Thresholds and Invariant Intervals for Network Meta-Analysis (nmathresh)
Calculation and presentation of decision-invariant bias adjustment thresholds and intervals for Network Meta-Analysis, as described by Phillippo et al. (2017) <doi:10.1111/rssa.12341>. These describe the smallest changes to the data that would result in a change of decision.

Simple Toolkit in R for ANomalies Get, Explain and Report (stranger)
Framework for unsupervised anomalies detection that simplifies the user experience because the one does not need to be concerned with the many packages and functions that are required. Package ‘stranger’ acts as a wrapper around existing packages (‘a la ‘caret’ for modeling’) and provides a clean and uniform toolkit for evaluation/explain/reporting purposes.

Selecting Combinations of Predictors by Leveraging Multiple AUCs for an Ordered Multilevel Outcome (multiselect)
Uses multiple AUCs to select a combination of predictors when the outcome has multiple (ordered) levels and the focus is discriminating one particular level from the others. This method is most naturally applied to settings where the outcome has three levels. (Meisner, A, Parikh, CR, and Kerr, KF (2017) <http://…/>.)

Automatically Search Errors or Warnings (errorist)
Provides environment hooks that obtain errors and warnings which occur during the execution of code to automatically search for solutions.

Fit Rank-Ordered Logit (RO-Logit) Model (ROlogit)
Implements the rank-ordered logit (RO-logit) model for stratified analysis of continuous outcomes introduced by Tan et al. (2017) <doi:10.1177/0962280217747309>. Model diagnostics based on the heuristic residuals and estimates in linear scales are available from the package, and outcomes with ties are supported.

Advertisements