https://github.com/tpapp/hiddenpoisson.jl

Simulate a hidden state model in continuous time with Poisson shocks.
https://github.com/tpapp/hiddenpoisson.jl

Last synced: 4 months ago
JSON representation

Simulate a hidden state model in continuous time with Poisson shocks.

• Host: GitHub
• URL: https://github.com/tpapp/hiddenpoisson.jl
• Owner: tpapp
• License: other
• Created: 2017-04-03T14:26:00.000Z (about 9 years ago)
• Default Branch: master
• Last Pushed: 2020-12-20T09:15:24.000Z (over 5 years ago)
• Last Synced: 2026-01-20T20:04:53.824Z (5 months ago)
• Language: Julia
• Size: 9.77 KB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

          
# HiddenPoisson

[![Project Status: WIP - Initial development is in progress, but there has not yet been a stable, usable release suitable for the public.](http://www.repostatus.org/badges/latest/wip.svg)](http://www.repostatus.org/#wip)

[![Build Status](https://travis-ci.org/tpapp/HiddenPoisson.jl.svg?branch=master)](https://travis-ci.org/tpapp/HiddenPoisson.jl)

[![Coverage Status](https://coveralls.io/repos/tpapp/HiddenPoisson.jl/badge.svg?branch=master&service=github)](https://coveralls.io/github/tpapp/HiddenPoisson.jl?branch=master)

[![codecov.io](http://codecov.io/github/tpapp/HiddenPoisson.jl/coverage.svg?branch=master)](http://codecov.io/github/tpapp/HiddenPoisson.jl?branch=master)

## Overview

Simulate a hidden state model in continuous time with the following setup:

1. Let `state` denote the hidden (unobserved) *state*. It can be an arbitrary Julia object, as long as the relevant methods are defined.

2. The *model* parameters are packed into the `model` object.

3. `transitions(model, state)` returns a vector of `Pair(λ, next_state)` elements. *Shocks* can happen at rates `λ` independently (competing Poisson processes), and then `next_state`, which is a function or a constant, is used to generate the next state.

4. `observation(model, state)` is another (possibly stochastic) function for returning an observation for the hidden `state`.

The user needs to define a model structure, then

```julia

import HiddenPoisson: transitions, observation

```

and then define these methods for the model structure. Then simulations are obtained using `next_observation` or `next_observations`. See the tests for examples.

## How it works

A `HiddenState` object keeps track of the time remaining until the next shock, and its value. Given a time interval `t`, new transitions are generated on demand until enough time has passed.