**Random Forest Prediction Decomposition and Feature Importance Measure** (**tree.interpreter**)

An R re-implementation of the ‘treeinterpreter’ package on PyPI <https://…/>. Each prediction can be decomposed as ‘prediction = bias + feature_1_contribution + … + feature_n_contribution’. This decomposition is then used to calculate the Mean Decrease Impurity (MDI) and Mean Decrease Impurity using out-of-bag samples (MDI-oob) feature importance measures based on the work of Li et al. (2019) <arXiv:1906.10845>.

**Scalable Robust Estimators with High Breakdown Point for Incomplete Data** (**rrcovNA**)

Robust Location and Scatter Estimation and Robust Multivariate Analysis with High Breakdown Point for Incomplete Data (missing values) (Todorov et al. (2010) <doi:10.1007/s11634-010-0075-2>).

**Calculation for Single Arm Group Sequential Test with Binary Endpoint** (**BinGSD**)

Consider an at-most-K-stage group sequential design with only an upper bound for the last analysis and non-binding lower bounds.With binary endpoint, two kinds of test can be applied, asymptotic test based on normal distribution and exact test based on binomial distribution. This package supports the computation of boundaries and conditional power for single-arm group sequential test with binary endpoint, via either asymptotic or exact test. The package also provides functions to obtain boundary crossing probabilities given the design.

**Analysis and Prediction of Tides** (**TideCurves**)

Tidal analysis of evenly spaced observed time series (time step 1 to 60 min) with or without shorter gaps using the harmonic representation of inequalities. The analysis should preferably cover an observation period of at least 19 years. For shorter periods low frequency constituents are not taken into account, in accordance with the Rayleigh-Criterion. The main objective of this package is to synthesize or predict a tidal time series.

**Table One for ‘Latex’, ‘Word’, and ‘Html’ ‘R Markdown’ Documents** (**tibbleOne**)

Table one is a tabular description of characteristics, e.g., demographics of patients in a clinical trial, presented overall and also stratified by a categorical variable, e.g. treatment group. There are many excellent packages available to create table one. This package focuses on providing table one objects that seamlessly fit into ‘R Markdown’ analyses.

### Like this:

Like Loading...