
Xiaofei XuWuhan University | WHU · School of Mathematics and Statistics
Xiaofei Xu
Doctor of Philosophy
About
18
Publications
3,870
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
37
Citations
Introduction
Functional time series, Nonstationarity, High-dimensional time series, Forecasting
Additional affiliations
January 2021 - present
June 2020 - December 2020
September 2019 - June 2020
Education
August 2015 - March 2020
July 2011 - July 2015
Publications
Publications (18)
In this chapter, we illustrate some numerical studies investigating the finite sample performance of the tests for one-way and two-way models presented in the previous chapters. First, we demonstrate the performance of the Lawley–Hotelling test statistic (LH), the likelihood ratio test statistic (LR), and the Bartlett–Nanda–Pillai test statistic (B...
The optimality of the tests has not been discussed so far. For the test for the existence of fixed effects, the locally asymptotically maximin test based on local asymptotic normality (LAN) was proposed by Hallin et al. (2021) for i.i.d. data. In this chapter, we show that the one-way random effect model for i.i.d. sequences does not have the LAN p...
While ANOVA for independent errors has been well-tuned, ANOVA for time-dependent errors is in its infancy. In this chapter, we extend the one-way fixed model with independent errors and groups to a one-way fixed model with time-dependent errors and independent groups.
This chapter extends the one-way models with time-dependent errors and correlated groups dealt with in Chapter 4 to the two-way models with time-dependent errors and correlated groups. We propose a test for the existence of random effects in Section 5.1 and a test for the existence of random interactions in Section 5.2. We show that the tests have...
The independence between groups was imposed in Chapter 2 but this assumption is not fulfilled by some real data, e.g., stock prices. This chapter extends one-way fixed models with time-dependent errors and independent groups dealt with in Chapter 2 to one-way fixed and random models with time-dependent errors and correlated groups. We propose a tes...
Although finite dimensionality was assumed in Chapter 2, ANOVA for high-dimensional time-dependent errors has not been fully developed. In this chapter, we extend the one-way fixed model with time-dependent errors and independent groups to a one-way fixed model with high-dimensional time-dependent errors and independent groups. In Section 3.1, we d...
This chapter analyzes the average wind speed data observed in seven cities located in coastal and inland areas in Japan by assuming the one-way effect model with time-dependent errors and correlated groups. The purpose is to assess the existence of area effects. To this end, both the \( T_{\textrm{GALT},n}\) statistic designed for correlated groups...
In this paper, we propose tests for the existence of random effects and interactions for two-way models with dependent errors. We prove that the proposed tests are asymptotically distribution-free which have asymptotically size \({{\tau }}\) and are consistent. We elucidate the nontrivial power under the local alternative when a sample size tends t...
We consider the minimax estimation of time series in view of higher order asymptotic theory. Under the framework of Bayesian inference, we focus on the Bayes estimator and the Bayesian Whittle estimator for parameter estimation. It is shown that these estimators are minimax with respect to the Bayes risk of higher order bias appeared in their asymp...
About 23% of the German energy demand is supplied by natural gas. Additionally, for about the same amount Germany serves as a transit country. Thereby, the German network represents a central hub in the European natural gas transport network. The transport infrastructure is operated by transmissions system operators (TSOs). The number one priority...
For Gaussian stationary processes, the likelihood functions include the inverse and determinant of the covariance matrices, and Whittle likelihood is considered as a standard technique to avoid expensive matrix determinant and inversions under large sample size. In this paper, we investigate the difference between the exact likelihood and Whittle l...
In many business and economics studies, researchers have sought to measure the dynamic dependence of curves with high-dimensional mixed-type predictors. We propose a partially functional autoregressive model (pFAR) where the serial dependence of curves is controlled by coefficient operators that are defined on a two-dimensional surface, and the ind...
This is a discussion on the paper "Text Selection" by Kelly et al. (2021).
We propose a nonlinear network autoregressive (NNAR) model to investigate the dynamics of complex network time series with high-dimensionality and nonlinear spatial-temporal dependence. We assume that the current network at a given time point non-linearly depends on the lagged values, neighborhood effect, and a set of node-specific covariates via a...
This research proposes a comprehensive ALG model (Adaptive Log-linear zeroin
ated Generalized Poisson integer-valued GARCH) to describe the dynamics of integervalued
time series of crime incidents with the features of autocorrelation, heteroscedasticity,
over-dispersion, and excessive number of zero observations. The proposed ALG
model captures ti...
In this data‐rich era, it is essential to develop advanced techniques to analyze and understand large amounts of data and extract the underlying information in a flexible way. We provide a review study on the state‐of‐the‐art statistical time series models for univariate and multivariate functional data with serial dependence. In particular, we rev...