysing time series data. It aims to fit into the ‘tidyverse’ and grammar of graphics framework for handling temporal data.

Hybrid Mortality Estimation (RkMetrics)
Hybrid Mortality Modelling (HMM) provides a framework in which mortality around ‘the accident hump’ and at very old ages can be modelled under a single model. The graphics’ codes necessary for visualization of the models’ output are included here.

Hierarchical Item Response Theory Models (hIRT)
Implementation of a class of hierarchical item response theory (IRT) models where both the mean and the variance of latent preferences (ability parameters) can depend on observed covariates. The current implementation includes both the two-parameter latent trait model and the graded response model for ordinal data. Both are fitted via the Expectation-Maximization (EM) algorithm. Asymptotic standard errors are derived from the observed information matrix.

Advertisements