arXiv subjects

Daniel Kosiorowski

Publications and source records attributed to Daniel Kosiorowski.

8 recordsLinked to original sources

arXiv2019

DepthProc An R Package for Robust Exploration of Multidimensional Economic Phenomena

Data depth concept offers a variety of powerful and user friendly tools for robust exploration and inference for multivariate socio-economic phenomena. The offered techniques may be successfully used in cases of lack of our knowledge on parametric models generating data due to their nonparametric nature. This paper presents the R package DepthProc, which is available under GPL-2 licence on CRAN and R-forge servers for Windows, Linux and OS X platform. The package consist of among others successful implementations of several data depth techniques involving multivariate quantile-quantile plots, multivariate scatter estimators, local Wilcoxon tests for multivariate as well as for functional data, robust regressions. In order to show the package capabilities, real datasets concerning United Nations Fourth Millennium Goal and the Internet users activity are used.

stat.CO↗

arXiv2018

Generalized Exponential smoothing in prediction of hierarchical time series

Shang and Hyndman (2017) proposed a grouped functional time series forecasting approach as a combination of individual forecasts obtained using generalized least squares method. We modify their methodology using generalized exponential smoothing technique for the most disaggregated functional time series in order to obtain more robust predictor. We discuss some properties of our proposals basing on results obtained via simulation studies and analysis of real data related to a prediction of a demand for electricity in Australia in 2016.

stat.ME↗

arXiv2018

New Proposals of a Stress Measure in a Capital and its Robust Estimator

In this paper a novel approach for a measurement of stresses in a capital, which induce the capital flows between economic systems, is proposed. The proposals appeal to an apparatus offered by the statistical theory of shape. We propose a stress functional basing on a concept of mean shape determined by representative particles of a capital carrier. We also propose methods of describing changes in an amount and a structure of stresses in a capital appealing, among others, to a Bookstein's pair of thin plain spline deformation, and a measure of a shape variability. We apply our approach to an indirect verification of the hypothesis according to which a capital flow between economic systems is related to an activity of an inner force related to stresses in a capital. We indicate, that the stresses create a phenomenon analogous to the heat, which may be interpreted in terms of a positive economic external effect, which attracts a capital from environment of a system to the system. For empirical studies we propose robust approach to estimate the stress functional basing on the data depth concept. In the empirical research we use data on five branch stock indexes from Warsaw Stock Exchange. The studied period involves the financial crisis of 2007.

econ.GN↗

arXiv2017

Forecasting of a Hierarchical Functional Time Series on Example of Macromodel for Day and Night Air Pollution in Silesia Region: A Critical Overview

In economics we often face a system, which intrinsically imposes a structure of hierarchy of its components, i.e., in modelling trade accounts related to foreign exchange or in optimization of regional air protection policy. A problem of reconciliation of forecasts obtained on different levels of hierarchy has been addressed in the statistical and econometric literature for many times and concerns bringing together forecasts obtained independently at different levels of hierarchy. This paper deals with this issue in case of a hierarchical functional time series. We present and critically discuss a state of art and indicate opportunities of an application of these methods to a certain environment protection problem. We critically compare the best predictor known from the literature with our own original proposal. Within the paper we study a macromodel describing a day and night air pollution in Silesia region divided into five subregions.

econ.EM↗

arXiv2017

Aggregated moving functional median in robust prediction of hierarchical functional time series - an application to forecasting web portal users behaviors

In this article, a new nonparametric and robust method of forecasting hierarchical functional time series is presented. The method is compared with Hyndman and Shang's method with respect to their unbiasedness, effectiveness, robustness, and computational complexity. Taking into account results of the analytical, simulation and empirical studies, we come to the conclusion that our proposal is superior over the proposal of Hyndman and Shang with respect to some statistical criteria and especially with respect to robustness and computational complexity. An empirical usefulness of our method is presented on example of management of a certain web portal divided into four subservices. An extensive simulation study involving hierarchical systems consisted of FAR(1) processes and Wiener processes has been conducted as well.

stat.CO↗

arXiv2016

Detecting a Structural Change in Functional Time Series Using Local Wilcoxon Statistic

Functional data analysis (FDA) is a part of modern multivariate statistics that analyses data providing information about curves, surfaces or anything else varying over a certain continuum. In economics and empirical finance we often have to deal with time series of functional data, where we cannot easily decide, whether they are to be considered as homogeneous or heterogeneous. At present a discussion on adequate tests of homogenity for functional data is carried. We propose a novel statistic for detetecting a structural change in functional time series based on a local Wilcoxon statistic induced by a local depth function proposed by Paindaveine and Van Bever (2013).

stat.ME↗

arXiv2015

Two Procedures for Robust Monitoring of Probability Distributions of Economic Data Streams induced by Depth Functions

Data streams (streaming data) consist of transiently observed, evolving in time, multidimensional data sequences that challenge our computational and/or inferential capabilities. In this paper we propose user friendly approaches for robust monitoring of selected properties of unconditional and conditional distribution of the stream basing on depth functions. Our proposals are robust to a small fraction of outliers and/or inliers but sensitive to a regime change of the stream at the same time. Their implementations are available in our free R package DepthProc.

stat.AP↗

arXiv2015

Evaluation of the Fourth Millennium Development Goal Realisation Using Robust and Nonparametric Tools Offered by Data Depth Concept

We briefly communicate results of a nonparametric and robust evaluation of effects of \emph{the Fourth Millennium Development Goal of United Nations}. Main aim of the goal was reducing by two thirds, between 1990--2015, the under five months child mortality. Our novel analysis was conducted by means of very powerful and user friendly tools offered by the \emph{Data Depth Concept} being a collection of multivariate techniques basing on multivariate generalizations of quantiles, ranges and order statistics. Results of our analysis are more convincing than results obtained using classical statistical tools.

stat.AP↗