Department of Economics and Business Economics

A Non-standard Empirical Likelihood for Time Series

Research output: Working paperResearch

Standard

A Non-standard Empirical Likelihood for Time Series. / Nordman, Daniel J.; Bunzel, Helle; Lahiri, Soumendra N.

Aarhus : Institut for Økonomi, Aarhus Universitet, 2012.

Research output: Working paperResearch

Harvard

Nordman, DJ, Bunzel, H & Lahiri, SN 2012 'A Non-standard Empirical Likelihood for Time Series' Institut for Økonomi, Aarhus Universitet, Aarhus.

APA

Nordman, D. J., Bunzel, H., & Lahiri, S. N. (2012). A Non-standard Empirical Likelihood for Time Series. Aarhus: Institut for Økonomi, Aarhus Universitet. CREATES Research Papers, No. 2012-55

CBE

Nordman DJ, Bunzel H, Lahiri SN. 2012. A Non-standard Empirical Likelihood for Time Series. Aarhus: Institut for Økonomi, Aarhus Universitet.

MLA

Nordman, Daniel J., Helle Bunzel and Soumendra N. Lahiri A Non-standard Empirical Likelihood for Time Series. Aarhus: Institut for Økonomi, Aarhus Universitet. (CREATES Research Papers; Journal number 2012-55). 2012., 27 p.

Vancouver

Nordman DJ, Bunzel H, Lahiri SN. A Non-standard Empirical Likelihood for Time Series. Aarhus: Institut for Økonomi, Aarhus Universitet. 2012 Dec 4.

Author

Nordman, Daniel J. ; Bunzel, Helle ; Lahiri, Soumendra N. / A Non-standard Empirical Likelihood for Time Series. Aarhus : Institut for Økonomi, Aarhus Universitet, 2012. (CREATES Research Papers; No. 2012-55).

Bibtex

@techreport{64de369a58d7482c928a19869721d23a,
title = "A Non-standard Empirical Likelihood for Time Series",
abstract = "Standard blockwise empirical likelihood (BEL) for stationary, weakly dependent time series requires specifying a fixed block length as a tuning parameter for setting confidence regions. This aspect can be difficult and impacts coverage accuracy. As an alternative, this paper proposes a new version of BEL based on a simple, though non-standard, data-blocking rule which uses a data block of every possible length. Consequently, the method involves no block selection and is also anticipated to exhibit better coverage performance. Its non-standard blocking scheme, however, induces non-standard asymptotics and requires a significantly different development compared to standard BEL. We establish the large-sample distribution of log-ratio statistics from the new BEL method for calibrating confidence regions for mean or smooth function parameters of time series. This limit law is not the usual chi-square one, but is distribution-free and can be reproduced through straightforward simulations. Numerical studies indicate that the proposed method generally exhibits better coverage accuracy than standard BEL.",
keywords = "Brownian motion, Confidence Regions, Stationarity, Weak Dependence, Brownian motion, Confidence Regions, Stationarity, Weak Dependence",
author = "Nordman, {Daniel J.} and Helle Bunzel and Lahiri, {Soumendra N.}",
year = "2012",
month = "12",
day = "4",
language = "English",
series = "CREATES Research Papers",
publisher = "Institut for {\O}konomi, Aarhus Universitet",
number = "2012-55",
type = "WorkingPaper",
institution = "Institut for {\O}konomi, Aarhus Universitet",

}

RIS

TY - UNPB

T1 - A Non-standard Empirical Likelihood for Time Series

AU - Nordman, Daniel J.

AU - Bunzel, Helle

AU - Lahiri, Soumendra N.

PY - 2012/12/4

Y1 - 2012/12/4

N2 - Standard blockwise empirical likelihood (BEL) for stationary, weakly dependent time series requires specifying a fixed block length as a tuning parameter for setting confidence regions. This aspect can be difficult and impacts coverage accuracy. As an alternative, this paper proposes a new version of BEL based on a simple, though non-standard, data-blocking rule which uses a data block of every possible length. Consequently, the method involves no block selection and is also anticipated to exhibit better coverage performance. Its non-standard blocking scheme, however, induces non-standard asymptotics and requires a significantly different development compared to standard BEL. We establish the large-sample distribution of log-ratio statistics from the new BEL method for calibrating confidence regions for mean or smooth function parameters of time series. This limit law is not the usual chi-square one, but is distribution-free and can be reproduced through straightforward simulations. Numerical studies indicate that the proposed method generally exhibits better coverage accuracy than standard BEL.

AB - Standard blockwise empirical likelihood (BEL) for stationary, weakly dependent time series requires specifying a fixed block length as a tuning parameter for setting confidence regions. This aspect can be difficult and impacts coverage accuracy. As an alternative, this paper proposes a new version of BEL based on a simple, though non-standard, data-blocking rule which uses a data block of every possible length. Consequently, the method involves no block selection and is also anticipated to exhibit better coverage performance. Its non-standard blocking scheme, however, induces non-standard asymptotics and requires a significantly different development compared to standard BEL. We establish the large-sample distribution of log-ratio statistics from the new BEL method for calibrating confidence regions for mean or smooth function parameters of time series. This limit law is not the usual chi-square one, but is distribution-free and can be reproduced through straightforward simulations. Numerical studies indicate that the proposed method generally exhibits better coverage accuracy than standard BEL.

KW - Brownian motion, Confidence Regions, Stationarity, Weak Dependence

KW - Brownian motion, Confidence Regions, Stationarity, Weak Dependence

M3 - Working paper

T3 - CREATES Research Papers

BT - A Non-standard Empirical Likelihood for Time Series

PB - Institut for Økonomi, Aarhus Universitet

CY - Aarhus

ER -