Bayesian Group Analysis

W. Von Der Linden, V. Dose, A. Ramaswami

Research output: Chapter in Book/Report/Conference proceedingOther chapter contributionResearch

Abstract

In many fields of research the following problem is encountered: a large collection of data is given for which a detailed theory is yet missing. To gain insight into the underlying problem it is important to reveal the interrelationships in the data and to determine the relevant input and response quantities. A central part of this task is to find the natural splitting of the data into groups and to analyze the respective characteristics. Bayesian probability theory is invoked for a consistent treatment of these problems. Due to Ockham’s Razor, which is an integral part of the theory, the simplest group configuration that still fits the data has the highest probability. In addition the Bayesian approach allows to eliminate outliers, which otherwise could lead to erroneous conclusions. Simple textbook and mock data sets are analyzed in order to assess the Bayesian approach.
Original languageEnglish
Title of host publicationMaximum Entropy and Bayesian Methods
EditorsGary J. Erickson, Joshua T. Rychert, C. Ray Smith
PublisherSpringer Netherlands
Pages87-99
Number of pages13
ISBN (Print)978-94-010-6111-7 978-94-011-5028-6
Publication statusPublished - 1998

Publication series

NameFundamental Theories of Physics
PublisherSpringer Netherlands

Fingerprint

Bayesian Approach
Probability Theory
Simple group
Outlier
Eliminate
Configuration

Keywords

  • Artificial Intelligence (incl. Robotics), Auto-classification, auto-clustering, Coding and Information Theory, Discrete Mathematics in Computer Science, group analysis, Mahalonobis distance, Probability Theory and Stochastic Processes, Statistics, general

Cite this

Linden, W. V. D., Dose, V., & Ramaswami, A. (1998). Bayesian Group Analysis. In G. J. Erickson, J. T. Rychert, & C. R. Smith (Eds.), Maximum Entropy and Bayesian Methods (pp. 87-99). (Fundamental Theories of Physics). Springer Netherlands.

Bayesian Group Analysis. / Linden, W. Von Der; Dose, V.; Ramaswami, A.

Maximum Entropy and Bayesian Methods. ed. / Gary J. Erickson; Joshua T. Rychert; C. Ray Smith. Springer Netherlands, 1998. p. 87-99 (Fundamental Theories of Physics).

Research output: Chapter in Book/Report/Conference proceedingOther chapter contributionResearch

Linden, WVD, Dose, V & Ramaswami, A 1998, Bayesian Group Analysis. in GJ Erickson, JT Rychert & CR Smith (eds), Maximum Entropy and Bayesian Methods. Fundamental Theories of Physics, Springer Netherlands, pp. 87-99.
Linden WVD, Dose V, Ramaswami A. Bayesian Group Analysis. In Erickson GJ, Rychert JT, Smith CR, editors, Maximum Entropy and Bayesian Methods. Springer Netherlands. 1998. p. 87-99. (Fundamental Theories of Physics).
Linden, W. Von Der ; Dose, V. ; Ramaswami, A. / Bayesian Group Analysis. Maximum Entropy and Bayesian Methods. editor / Gary J. Erickson ; Joshua T. Rychert ; C. Ray Smith. Springer Netherlands, 1998. pp. 87-99 (Fundamental Theories of Physics).
@inbook{3a6c1f8df0cd40318e49cc101312d355,
title = "Bayesian Group Analysis",
abstract = "In many fields of research the following problem is encountered: a large collection of data is given for which a detailed theory is yet missing. To gain insight into the underlying problem it is important to reveal the interrelationships in the data and to determine the relevant input and response quantities. A central part of this task is to find the natural splitting of the data into groups and to analyze the respective characteristics. Bayesian probability theory is invoked for a consistent treatment of these problems. Due to Ockham’s Razor, which is an integral part of the theory, the simplest group configuration that still fits the data has the highest probability. In addition the Bayesian approach allows to eliminate outliers, which otherwise could lead to erroneous conclusions. Simple textbook and mock data sets are analyzed in order to assess the Bayesian approach.",
keywords = "Artificial Intelligence (incl. Robotics), Auto-classification, auto-clustering, Coding and Information Theory, Discrete Mathematics in Computer Science, group analysis, Mahalonobis distance, Probability Theory and Stochastic Processes, Statistics, general",
author = "Linden, {W. Von Der} and V. Dose and A. Ramaswami",
note = "DOI: 10.1007/978-94-011-5028-67",
year = "1998",
language = "English",
isbn = "978-94-010-6111-7 978-94-011-5028-6",
series = "Fundamental Theories of Physics",
publisher = "Springer Netherlands",
pages = "87--99",
editor = "Erickson, {Gary J.} and Rychert, {Joshua T.} and Smith, {C. Ray}",
booktitle = "Maximum Entropy and Bayesian Methods",
address = "Netherlands",

}

TY - CHAP

T1 - Bayesian Group Analysis

AU - Linden, W. Von Der

AU - Dose, V.

AU - Ramaswami, A.

N1 - DOI: 10.1007/978-94-011-5028-67

PY - 1998

Y1 - 1998

N2 - In many fields of research the following problem is encountered: a large collection of data is given for which a detailed theory is yet missing. To gain insight into the underlying problem it is important to reveal the interrelationships in the data and to determine the relevant input and response quantities. A central part of this task is to find the natural splitting of the data into groups and to analyze the respective characteristics. Bayesian probability theory is invoked for a consistent treatment of these problems. Due to Ockham’s Razor, which is an integral part of the theory, the simplest group configuration that still fits the data has the highest probability. In addition the Bayesian approach allows to eliminate outliers, which otherwise could lead to erroneous conclusions. Simple textbook and mock data sets are analyzed in order to assess the Bayesian approach.

AB - In many fields of research the following problem is encountered: a large collection of data is given for which a detailed theory is yet missing. To gain insight into the underlying problem it is important to reveal the interrelationships in the data and to determine the relevant input and response quantities. A central part of this task is to find the natural splitting of the data into groups and to analyze the respective characteristics. Bayesian probability theory is invoked for a consistent treatment of these problems. Due to Ockham’s Razor, which is an integral part of the theory, the simplest group configuration that still fits the data has the highest probability. In addition the Bayesian approach allows to eliminate outliers, which otherwise could lead to erroneous conclusions. Simple textbook and mock data sets are analyzed in order to assess the Bayesian approach.

KW - Artificial Intelligence (incl. Robotics), Auto-classification, auto-clustering, Coding and Information Theory, Discrete Mathematics in Computer Science, group analysis, Mahalonobis distance, Probability Theory and Stochastic Processes, Statistics, general

M3 - Other chapter contribution

SN - 978-94-010-6111-7 978-94-011-5028-6

T3 - Fundamental Theories of Physics

SP - 87

EP - 99

BT - Maximum Entropy and Bayesian Methods

A2 - Erickson, Gary J.

A2 - Rychert, Joshua T.

A2 - Smith, C. Ray

PB - Springer Netherlands

ER -