Code DAO

Dec 16, 2021 · Fundamentals

How Poisson Hidden Markov Models Enable Count‑Based Time‑Series Regression

This article explains how mixing a Poisson process with a discrete k‑state hidden Markov model creates a Poisson HMM that captures autocorrelation in integer‑valued time‑series, detailing the model formulation, prediction via expectation over states, and parameter estimation using MLE or EM.