# Hidden Markov model for discrete circular-linear wind data time series

## TL;DR

This paper develops a non-parametric Bayesian hidden Markov model for bivariate wind data, effectively handling missing, censored, and unreliable measurements by introducing novel emission distributions tailored to the data's peculiar features.

## Contribution

It introduces a new emission distribution based on the invariant wrapped Poisson, Poisson, and hurdle densities for modeling complex wind data within a hidden Markov framework.

## Key findings

- Model successfully applied to simulated data
- Effective handling of missing and censored data
- Real data analysis demonstrates practical utility

## Abstract

In this work, we deal with a bivariate time series of wind speed and direction. Our observed data have peculiar features, such as informative missing values, non-reliable measures under a specific condition and interval-censored data, that we take into account in the model specification. We analyze the time series with a non-parametric Bayesian hidden Markov model, introducing a new emission distribution based on the invariant wrapped Poisson, the Poisson and the hurdle density, suitable to model our data. The model is estimated on simulated datasets and on the real data example that motivated this work.