Bootstrapping the Box-Pierce \(Q\) test: a robust test of uncorrelatedness

DOI10.1016/j.jeconom.2005.06.014zbMath1345.62072OpenAlexW2010111628MaRDI QIDQ275269

N. E. Savin, Joel L. Horowitz, John C. Nankervis, Ignacio N. Lobato

Publication date: 25 April 2016

Published in: Journal of Econometrics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jeconom.2005.06.014

zbMATH Keywords

double bootstrapadjusted \(P\)-valuesblocks of blocks bootstrapBox-Pierce \(Q\)serial correlation tests

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Nonparametric robustness (62G35) Nonparametric statistical resampling methods (62G09) Economic time series analysis (91B84)

Related Items

TESTING FOR WHITE NOISE UNDER UNKNOWN DEPENDENCE AND ITS APPLICATIONS TO DIAGNOSTIC CHECKING FOR TIME SERIES MODELS, A Consistent Test for Multivariate Conditional Distributions, An automatic portmanteau test for serial correlation, ROBUST TESTS FOR WHITE NOISE AND CROSS-CORRELATION, White noise testing and model diagnostic checking for functional time series, Papers with John, Wild bootstrap tests for autocorrelation in vector autoregressive models, A computational bootstrap procedure to compare two dependent time series, A portmanteau-type test for detecting serial correlation in locally stationary functional time series, Robust inference on correlation under general heterogeneity, An Asymptotic F Test for Uncorrelatedness in the Presence of Time Series Dependence, Multi-scale tests for serial correlation, Testing a large set of zero restrictions in regression models, with an application to mixed frequency Granger causality, A bootstrapped spectral test for adequacy in weak ARMA models, Testing autocorrelation and partial autocorrelation: Asymptotic methods versus resampling techniques, Moment condition tests for heavy tailed time series, A bootstrap-assisted spectral test of white noise under unknown dependence, Falsifying ARCH/GARCH Models Using Bispectral Based Tests, A MAX-CORRELATION WHITE NOISE TEST FOR WEAKLY DEPENDENT TIME SERIES, Fourier–type tests involving martingale difference processes, Using bootstrap methods to obtain non-normality robust Chow prediction tests.

Uses Software

• RANLUX
• bootlib

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bootstrapping autoregressions with conditional heteroskedasticity of unknown form
• The use of subseries values for estimating the variance of a general statistic from a stationary sequence
• On the invertibility of time series models
• Acceleration of RANLUX
• Properties of moments of a family of GARCH processes
• Subsampling for heteroskedastic time series
• Empirically relevant critical values for hypothesis tests: A bootstrap approach
• Theoretical comparisons of block bootstrap methods
• The jackknife and the bootstrap for general stationary observations
• Inference For Autocorrelations Under Weak Assumptions
• Prepivoting Test Statistics: A Bootstrap View of Asymptotic Refinements
• The Stationary Bootstrap
• Testing for Serial Correlation Against an ARMA(1, 1,) Process
• TESTING FOR ZERO AUTOCORRELATION IN THE PRESENCE OF STATISTICAL DEPENDENCE
• On blocking rules for the bootstrap with dependent data
• Bootstrap Critical Values for Tests Based on Generalized-Method-of-Moments Estimators
• Higher-Order Improvements of a Computationally Attractive k-Step Bootstrap for Extremum Estimators
• Improved nonparametric confidence intervals in time series regressions
• Distribution of Residual Autocorrelations in Autoregressive-Integrated Moving Average Time Series Models
• On Limit Theorems for Quadratic Functions of Discrete Time Series
• Contemporaneous asymmetry in GARCH processes