Modeling the exchange rates of algerian dinar per united states dollar using a markov-switching autoregressive model

Abstract EN

This paper aims to model the Algerian dinar per United States dollar exchange rates using a regime Markov switching model.

Firstly, we detect if nonlinear model suits the data at hand, the BDS test and CUSUM of squares test were used and the results indicates that a non linear model suits the data.

Then, we proceed by using a two state Markov switching autoregressive model (MS-AR) developed by (Hamilton, 1989), Engle, Hamilton, 1990) for a period from January 1994 to March 2018.

The empirical evidence indicates strong transition probabilities suggesting that only extreme events can switch the series from an appreciation regime to depreciation regime vice versa.

Furthermore, the MA (2)-AR (3) is well suited to capture the nonlinearity in exchange rates.