Toolbox for Model Selection and Combinations for the Forecasting Purposes (greybox)
Implements model selection and combinations via information criteria based on the values of partial correlations. This allows, for example, solving ‘fat regression’ problems, where the number of variables is much larger than the number of observations. This is driven by the research on information criteria, which is well discussed in Burnham & Anderson (2002) <doi:10.1007/b97636>, and currently developed further by Ivan Svetunkov and Yves Sagaert (working paper in progress). Models developed in the package are tailored specifically for forecasting purposes. So as a results there are several methods that allow producing forecasts from these models and visualising them.

High-Dimensional Regression with Measurement Error (hdme)
Penalized regression for generalized linear models for measurement error problems (aka. errors-in-variables). The package contains a version of the lasso (L1-penalization) which corrects for measurement error (Sorensen et al. (2015) <doi:10.5705/ss.2013.180>). It also contains an implementation of the Generalized Matrix Uncertainty Selector, which is a version the (Generalized) Dantzig Selector for the case of measurement error (Sorensen et al. (2018) <doi:10.1080/10618600.2018.1425626>).

Interface to the Corpus Query Protocol (rcqp)
Implements Corpus Query Protocol functions based on the CWB software. Rely on CWB (GPL v2), PCRE (BSD licence), glib2 (LGPL).

Create the Best Train for Classification Models (OptimClassifier)
Patterns searching and binary classification in economic and financial data is a large field of research. There are a large part of the data that the target variable is binary. Nowadays, many methodologies are used, this package collects most popular and compare different configuration options for Linear Models (LM), Generalized Linear Models (GLM), Linear Mixed Models (LMM), Discriminant Analysis (DA), Classification And Regression Trees (CART), Neural Networks (NN) and Support Vector Machines (SVM).

Effortlessly Read Any Rectangular Data (readit)
Providing just one primary function, ‘readit’ uses a set of reasonable heuristics to apply the appropriate reader function to the given file path. As long as the data file has an extension, and the data is (or can be coerced to be) rectangular, readit() can probably read it.

Advertisements