Tools for Descriptive Statistics

A toolbox for descriptive statistics, based on the computation of frequency and contingency tables. Several statistical functions and plot methods are provided to describe univariate or bivariate distributions of factors, integer series and numerical series either provided as individual values or as bins.

Binscatter Estimation and Inference

Provides tools for statistical analysis using the binscatter methods developed by Cattaneo, Crump, Farrell and Feng (2024a) , Cattaneo, Crump, Farrell and Feng (2024b) < https://nppackages.github.io/references/Cattaneo-Crump-Farrell-Feng_2024_NonlinearBinscatter.pdf> and Cattaneo, Crump, Farrell and Feng (2024c) . Binscatter provides a flexible way of describing the relationship between two variables based on partitioning/binning of the independent variable of interest. binsreg(), binsqreg() and binsglm() implement binscatter least squares regression, quantile regression and generalized linear regression respectively, with particular focus on constructing binned scatter plots. They also implement robust (pointwise and uniform) inference of regression functions and derivatives thereof. binstest() implements hypothesis testing procedures for parametric functional forms of and nonparametric shape restrictions on the regression function. binspwc() implements hypothesis testing procedures for pairwise group comparison of binscatter estimators. binsregselect() implements data-driven procedures for selecting the number of bins for binscatter estimation. All the commands allow for covariate adjustment, smoothness restrictions and clustering.

Reliability Diagrams Using Isotonic Regression

Checking the reliability of predictions via the CORP approach, which generates provably statistically 'C'onsistent, 'O'ptimally binned, and 'R'eproducible reliability diagrams using the 'P'ool-adjacent-violators algorithm. See Dimitriadis, Gneiting, Jordan (2021) .

Tidy Consultant Universe

Loads the 5 packages in the Tidy Consultant Universe. This collection of packages is useful for anyone doing data science, data analysis, or quantitative consulting. The functions in these packages range from data cleaning, data validation, data binning, statistical modeling, and file exporting.

Preprocessor for Data Modeling

Includes binning categorical variables into lesser number of categories based on t-test, converting categorical variables into continuous features using the mean of the response variable for the respective categories, understanding the relationship between the response variable and predictor variables using data transformations.

Probability Functions for Occupancy Distributions

The classical and extended occupancy distributions occur in cases where balls are randomly allocated to bins. The PDF, CDF, quantile functions, generation of random variates, and calculating the first four central moments of the distributions are implemented as described in O’Neill (2019) .

Inky Color Schemes

Provides color palettes designed to be reminiscent of text on paper. The color schemes were taken from < https://stephango.com/flexoki>. Includes discrete, continuous, and binned scales that are not necessarily color-blind friendly. Simple scale and theme functions are available for use with 'ggplot2'.

Genetic Algorithm Assisted Genomic Best Liner Unbiased Prediction

Performs genetic algorithm (Scrucca, L (2013) ) assisted genomic best liner unbiased prediction for genomic selection. It also provides a binning method in natural population for genomic selection under the principle of linkage disequilibrium for dimensional reduction.

Lookup for IP Address Proxy Information

Enable user to find the IP addresses which are used as VPN anonymizer, open proxies, web proxies and Tor exits. The package lookup the proxy IP address from IP2Proxy BIN Data file. You may visit < https://lite.ip2location.com> for free database download.

Collection of Tools for PD Rating Model Development and Validation

The goal of this package is to cover the most common steps in probability of default (PD) rating model development and validation. The main procedures available are those that refer to univariate, bivariate, multivariate analysis, calibration and validation. Along with accompanied 'monobin' and 'monobinShiny' packages, 'PDtoolkit' provides functions which are suitable for different data transformation and modeling tasks such as: imputations, monotonic binning of numeric risk factors, binning of categorical risk factors, weights of evidence (WoE) and information value (IV) calculations, WoE coding (replacement of risk factors modalities with WoE values), risk factor clustering, area under curve (AUC) calculation and others. Additionally, package provides set of validation functions for testing homogeneity, heterogeneity, discriminatory and predictive power of the model.