Time-varying parameter VAR model using TVP-VAR package
Jouchi Nakajima
jouchi.nakajima@gmail.com
June 30, 2018
1 Introduction
TVP-VAR (Time-Varying Parameter Vector AutoRegression) is the package for a Bayesian
analysis of the time-varying parameter VAR models. It implements the Markov chain Monte
Carlo (MCMC) algorithm to generate samples from the posterior distribution of the TVP-
VAR models. The TVP-VAR class is written in MATLAB, and can be used by linking the
TVP-VAR package in MATLAB source codes. You may use and modify this code at your own
risk. Please cite Nakajima (2011) in products involving the application of TVP-VAR package.
1.1 Running TVP-VAR
To use the TVP-VAR package, put the files of TVPVAR folder into the folder of the current
directory where you are working. Alternatively, you can use the package by adding the TVPVAR
folder to the working directory in MATLAB.
1.2 Files in TVP-VAR
The main files in TVP-VAR package are
• setvar.m – sets variables in the model;
• mcmc.m – estimates the model by MCMC algorithm;
• TVPVAR-Package.m – description of functions;
• tvpvar m.pdf – this document;
with sample programs:
• tvpvar ex*.m – example for use of TVP-VAR package;
• tvpvar ex.xlsx – example data for tvpvar ex*.m.
1