Biips examples

This page contains several illustrations of the use of Biips software via R and MATLAB.

First, in order to familiarize with the software, we provide a tutorial in three parts, for inference on a standard univariate nonlinear non-Gaussian state-space model.

Three additional, realistic applications are then provided:

• (Switching) Stochastic volatility
• Stochastic kinetic prey-predator
• Object tracking

Click on the links below for html versions of the matbiipsrbiips examples.

Tutorials

Simple illustrative example with a nonlinear non-Gaussian Hidden Markov model.

• Tutorial 1: Sequential Monte Carlo (SMC), Particle Independent Metropolis Hastings (PIMH) [rbiips] [matbiips]

• Tutorial 2: Sensitivity analysis with SMC, Particle Marginal Metropolis-Hastings (PMMH) [rbiips] [matbiips]

• Tutorial 3: Adding a user-defined function [rbiips] [matbiips]

Stochastic volatility

• Stochastic volatility model [rbiips] [matbiips]

• Switching Stochastic volatility model [rbiips] [matbiips]

• Switching Stochastic volatility model with parameter estimation [rbiips] [matbiips]

Stochastic kinetic

• Stochastic kinetic predator-prey model [rbiips] [matbiips]

• Stochastic kinetic predator-prey model with Gillespie algorithm [rbiips] [matbiips]

Object tracking

• 4-dimensional (2-d position and velicity) radar tracking model. [rbiips] [matbiips]