Two procedures for robust monitoring of probability distributions of economic data stream induced by depth functions

Journal Title: Operations Research and Decisions - Year 2015, Vol 25, Issue 1

Abstract

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

Authors and Affiliations

Daniel KOSIOROWSKI

Keywords

Related Articles

Choquet integral calculus on a continuous support and its applications

The results of the calculation of the Choquet integral of a monotone function on the nonnegative real line have been described. Next, the authors prepresented Choquet integral of nonmonotone functions, by constructing mo...

Determination of the optimal exchange rate via control of the domestic interest rate in Nigeria

An economic scenario has been considered where the government seeks to achieve a favourable balance-of-payments over a fixed planning horizon through exchange rate policy and control of the domestic interest rate. The dy...

A comparative analysis of methods of measuring a company's intellectual capital.

Intellectual capital is, in general, considered to be a component of a company’s market value, which is not always reflected in its financial statements. The authors analyzed 21 of the most common methods of measuring co...

The coexistence of controlling and other management methods

The effects of the coexistence of Controlling and other management methods (benchmarking, BPM, BPR, BSC, Competency-based Management, CRM, ERP, KM, LM, Outsourcing, Six Sigma, TQM) have been analysed. The complexity and...

Perturbation algorithm for a minimax regret minimum spanning tree problem

The problem of finding a robust spanning tree has been analysed. The problem consists of determining a minimum spanning tree of a graph with uncertain edge costs. We should determine a spanning tree that minimizes the di...

Download PDF file
  • EP ID EP323589
  • DOI -
  • Views 36
  • Downloads 0

How To Cite

Daniel KOSIOROWSKI (2015). Two procedures for robust monitoring of probability distributions of economic data stream induced by depth functions. Operations Research and Decisions, 25(1), 55-79. https://europub.co.uk/articles/-A-323589