International Journal of Statistics and Systems
  • Year: 2010
  • Volume: 5
  • Issue: 3

Bayesian Analysis of Exchange Rates with Partially Linear Time Trend

  • Author:
  • Jitendra Kumar1, Ashutosh Shukla1, Anoop Chaturvedi3
  • Total Page Count: 15
  • Page Number: 439 to 453

1Department of Mathematics and Statistics Allahabad Agriculture Institute- Deemed University, Allahabad, UP-211007, India

3Department of Statistics, University of Allahabad, Allahabad, UP-211002, India

Abstract

In the present paper we study the stationarity of exchange rates using the autoregressive time series model having partially linear time trend. The unit root hypothesis is tested for the monthly time series of Canadian dollar for the period of April 2004 to March 2009 using posterior odds ratio derived under appropriate prior assumptions for the parameters. The impact of ignoring nonlinear part on posterior odds ratio has been analyzed.

Key words and phases: autoregressive models; partial linear model; unit root hypothesis; prior distribution; posterior odds ratio.