Exact Discrete Representations of Linear Continuous Time Models with Mixed Frequency Data

Michael Alan Thornton

doi:10.1111/jtsa.12471

Exact Discrete Representations of Linear Continuous Time Models with Mixed Frequency Data

Michael Alan Thornton

Economics

Research output: Contribution to journal › Article › peer-review

Abstract

The time aggregation of vector linear processes containing (i) mixed stock-
ow data and (ii) aggregated at mixed frequencies, is explored, focusing on a method to translate the parameters of the underlying continuous time model into those of an equivalent model of the observed data. Based on manipulations of a general state-space form, the results may be used to model multiple frequencies or aggregation schemes. Estimation of the continuous
time parameters via the ARMA representation of the observable data vector is discussed and demonstrated in an application to model stock price and dividend data. Simulation evidence suggests that these estimators have superior properties to the traditional approach of concentrating the data to a single low frequency.

Original language	English
Article number	5
Pages (from-to)	951-967
Number of pages	17
Journal	Journal of Time Series Analysis
Volume	40
Issue number	6
Early online date	6 May 2019
DOIs	https://doi.org/10.1111/jtsa.12471
Publication status	E-pub ahead of print - 6 May 2019

Bibliographical note

© 2019 John Wiley & Sons Ltd. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

Keywords

Time aggregation
CARMA process
mixed frequency
State space model
exact discrete representation
the exact discrete representation
state space

Access to Document

10.1111/jtsa.12471

CTMF_final
© 2019 John Wiley & Sons Ltd. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.
Accepted author manuscript, 317 KB

Cite this

@article{25026ae23cd54fb9aad2bb536d6cab55,

title = "Exact Discrete Representations of Linear Continuous Time Models with Mixed Frequency Data",

abstract = "The time aggregation of vector linear processes containing (i) mixed stock-ow data and (ii) aggregated at mixed frequencies, is explored, focusing on a method to translate the parameters of the underlying continuous time model into those of an equivalent model of the observed data. Based on manipulations of a general state-space form, the results may be used to model multiple frequencies or aggregation schemes. Estimation of the continuoustime parameters via the ARMA representation of the observable data vector is discussed and demonstrated in an application to model stock price and dividend data. Simulation evidence suggests that these estimators have superior properties to the traditional approach of concentrating the data to a single low frequency.",

keywords = "Time aggregation, CARMA process, mixed frequency, State space model, exact discrete representation, the exact discrete representation, state space",

author = "Thornton, {Michael Alan}",

note = "{\textcopyright} 2019 John Wiley & Sons Ltd. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details.",

year = "2019",

month = may,

day = "6",

doi = "10.1111/jtsa.12471",

language = "English",

volume = "40",

pages = "951--967",

journal = "Journal of Time Series Analysis",

issn = "0143-9782",

publisher = "Wiley-Blackwell",

number = "6",

}

TY - JOUR

T1 - Exact Discrete Representations of Linear Continuous Time Models with Mixed Frequency Data

AU - Thornton, Michael Alan

N1 - © 2019 John Wiley & Sons Ltd. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details.

PY - 2019/5/6

Y1 - 2019/5/6

N2 - The time aggregation of vector linear processes containing (i) mixed stock-ow data and (ii) aggregated at mixed frequencies, is explored, focusing on a method to translate the parameters of the underlying continuous time model into those of an equivalent model of the observed data. Based on manipulations of a general state-space form, the results may be used to model multiple frequencies or aggregation schemes. Estimation of the continuoustime parameters via the ARMA representation of the observable data vector is discussed and demonstrated in an application to model stock price and dividend data. Simulation evidence suggests that these estimators have superior properties to the traditional approach of concentrating the data to a single low frequency.

AB - The time aggregation of vector linear processes containing (i) mixed stock-ow data and (ii) aggregated at mixed frequencies, is explored, focusing on a method to translate the parameters of the underlying continuous time model into those of an equivalent model of the observed data. Based on manipulations of a general state-space form, the results may be used to model multiple frequencies or aggregation schemes. Estimation of the continuoustime parameters via the ARMA representation of the observable data vector is discussed and demonstrated in an application to model stock price and dividend data. Simulation evidence suggests that these estimators have superior properties to the traditional approach of concentrating the data to a single low frequency.

KW - Time aggregation

KW - CARMA process

KW - mixed frequency

KW - State space model

KW - exact discrete representation

KW - the exact discrete representation

KW - state space

UR - http://www.scopus.com/inward/record.url?scp=85065303612&partnerID=8YFLogxK

U2 - 10.1111/jtsa.12471

DO - 10.1111/jtsa.12471

M3 - Article

VL - 40

SP - 951

EP - 967

JO - Journal of Time Series Analysis

JF - Journal of Time Series Analysis

SN - 0143-9782

IS - 6

M1 - 5

ER -

Exact Discrete Representations of Linear Continuous Time Models with Mixed Frequency Data

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this