Density forecasts of locally explosive processes are investigated using mixed causal-noncausal models, namely time series models with both lag and lead components. In the absence theoretical expressions for predictive density a large range potential error distributions, two approximation methods analysed compared Monte Carlo simulations. The focus is on prediction one-step ahead probabilities t...

Hydrologic modeling allows the simulation of runoff and sediment processes, which are applied in integrated watershed management, soil water nutrients, among others. However, these models require considerable amounts input data. Sediment data is often lacking quantity quality, leads to uncertainty hydrological models. The objective present study was propose a methodological alternative based on...

Vector autoregressive (VAR) models assume linearity between the endogenous variables and their lags. This assumption might be overly restrictive could have a deleterious impact on forecasting accuracy. As solution we propose combining VAR with Bayesian additive regression tree (BART) models. The resulting vector (BAVART) model is capable of capturing arbitrary nonlinear relations covariates wit...

The FitAR R (R Development Core Team 2008) package that is available on the Comprehensive R Archive Network is described. This package provides a comprehensive approach to fitting autoregressive and subset autoregressive time series. For long time series with complicated autocorrelation behavior, such as the monthly sunspot numbers, subset autoregression may prove more feasible and/or parsimoni...

The classical method of process capability analysis necessarily assumes that collected data are independent; nonetheless, some processes such as biological and chemical processes are autocorrelated and violate the independency assumption. Many processes exhibit a certain degree of correlation and can be treated by autoregressive models among which the autoregressive model of order one (AR (1)) ...

Ecological data often exhibit spatial pattern, which can be modeled as autocorrelation. Conditional autoregressive (CAR) and simultaneous autoregressive (SAR) models are network-based models (also known as graphical models) specifically designed to model spatially autocorrelated data based on neighborhood relationships. We identify and discuss six different types of practical ecological inferen...