Inference on Multivariate Heteroscedastic Time Varying Random Coefficient Models

Liudas Giraitis; George Kapetanios; Tony Yates

doi:10.1111/jtsa.12271

Inference on Multivariate Heteroscedastic Time Varying Random Coefficient Models

Liudas Giraitis, George Kapetanios^*, Tony Yates

^*Corresponding author for this work

King's Business School

Research output: Contribution to journal › Article › peer-review

31 Citations (Scopus)

Abstract

In this article, we introduce the general setting of a multivariate time series autoregressive model with stochastic time-varying coefficients and time-varying conditional variance of the error process. This allows modelling VAR dynamics for non-stationary time series and estimation of time-varying parameter processes by the well-known rolling regression estimation techniques. We establish consistency, convergence rates, and asymptotic normality for kernel estimators of the paths of coefficient processes and provide pointwise valid standard errors. The method is applied to a popular seven-variable dataset to analyse evidence of time variation in empirical objects of interest for the DSGE (dynamic stochastic general equilibrium) literature.

Original language	English
Number of pages	21
Journal	JOURNAL OF TIME SERIES ANALYSIS
Early online date	5 Dec 2017
DOIs	https://doi.org/10.1111/jtsa.12271
Publication status	E-pub ahead of print - 5 Dec 2017

Keywords

Random coefficient models
Time varying estimation

Access to Document

10.1111/jtsa.12271

Cite this

@article{9edbf27d79bc493bb902b73ceca62593,

title = "Inference on Multivariate Heteroscedastic Time Varying Random Coefficient Models",

abstract = "In this article, we introduce the general setting of a multivariate time series autoregressive model with stochastic time-varying coefficients and time-varying conditional variance of the error process. This allows modelling VAR dynamics for non-stationary time series and estimation of time-varying parameter processes by the well-known rolling regression estimation techniques. We establish consistency, convergence rates, and asymptotic normality for kernel estimators of the paths of coefficient processes and provide pointwise valid standard errors. The method is applied to a popular seven-variable dataset to analyse evidence of time variation in empirical objects of interest for the DSGE (dynamic stochastic general equilibrium) literature.",

keywords = "Random coefficient models, Time varying estimation",

author = "Liudas Giraitis and George Kapetanios and Tony Yates",

year = "2017",

month = dec,

day = "5",

doi = "10.1111/jtsa.12271",

language = "English",

journal = "JOURNAL OF TIME SERIES ANALYSIS",

issn = "0143-9782",

publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Inference on Multivariate Heteroscedastic Time Varying Random Coefficient Models

AU - Giraitis, Liudas

AU - Kapetanios, George

AU - Yates, Tony

PY - 2017/12/5

Y1 - 2017/12/5

N2 - In this article, we introduce the general setting of a multivariate time series autoregressive model with stochastic time-varying coefficients and time-varying conditional variance of the error process. This allows modelling VAR dynamics for non-stationary time series and estimation of time-varying parameter processes by the well-known rolling regression estimation techniques. We establish consistency, convergence rates, and asymptotic normality for kernel estimators of the paths of coefficient processes and provide pointwise valid standard errors. The method is applied to a popular seven-variable dataset to analyse evidence of time variation in empirical objects of interest for the DSGE (dynamic stochastic general equilibrium) literature.

AB - In this article, we introduce the general setting of a multivariate time series autoregressive model with stochastic time-varying coefficients and time-varying conditional variance of the error process. This allows modelling VAR dynamics for non-stationary time series and estimation of time-varying parameter processes by the well-known rolling regression estimation techniques. We establish consistency, convergence rates, and asymptotic normality for kernel estimators of the paths of coefficient processes and provide pointwise valid standard errors. The method is applied to a popular seven-variable dataset to analyse evidence of time variation in empirical objects of interest for the DSGE (dynamic stochastic general equilibrium) literature.

KW - Random coefficient models

KW - Time varying estimation

UR - http://www.scopus.com/inward/record.url?scp=85037667453&partnerID=8YFLogxK

U2 - 10.1111/jtsa.12271

DO - 10.1111/jtsa.12271

M3 - Article

AN - SCOPUS:85037667453

SN - 0143-9782

JO - JOURNAL OF TIME SERIES ANALYSIS

JF - JOURNAL OF TIME SERIES ANALYSIS

ER -

Inference on Multivariate Heteroscedastic Time Varying Random Coefficient Models

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this