Software

Pacote BTSR

Simulate, estimate and forecast a wide range of regression-based dynamic models for bounded time series, covering the most commonly applied models in the literature. The main calculations are done in 'FORTRAN', which translates into very fast algorithms. The main references are Bayer et al. (2017) <doi:10.1016/j.jhydrol.2017.10.006>, Pumi et al.

Pacote DCCA

A collection of functions to perform Detrended Fluctuation Analysis (DFA) and Detrended Cross-Correlation Analysis (DCCA). This package implements the results presented in Prass, T.S. and Pumi, G. (2019). "On the behavior of the DFA and DCCA in trend-stationary processes" <arXiv:1910.10589>.

Referência:

Pacote PPMiss

Implements the copula-based estimator for univariate long-range dependent processes, introduced in Pumi et al. (2023) <doi:10.1007/s00362-023-01418-z>. Notably, this estimator is capable of handling missing data and has been shown to perform exceptionally well, even when up to 70% of data is missing (as reported in <doi:10.48550/arXiv.2303.04754>) and has been found to outperform several other commonly applied estimators.

Pacote PRTree

Probabilistic Regression Trees (PRTree). Functions for fitting and predicting PRTree models with some adaptations to handle missing values. The main calculations are performed in 'FORTRAN', resulting in highly efficient algorithms. This package's implementation is based on the PRTree methodology described in Alkhoury, S.; Devijver, E.; Clausel, M.; Tami, M.; Gaussier, E.; Oppenheim, G.

Pacote PTSR

A collection of functions to simulate, estimate and forecast a wide range of regression based dynamic models for positive time series. This package implements the results presented in Prass, T.S.; Carlos, J.H.; Taufemback, C.G. and Pumi, G. (2022). "Positive Time Series Regression" <arXiv:2201.03667>.