Spectral analysis for categorical time series: Scaling and the spectral envelope

David S. Stoffer, David E. Tyler, Andrew McDougall

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

SUMMARY: Many studies produce categorical time series in which harmonic analysis is of interest. Although there exist time domain approaches for the analysis of categorical time series such as Markov chains or link function based regression models, there is apparently little statistical theory or methodology for analyzing qualitative-valued time series in the frequency domain. The purpose of this paper is to initiate the development of a general framework for the frequency domain analysis of categorical time series. In doing so, we discuss the scaling of categorical time series and introduce a new concept that we call the spectral envelope of a categorical time series. We demonstrate our methodology on a data set from a problem in molecular biology.

Original languageEnglish
Pages (from-to)611-622
Number of pages12
JournalBiometrika
Volume80
Issue number3
DOIs
StatePublished - 1 Sep 1993

Fingerprint

Spectral Analysis
Categorical
Spectrum analysis
spectral analysis
Envelope
Time series
time series analysis
Scaling
Frequency Domain Analysis
Frequency domain analysis
Link Function
Molecular biology
Harmonic analysis
Methodology
Molecular Biology
Harmonic Analysis
Markov Chains
Markov processes
molecular biology
Frequency Domain

Keywords

  • Asymptotic distribution of latent roots and vectors
  • DNA sequencing
  • Frequency domain analysis
  • Markov chain
  • Multinomial time series
  • Scaling
  • Spectral envelope

Cite this

Stoffer, David S. ; Tyler, David E. ; McDougall, Andrew. / Spectral analysis for categorical time series : Scaling and the spectral envelope. In: Biometrika. 1993 ; Vol. 80, No. 3. pp. 611-622.
@article{596541ca97a84606b4f9b7523dfaedd4,
title = "Spectral analysis for categorical time series: Scaling and the spectral envelope",
abstract = "SUMMARY: Many studies produce categorical time series in which harmonic analysis is of interest. Although there exist time domain approaches for the analysis of categorical time series such as Markov chains or link function based regression models, there is apparently little statistical theory or methodology for analyzing qualitative-valued time series in the frequency domain. The purpose of this paper is to initiate the development of a general framework for the frequency domain analysis of categorical time series. In doing so, we discuss the scaling of categorical time series and introduce a new concept that we call the spectral envelope of a categorical time series. We demonstrate our methodology on a data set from a problem in molecular biology.",
keywords = "Asymptotic distribution of latent roots and vectors, DNA sequencing, Frequency domain analysis, Markov chain, Multinomial time series, Scaling, Spectral envelope",
author = "Stoffer, {David S.} and Tyler, {David E.} and Andrew McDougall",
year = "1993",
month = "9",
day = "1",
doi = "10.1093/biomet/80.3.611",
language = "English",
volume = "80",
pages = "611--622",
journal = "Biometrika",
issn = "0006-3444",
publisher = "Oxford University Press",
number = "3",

}

Spectral analysis for categorical time series : Scaling and the spectral envelope. / Stoffer, David S.; Tyler, David E.; McDougall, Andrew.

In: Biometrika, Vol. 80, No. 3, 01.09.1993, p. 611-622.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Spectral analysis for categorical time series

T2 - Scaling and the spectral envelope

AU - Stoffer, David S.

AU - Tyler, David E.

AU - McDougall, Andrew

PY - 1993/9/1

Y1 - 1993/9/1

N2 - SUMMARY: Many studies produce categorical time series in which harmonic analysis is of interest. Although there exist time domain approaches for the analysis of categorical time series such as Markov chains or link function based regression models, there is apparently little statistical theory or methodology for analyzing qualitative-valued time series in the frequency domain. The purpose of this paper is to initiate the development of a general framework for the frequency domain analysis of categorical time series. In doing so, we discuss the scaling of categorical time series and introduce a new concept that we call the spectral envelope of a categorical time series. We demonstrate our methodology on a data set from a problem in molecular biology.

AB - SUMMARY: Many studies produce categorical time series in which harmonic analysis is of interest. Although there exist time domain approaches for the analysis of categorical time series such as Markov chains or link function based regression models, there is apparently little statistical theory or methodology for analyzing qualitative-valued time series in the frequency domain. The purpose of this paper is to initiate the development of a general framework for the frequency domain analysis of categorical time series. In doing so, we discuss the scaling of categorical time series and introduce a new concept that we call the spectral envelope of a categorical time series. We demonstrate our methodology on a data set from a problem in molecular biology.

KW - Asymptotic distribution of latent roots and vectors

KW - DNA sequencing

KW - Frequency domain analysis

KW - Markov chain

KW - Multinomial time series

KW - Scaling

KW - Spectral envelope

UR - http://www.scopus.com/inward/record.url?scp=0000374354&partnerID=8YFLogxK

U2 - 10.1093/biomet/80.3.611

DO - 10.1093/biomet/80.3.611

M3 - Article

AN - SCOPUS:0000374354

VL - 80

SP - 611

EP - 622

JO - Biometrika

JF - Biometrika

SN - 0006-3444

IS - 3

ER -