Studierende sitzt am Arbeitsplatz und schaut auf den Laptop. © Aliona Kardash​/​TU Dortmund

New R-package PrInDT, version 2.0.1 (Authors: C. Weihs, S. Buschfeld, TU Dortmund)

Conditional inference trees for classification and regression from the package 'party' are optimized by searching the model space for the best tree on the full sample by means of repeated random subsampling. Restrictions are allowed so that only trees are accepted which do not include pre-specified uninterpretable split results (cf. Weihs & Buschfeld, 2021).

Individual modeling

The functions PrInDT(), RePrInDT(), OptPrInDT(), NesPrInDT(), and PrInDTMulev() deal with classification problems.

The function PrInDTreg() has been developed for regression problems.

NEW in version 2:

A second kind of subsampling called “structured sampling” is implemented in the functions PrInDTCstruc() and PrInDTRstruc() for classification and regression. In these functions, repeated measurements data can be analyzed, too.

Simultaneous modeling

The function PrInDTMulab() deals with multilabel classification.

NEW in version 2:

Multilabel 2-stage versions of classification and regression trees are implemented in the functions C2SPrInDT() and R2SPrInDT() as well as interdependent multilabel models in functions SimCPrInDT() and SimRPrInDT().

For mixtures of classification and regression models, the functions Mix2SPrInDT() and SimMixPrInDT() are implemented.

Most of the extensions of PrInDT in version 2 are illustrated in Buschfeld & Weihs (2025Fc).

References:

Buschfeld, S., Weihs, C. (2025Fc) "Optimizing decision trees for the analysis of World Englishes and sociolinguistic data", Cambridge Elements.

Weihs, C., Buschfeld, S. (2021) "Combining Prediction and Interpretation in Decision Trees (PrInDT) - a Linguistic Example", doi:10.48550/arXiv.2103.02336

Weihs, C., Buschfeld, S. (2025): PrInDT: Prediction and Interpretation in Decision Trees for Clas sification and Regression, R package version 2.0.1., doi: CRAN.R-project.org/package=PrInDT

Zurück