Testing Linearity for Network Autoregressive Models

DOI10.48550/ARXIV.2202.03852MaRDI QIDQ91246zbMATH OpenFDO

Authors Mirko Armillotta, Konstantinos Fokianos, Mirko Armillotta, Konstantinos Fokianos

Publication date 8 February 2022

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2202.03852, https://projecteuclid.org/journals/annals-of-statistics/volume-51/issue-6/Nonlinear-network-autoregression/10.1214/23-AOS2345.full

zbMATH Keywords

hypothesis testingcontractionincreasing dimensionmultivariate count time series

Mathematics Subject Classification ID

General nonlinear regression (62J02) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)

Abstract: A quasi-score linearity test for continuous and count network autoregressive models is developed. We establish the asymptotic distribution of the test when the network dimension is fixed or increasing, under the null hypothesis of linearity and Pitman's local alternatives. When the parameters are identifiable, the test statistic approximates a chi-square and noncentral chi-square asymptotic distribution, respectively. These results still hold true when the parameters tested belong to the boundary of their space. When we deal with non-identifiable parameters, a suitable test is proposed and its asymptotic distribution is established when the network dimension is fixed. Since, in general, critical values of such test cannot be tabulated, the empirical computation of the p-values is implemented using a feasible bound. Bootstrap approximations are also provided. Moreover, consistency and asymptotic normality of the quasi maximum likelihood estimator is established for continuous and count nonlinear network autoregressions, under standard smoothness conditions. A simulation study and two data examples complement this work.

Recommendations

• Network vector autoregression
• Large sample inference based on multiple observations from nonlinear autoregressive processes
• Identification of nonlinear VAR models using general conditional independence graphs
• On nonlinear models for time series
• Nonlinear Autoregression with Positive Innovations

Cites work

• scientific article; zbMATH DE number 3150484 (Why is no real title available?)
• scientific article; zbMATH DE number 3990600 (Why is no real title available?)
• scientific article; zbMATH DE number 3742453 (Why is no real title available?)
• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• scientific article; zbMATH DE number 48093 (Why is no real title available?)
• scientific article; zbMATH DE number 51427 (Why is no real title available?)
• scientific article; zbMATH DE number 1168330 (Why is no real title available?)
• scientific article; zbMATH DE number 1821192 (Why is no real title available?)
• scientific article; zbMATH DE number 5224144 (Why is no real title available?)
• A bivariate INAR(1) process with application
• A dynamic logistic regression for network link prediction
• A negative binomial model for time series of counts
• A note on the stability of multivariate non-linear time series with an application to time series of counts
• A strong law of large numbers for triangular mixingale arrays
• Asymptotic properties of quasi-maximum likelihood estimators in observation-driven time series models
• Asymptotic theory of statistical inference for time series
• Beta–Negative Binomial Auto-Regressions for Modelling Integer-Valued Time Series with Extreme Observations
• Bootstrapping general empirical measures
• Chaos: A statistical perspective
• Consistency in Nonlinear Econometric Models: A Generic Uniform Law of Large Numbers
• Ergodicity of observation-driven time series models and consistency of the maximum likelihood estimator
• Estimation and Prediction for Stochastic Blockstructures
• Estimation and testing linearity for non-linear mixed Poisson autoregressions
• Grouped network vector autoregression
• Inference When a Nuisance Parameter Is Not Identified Under the Null Hypothesis
• Mixing: Properties and examples
• Modelling Nonlinear Economic Time Series
• Multivariate count autoregression
• Network GARCH model
• Network quantile autoregression
• Network vector autoregression
• Nonlinear Poisson autoregression
• Nonlinear time series. Nonparametric and parametric methods
• Observation-driven models for Poisson counts
• Observation-driven models for discrete-valued time series
• On composite likelihood estimation of a multivariate INAR(1) model
• On weak dependence conditions for Poisson autoregressions
• On weak dependence conditions: the case of discrete valued processes
• Optimal Tests when a Nuisance Parameter is Present Only Under the Alternative
• Poisson QMLE of count time series models
• Poisson autoregression
• Quasi-likelihood and its application. A general approach to optimal parameter estimation
• Quasi-likelihood inference for negative binomial time series models
• Random Graphs
• SUP-TESTS FOR LINEARITY IN A GENERAL NONLINEAR AR(1) MODEL
• Self-excited threshold Poisson autoregression
• Some properties of multivariate INAR(1) processes
• Specification testing in nonlinear and nonstationary time series autoregression
• Specification, estimation, and evaluation of smooth transition autoregressive models
• Stationarity of generalized autoregressive moving average models
• Statistical analysis of network data with R
• Stochastic Blockmodels for Directed Graphs
• Theory and inference for a class of nonlinear models with application to time series of counts
• Variance inequalities for quadratic forms with applications

Cited in

(4)

• Network vector autoregression
• Nonlinear factor models for network and panel data
• scientific article; zbMATH DE number 125307 (Why is no real title available?)
• PNAR

This page was built for publication: Testing Linearity for Network Autoregressive Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q91246)