On the consistency of bootstrap testing for a parameter on the boundary of the parameter space

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Standard

On the consistency of bootstrap testing for a parameter on the boundary of the parameter space. / Cavaliere, Giuseppe; Nielsen, Heino Bohn; Rahbek, Anders.

I: Journal of Time Series Analysis, Bind 38, Nr. 4, 07.2017, s. 513–534 .

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Harvard

Cavaliere, G, Nielsen, HB & Rahbek, A 2017, 'On the consistency of bootstrap testing for a parameter on the boundary of the parameter space', Journal of Time Series Analysis, bind 38, nr. 4, s. 513–534 . https://doi.org/10.1111/jtsa.12214

APA

Cavaliere, G., Nielsen, H. B., & Rahbek, A. (2017). On the consistency of bootstrap testing for a parameter on the boundary of the parameter space. Journal of Time Series Analysis, 38(4), 513–534 . https://doi.org/10.1111/jtsa.12214

Vancouver

Cavaliere G, Nielsen HB, Rahbek A. On the consistency of bootstrap testing for a parameter on the boundary of the parameter space. Journal of Time Series Analysis. 2017 jul;38(4):513–534 . https://doi.org/10.1111/jtsa.12214

Author

Cavaliere, Giuseppe ; Nielsen, Heino Bohn ; Rahbek, Anders. / On the consistency of bootstrap testing for a parameter on the boundary of the parameter space. I: Journal of Time Series Analysis. 2017 ; Bind 38, Nr. 4. s. 513–534 .

Bibtex

@article{bc4cb4898dcd497f89ec7c39e3da2aeb,
title = "On the consistency of bootstrap testing for a parameter on the boundary of the parameter space",
abstract = "It is well known that with a parameter on the boundary of the parameter space, such as in the classic cases of testing for a zero location parameter or no autoregressive conditional heteroskedasticity (ARCH) effects, the classic nonparametric bootstrap – based on unrestricted parameter estimates – leads to inconsistent testing. In contrast, we show here that for the two aforementioned cases, a nonparametric bootstrap test based on parameter estimates obtained under the null – referred to as ‘restricted bootstrap’ – is indeed consistent. While the restricted bootstrap is simple to implement in practice, novel theoretical arguments are required in order to establish consistency. In particular, since the bootstrap is analysed both under the null hypothesis and under the alternative, non-standard asymptotic expansions are required to deal with parameters on the boundary. Detailed proofs of the asymptotic validity of the restricted bootstrap are given and, for the leading case of testing for no ARCH, a Monte Carlo study demonstrates that the bootstrap quasi-likelihood ratio statistic performs extremely well in terms of empirical size and power for even remarkably small samples, outperforming the standard and bootstrap Lagrange multiplier tests as well as the asymptotic quasi-likelihood ratio test.",
keywords = "Faculty of Social Sciences, bootstrap, boundary, ARCH, location model, C32",
author = "Giuseppe Cavaliere and Nielsen, {Heino Bohn} and Anders Rahbek",
year = "2017",
month = "7",
doi = "10.1111/jtsa.12214",
language = "English",
volume = "38",
pages = "513–534",
journal = "Journal of Time Series Analysis",
issn = "0143-9782",
publisher = "Wiley-Blackwell",
number = "4",

}

RIS

TY - JOUR

T1 - On the consistency of bootstrap testing for a parameter on the boundary of the parameter space

AU - Cavaliere, Giuseppe

AU - Nielsen, Heino Bohn

AU - Rahbek, Anders

PY - 2017/7

Y1 - 2017/7

N2 - It is well known that with a parameter on the boundary of the parameter space, such as in the classic cases of testing for a zero location parameter or no autoregressive conditional heteroskedasticity (ARCH) effects, the classic nonparametric bootstrap – based on unrestricted parameter estimates – leads to inconsistent testing. In contrast, we show here that for the two aforementioned cases, a nonparametric bootstrap test based on parameter estimates obtained under the null – referred to as ‘restricted bootstrap’ – is indeed consistent. While the restricted bootstrap is simple to implement in practice, novel theoretical arguments are required in order to establish consistency. In particular, since the bootstrap is analysed both under the null hypothesis and under the alternative, non-standard asymptotic expansions are required to deal with parameters on the boundary. Detailed proofs of the asymptotic validity of the restricted bootstrap are given and, for the leading case of testing for no ARCH, a Monte Carlo study demonstrates that the bootstrap quasi-likelihood ratio statistic performs extremely well in terms of empirical size and power for even remarkably small samples, outperforming the standard and bootstrap Lagrange multiplier tests as well as the asymptotic quasi-likelihood ratio test.

AB - It is well known that with a parameter on the boundary of the parameter space, such as in the classic cases of testing for a zero location parameter or no autoregressive conditional heteroskedasticity (ARCH) effects, the classic nonparametric bootstrap – based on unrestricted parameter estimates – leads to inconsistent testing. In contrast, we show here that for the two aforementioned cases, a nonparametric bootstrap test based on parameter estimates obtained under the null – referred to as ‘restricted bootstrap’ – is indeed consistent. While the restricted bootstrap is simple to implement in practice, novel theoretical arguments are required in order to establish consistency. In particular, since the bootstrap is analysed both under the null hypothesis and under the alternative, non-standard asymptotic expansions are required to deal with parameters on the boundary. Detailed proofs of the asymptotic validity of the restricted bootstrap are given and, for the leading case of testing for no ARCH, a Monte Carlo study demonstrates that the bootstrap quasi-likelihood ratio statistic performs extremely well in terms of empirical size and power for even remarkably small samples, outperforming the standard and bootstrap Lagrange multiplier tests as well as the asymptotic quasi-likelihood ratio test.

KW - Faculty of Social Sciences

KW - bootstrap

KW - boundary

KW - ARCH

KW - location model

KW - C32

U2 - 10.1111/jtsa.12214

DO - 10.1111/jtsa.12214

M3 - Journal article

VL - 38

SP - 513

EP - 534

JO - Journal of Time Series Analysis

JF - Journal of Time Series Analysis

SN - 0143-9782

IS - 4

ER -

ID: 164405276