Inference for Local Distributions at High Sampling Frequencies

A Bootstrap Approach

Ulrich Hounyo, Rasmus T. Varneskov

Research output: Working paperResearchpeer-review

Abstract

We study inference for the local innovations of Itˆo semimartingales. Specifically, we construct a resampling procedure for the empirical CDF of high-frequency innovations that have been standardized
using a nonparametric estimate of its stochastic scale (volatility) and truncated to rid the effect of “large” jumps. Our locally dependent wild bootstrap (LDWB) accommodate issues related to the stochastic scale and jumps as well as account for a special block-wise dependence structure induced by sampling errors. We show that the LDWB replicates first and second-order limit theory from the usual empirical process and the stochastic scale estimate, respectively, as well as an asymptotic bias. Moreover, we design the LDWB sufficiently general to establish asymptotic equivalence between it and and a nonparametric local block bootstrap, also introduced here, up to second-order distribution theory. Finally, we introduce LDWB-aided Kolmogorov-Smirnov tests for local Gaussianity as well as local von-Mises statistics, with and without bootstrap inference, and establish their asymptotic validity using the second-order distribution theory. The finite sample performance of CLT and LDWB-aided local Gaussianity tests are assessed in a simulation study as well as two empirical applications. Whereas the CLT test is oversized, even in large samples, the size of the LDWB tests are accurate, even in small samples. The empirical analysis verifies this pattern, in addition to providing new insights about the distributional properties of equity indices, commodities, exchange rates and popular macro finance variables.
Original languageEnglish
Place of PublicationAarhus
PublisherAarhus Universitet
Number of pages54
Publication statusPublished - 2018
SeriesCreates Research Paper
Number2018-16

Keywords

  • Bootstrap inference
  • High-frequency data
  • Itô semimartingales
  • Kolmogorov-Smirnov test
  • Stable processes
  • von-Mises statistics

Cite this

Hounyo, U., & Varneskov, R. T. (2018). Inference for Local Distributions at High Sampling Frequencies: A Bootstrap Approach. Aarhus: Aarhus Universitet. Creates Research Paper, No. 2018-16
Hounyo, Ulrich ; Varneskov, Rasmus T. / Inference for Local Distributions at High Sampling Frequencies : A Bootstrap Approach. Aarhus : Aarhus Universitet, 2018. (Creates Research Paper; No. 2018-16).
@techreport{2442ab42924e4439a78f2f2c6bb69d9c,
title = "Inference for Local Distributions at High Sampling Frequencies: A Bootstrap Approach",
abstract = "We study inference for the local innovations of Itˆo semimartingales. Specifically, we construct a resampling procedure for the empirical CDF of high-frequency innovations that have been standardizedusing a nonparametric estimate of its stochastic scale (volatility) and truncated to rid the effect of “large” jumps. Our locally dependent wild bootstrap (LDWB) accommodate issues related to the stochastic scale and jumps as well as account for a special block-wise dependence structure induced by sampling errors. We show that the LDWB replicates first and second-order limit theory from the usual empirical process and the stochastic scale estimate, respectively, as well as an asymptotic bias. Moreover, we design the LDWB sufficiently general to establish asymptotic equivalence between it and and a nonparametric local block bootstrap, also introduced here, up to second-order distribution theory. Finally, we introduce LDWB-aided Kolmogorov-Smirnov tests for local Gaussianity as well as local von-Mises statistics, with and without bootstrap inference, and establish their asymptotic validity using the second-order distribution theory. The finite sample performance of CLT and LDWB-aided local Gaussianity tests are assessed in a simulation study as well as two empirical applications. Whereas the CLT test is oversized, even in large samples, the size of the LDWB tests are accurate, even in small samples. The empirical analysis verifies this pattern, in addition to providing new insights about the distributional properties of equity indices, commodities, exchange rates and popular macro finance variables.",
keywords = "Bootstrap inference, High-frequency data, Itˆo semimartingales, Kolmogorov-Smirnov test, Stable processes, von-Mises statistics, Bootstrap inference, High-frequency data, It{\^o} semimartingales, Kolmogorov-Smirnov test, Stable processes, von-Mises statistics",
author = "Ulrich Hounyo and Varneskov, {Rasmus T.}",
year = "2018",
language = "English",
publisher = "Aarhus Universitet",
address = "Denmark",
type = "WorkingPaper",
institution = "Aarhus Universitet",

}

Inference for Local Distributions at High Sampling Frequencies : A Bootstrap Approach. / Hounyo, Ulrich; Varneskov, Rasmus T.

Aarhus : Aarhus Universitet, 2018.

Research output: Working paperResearchpeer-review

TY - UNPB

T1 - Inference for Local Distributions at High Sampling Frequencies

T2 - A Bootstrap Approach

AU - Hounyo, Ulrich

AU - Varneskov, Rasmus T.

PY - 2018

Y1 - 2018

N2 - We study inference for the local innovations of Itˆo semimartingales. Specifically, we construct a resampling procedure for the empirical CDF of high-frequency innovations that have been standardizedusing a nonparametric estimate of its stochastic scale (volatility) and truncated to rid the effect of “large” jumps. Our locally dependent wild bootstrap (LDWB) accommodate issues related to the stochastic scale and jumps as well as account for a special block-wise dependence structure induced by sampling errors. We show that the LDWB replicates first and second-order limit theory from the usual empirical process and the stochastic scale estimate, respectively, as well as an asymptotic bias. Moreover, we design the LDWB sufficiently general to establish asymptotic equivalence between it and and a nonparametric local block bootstrap, also introduced here, up to second-order distribution theory. Finally, we introduce LDWB-aided Kolmogorov-Smirnov tests for local Gaussianity as well as local von-Mises statistics, with and without bootstrap inference, and establish their asymptotic validity using the second-order distribution theory. The finite sample performance of CLT and LDWB-aided local Gaussianity tests are assessed in a simulation study as well as two empirical applications. Whereas the CLT test is oversized, even in large samples, the size of the LDWB tests are accurate, even in small samples. The empirical analysis verifies this pattern, in addition to providing new insights about the distributional properties of equity indices, commodities, exchange rates and popular macro finance variables.

AB - We study inference for the local innovations of Itˆo semimartingales. Specifically, we construct a resampling procedure for the empirical CDF of high-frequency innovations that have been standardizedusing a nonparametric estimate of its stochastic scale (volatility) and truncated to rid the effect of “large” jumps. Our locally dependent wild bootstrap (LDWB) accommodate issues related to the stochastic scale and jumps as well as account for a special block-wise dependence structure induced by sampling errors. We show that the LDWB replicates first and second-order limit theory from the usual empirical process and the stochastic scale estimate, respectively, as well as an asymptotic bias. Moreover, we design the LDWB sufficiently general to establish asymptotic equivalence between it and and a nonparametric local block bootstrap, also introduced here, up to second-order distribution theory. Finally, we introduce LDWB-aided Kolmogorov-Smirnov tests for local Gaussianity as well as local von-Mises statistics, with and without bootstrap inference, and establish their asymptotic validity using the second-order distribution theory. The finite sample performance of CLT and LDWB-aided local Gaussianity tests are assessed in a simulation study as well as two empirical applications. Whereas the CLT test is oversized, even in large samples, the size of the LDWB tests are accurate, even in small samples. The empirical analysis verifies this pattern, in addition to providing new insights about the distributional properties of equity indices, commodities, exchange rates and popular macro finance variables.

KW - Bootstrap inference

KW - High-frequency data

KW - Itˆo semimartingales

KW - Kolmogorov-Smirnov test

KW - Stable processes

KW - von-Mises statistics

KW - Bootstrap inference

KW - High-frequency data

KW - Itô semimartingales

KW - Kolmogorov-Smirnov test

KW - Stable processes

KW - von-Mises statistics

M3 - Working paper

BT - Inference for Local Distributions at High Sampling Frequencies

PB - Aarhus Universitet

CY - Aarhus

ER -