CREATES

Missing observations in observation-driven time series models

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Missing observations in observation-driven time series models. / Blasques, F.; Gorgi, P.; Koopman, S. J.

In: Journal of Econometrics, Vol. 221, No. 2, 04.2021, p. 542-568.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

Blasques, F, Gorgi, P & Koopman, SJ 2021, 'Missing observations in observation-driven time series models', Journal of Econometrics, vol. 221, no. 2, pp. 542-568. https://doi.org/10.1016/j.jeconom.2020.07.043

APA

CBE

MLA

Vancouver

Author

Blasques, F. ; Gorgi, P. ; Koopman, S. J. / Missing observations in observation-driven time series models. In: Journal of Econometrics. 2021 ; Vol. 221, No. 2. pp. 542-568.

Bibtex

@article{11ed1abb94b345dfa93ffc2b42ee3c54,
title = "Missing observations in observation-driven time series models",
abstract = "We argue that existing methods for the treatment of missing observations in time-varying parameter observation-driven models lead to inconsistent inference. We provide a formal proof of this inconsistency for a Gaussian model with time-varying mean. A Monte Carlo simulation study supports this theoretical result and illustrates how the inconsistency problem extends to score-driven and, more generally, to observation-driven models, which include well-known models for conditional volatility. To overcome the problem of inconsistent inference, we propose a novel estimation procedure based on indirect inference. This easy-to-implement method delivers consistent inference. The asymptotic properties of the new method are formally derived. Our proposed estimation procedure shows a promising performance in a Monte Carlo simulation exercise as well as in an empirical study concerning the measurement of conditional volatility from financial returns data.",
keywords = "Consistency, Indirect inference, Missing data, Observation-driven models, Volatility",
author = "F. Blasques and P. Gorgi and Koopman, {S. J.}",
note = "Funding Information: Blasques is thankful to the Dutch National Science Foundation (NWO) grant VIDI.195.099 for financial support. Koopman acknowledges support from CREATES, Aarhus University, Denmark, funded by Danish National Research Foundation, (DNRF78). Publisher Copyright: {\textcopyright} 2020 Elsevier B.V. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",
year = "2021",
month = apr,
doi = "10.1016/j.jeconom.2020.07.043",
language = "English",
volume = "221",
pages = "542--568",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

RIS

TY - JOUR

T1 - Missing observations in observation-driven time series models

AU - Blasques, F.

AU - Gorgi, P.

AU - Koopman, S. J.

N1 - Funding Information: Blasques is thankful to the Dutch National Science Foundation (NWO) grant VIDI.195.099 for financial support. Koopman acknowledges support from CREATES, Aarhus University, Denmark, funded by Danish National Research Foundation, (DNRF78). Publisher Copyright: © 2020 Elsevier B.V. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2021/4

Y1 - 2021/4

N2 - We argue that existing methods for the treatment of missing observations in time-varying parameter observation-driven models lead to inconsistent inference. We provide a formal proof of this inconsistency for a Gaussian model with time-varying mean. A Monte Carlo simulation study supports this theoretical result and illustrates how the inconsistency problem extends to score-driven and, more generally, to observation-driven models, which include well-known models for conditional volatility. To overcome the problem of inconsistent inference, we propose a novel estimation procedure based on indirect inference. This easy-to-implement method delivers consistent inference. The asymptotic properties of the new method are formally derived. Our proposed estimation procedure shows a promising performance in a Monte Carlo simulation exercise as well as in an empirical study concerning the measurement of conditional volatility from financial returns data.

AB - We argue that existing methods for the treatment of missing observations in time-varying parameter observation-driven models lead to inconsistent inference. We provide a formal proof of this inconsistency for a Gaussian model with time-varying mean. A Monte Carlo simulation study supports this theoretical result and illustrates how the inconsistency problem extends to score-driven and, more generally, to observation-driven models, which include well-known models for conditional volatility. To overcome the problem of inconsistent inference, we propose a novel estimation procedure based on indirect inference. This easy-to-implement method delivers consistent inference. The asymptotic properties of the new method are formally derived. Our proposed estimation procedure shows a promising performance in a Monte Carlo simulation exercise as well as in an empirical study concerning the measurement of conditional volatility from financial returns data.

KW - Consistency

KW - Indirect inference

KW - Missing data

KW - Observation-driven models

KW - Volatility

UR - http://www.scopus.com/inward/record.url?scp=85089466384&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2020.07.043

DO - 10.1016/j.jeconom.2020.07.043

M3 - Journal article

AN - SCOPUS:85089466384

VL - 221

SP - 542

EP - 568

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -