We construct classifiers for multivariate and functional data. Our approach is based on a kind of distance between data points and classes. The distance measure needs to be robust to outliers and invariant to linear transformations of the data. For this purpose we can use the bagdistance which is based on halfspace depth. It satisfies most of the properties of a norm but is able to reflect asymmetry when the class is skewed. Alternatively we can compute a measure of outlyingness based on the skew-adjusted projection depth. In either case we propose the DistSpace transform which maps each data point to the vector of its distances to all classes, followed by k-nearest neighbor (kNN) classification of the transformed data points. This combines invariance and robustness with the simplicity and wide applicability of kNN. The proposal is compared with other methods in experiments with real and simulated data.
Global Depths for Irregularly Observed Multivariate Functional Data
Two frameworks for multivariate functional depth based on multivariate depths are introduced in this paper. The first framework is multivariate functional integrated depth, and the second framework involves multivariate functional extremal depth, which is an extension of the extremal depth for univariate functional data. In each framework, global and local multivariate functional depths are proposed. The properties of population multivariate functional depths and consistency of finite sample depths to their population versions are established. In addition, finite sample depths under irregularl…
Functional analysis via extensions of the band depth
数据深度的概念长期以来一直用于在多变量环境中获得可靠的位置和规模估计。观察的深度是其相对于数据集或分布的中心性的度量。一组多元观测的数据深度转化为数据的中心向外排序。因此,数据深度提供了中位数到多变量设置(最深观测值)的一般化,并且还可以用于筛选极端观测值或离群值(具有低数据深度的观测值)。数据深度已被用于开发多种用于多变量数据的稳健和非参数方法,例如位置和尺度的非参数检验[Li和Liu(2004)],多变量秩检验[Liu和Singh(1993)],非参数分类和聚类[Jornsten(2004)]和稳健回归[Lesseeuw和Hubert(1999)]。对于多元数据,已经开发了许多不同的数据深度概念。相反,功能数据的数据深度度量直到最近才被提出[Fraiman and Muniz(1999),López-Pintado and Romo(2006 a)]。虽然这两个数据深度度量的定义都是由数据的功能方面激发的,但度量本身实际上相对于域的排列(即定义函数的紧凑区间)是不变的。因此,这些措施同样适用于多变量数据,其中没有明确的数据维度排序。在本文中,我们探讨了一些扩展的功能数据深度,以便考虑到数据维的排序。
Graphical Principal Component Analysis of Multivariate Functional Time Series
School of Mathematics, Sun Yat-sen University(中山大学数学学院);Center for Applied Statistics and School of Statistics, Renmin University of China(中国人民大学统计学院,应用统计中心)
Spatial Principal Component Analysis and Moran Statistics for Multivariate Functional Areal Data
Institute of Mathematical Sciences, Faculty of Science, Universiti Malaya(马来亚大学理学院数学科学研究所);Universiti Malaya Centre for Data Analytics, Universiti Malaya(马来亚大学数据分析中心);Center of Research for Statistical Modelling and Methodology, Faculty of Science, Universiti Malaya(马来亚大学理学院统计建模与方法研究中心);Institut de Mathématiques de Bordeaux, UMR 5251, CNRS, Université de Bordeaux, Bordeaux INP(波尔多大学波尔多数学研究所);Mathematics, Division of Science, New York University Abu Dhabi(纽约大学阿布扎比分校理学院数学系);CNRS, UMR 8524–Laboratoire Paul Painlevé, Inria-Datavers, Université de Lille(里尔大学保罗·潘勒瓦数学研究中心);Independent Researcher(独立研究者)
A General Framework for Multivariate Functional Principal Component Analysis of Amplitude and Phase Variation
函数数据通常包含幅度和相位变化。在许多数据情况下,相位变化被视为滋扰效应,并在预处理过程中被删除,尽管它可能包含有价值的信息。本文主要研究幅度和相位变化的联合主成分分析。由于翘曲函数空间具有复杂的几何结构,分析的一个关键要素是将翘曲函数转换为$L^2(\mathcal{T})$。我们提出了不同的转换方法,并展示了它们如何适合一般的转换类。这使我们能够比较它们的优势和局限性。在PCA的背景下,我们的研究结果提供了参数,有利于集中的对数比变换。我们进一步将Hadjipantelis et al.(2015)和Lee and Jung(2017)的现有方法嵌入到多变量函数PCA的框架中,其中我们研究了基于适当度量的估计器的特性。该方法是通过应用地震说明。
Sparse Functional Boxplots for Multivariate Curves
This paper introduces the sparse functional boxplot and the intensity sparse functional boxplot as practical exploratory tools. Besides being available for complete functional data, they can be used in sparse univariate and multivariate functional data. The sparse functional boxplot, based on the functional boxplot, displays sparseness proportions within the 50\% central region. The intensity sparse functional boxplot indicates the relative intensity of fitted sparse point patterns in the central region. The two-stage functional boxplot, which derives from the functional boxplot to detect outl…
Multivariate Functional Data Modeling with Time-varying Clustering
We consider the situation where multivariate functional data has been collected over time at each of a set of sites. Our illustrative setting is bivariate, monitoring ozone and PM $_{10}$ levels as a function of time over the course of a year at a set of monitoring sites. The data we work with is from 24 monitoring sites in Mexico City which record hourly ozone and PM $_{10}$ levels. We use the data for the year 2017. Hence, we have 48 functions to work with. Our objective is to implement model-based clustering of the functions across the sites. Using our example, such clustering can be consid…