Not Available for Download

Spectral Analysis: Time Series Analysis in Frequency Domain

ICFAI University Journal of Applied Economics, Vol. 8, No. 5 & 6, pp. 83-101, September-November 2009

Posted: 11 Aug 2009 Last revised: 10 Feb 2010

Viswanathan Iyer

ICFAI Business School, Hyderabad

Kaushik Roy Chowdhury

M.Phil/Ph.D, Indira Gandhi Institute of Devevlopment Research

Date Written: August 9, 2009

Abstract

This paper describes how the frequency domain analysis provides an alternative approach to time domain analysis for a given time series. Spectral and periodogram analysis for a given time series are performed to detect trends and seasonalities in the data. A cross-spectral analysis is used to find causality and co-movements in two different time series. Univariate frequency domain analysis is done using time series of varying nature including simulated white noise process, random walk process, AR (1) process, Wolfer’s Sunspot Data and Box-Jenkins Airlines Data; while bivariate (cross spectral) analysis is done for macroeconomic variables such as Money in Circulation and Inflation.

Keywords: spectral analysis, periodogram, cross-spectral analysis, time-series analysis

JEL Classification: C1, C22, C32, E4

Suggested Citation

Iyer, Viswanathan and Roy Chowdhury, Kaushik, Spectral Analysis: Time Series Analysis in Frequency Domain (August 9, 2009). ICFAI University Journal of Applied Economics, Vol. 8, No. 5 & 6, pp. 83-101, September-November 2009. Available at SSRN: https://ssrn.com/abstract=1446243

Viswanathan Iyer

ICFAI Business School, Hyderabad ( email )

Donthanapally Shankarapalli Road
Hyderabad, Andhra Pradesh 501203
India

Kaushik Roy Chowdhury (Contact Author)

M.Phil/Ph.D, Indira Gandhi Institute of Devevlopment Research ( email )

Gen A.K. Vaidya Marg Santoshnagar
Goregaon (East)
Mumbai, Maharashtra 400065
India

Paper statistics

Abstract Views
810