Steekproeven uit de halve cauchy verdeling

J.L. Mijnheer

Research output: Contribution to journalArticleAcademic

1 Citation (Scopus)
51 Downloads (Pure)

Abstract

Let x1…, xn be a sample from a distribution with infinite expectation, then for n→∞ the sample average Xn tends to +∞ with probability 1 (see [4]). Sometimes Xn contains high jumps due to large observations. In this paper we consider samples from the "absolute Cauchy" distribution. In practice, on may consider the logarithm of the observations as a sample from a normal distribution. So we found in our simulation. After rejecting the log-normality assumption, one will be tempted to regard the extreme observations as outliers. It is shown that the discarding of the outlying observations gives an underestimation of the expectation, variance and 99 percentile of the actual distribution.
Original languageDutch
Pages (from-to)97-101
JournalStatistica Neerlandica
Volume22
Issue number2
DOIs
Publication statusPublished - 1968

Keywords

  • IR-70658

Cite this

Mijnheer, J.L. / Steekproeven uit de halve cauchy verdeling. In: Statistica Neerlandica. 1968 ; Vol. 22, No. 2. pp. 97-101.
@article{b72f67f243064d3bbfcc2b6c41838db1,
title = "Steekproeven uit de halve cauchy verdeling",
abstract = "Let x1…, xn be a sample from a distribution with infinite expectation, then for n→∞ the sample average Xn tends to +∞ with probability 1 (see [4]). Sometimes Xn contains high jumps due to large observations. In this paper we consider samples from the {"}absolute Cauchy{"} distribution. In practice, on may consider the logarithm of the observations as a sample from a normal distribution. So we found in our simulation. After rejecting the log-normality assumption, one will be tempted to regard the extreme observations as outliers. It is shown that the discarding of the outlying observations gives an underestimation of the expectation, variance and 99 percentile of the actual distribution.",
keywords = "IR-70658",
author = "J.L. Mijnheer",
year = "1968",
doi = "10.1111/j.1467-9574.1968.tb01359.x",
language = "Dutch",
volume = "22",
pages = "97--101",
journal = "Statistica Neerlandica",
issn = "0039-0402",
publisher = "Wiley-Blackwell",
number = "2",

}

Steekproeven uit de halve cauchy verdeling. / Mijnheer, J.L.

In: Statistica Neerlandica, Vol. 22, No. 2, 1968, p. 97-101.

Research output: Contribution to journalArticleAcademic

TY - JOUR

T1 - Steekproeven uit de halve cauchy verdeling

AU - Mijnheer, J.L.

PY - 1968

Y1 - 1968

N2 - Let x1…, xn be a sample from a distribution with infinite expectation, then for n→∞ the sample average Xn tends to +∞ with probability 1 (see [4]). Sometimes Xn contains high jumps due to large observations. In this paper we consider samples from the "absolute Cauchy" distribution. In practice, on may consider the logarithm of the observations as a sample from a normal distribution. So we found in our simulation. After rejecting the log-normality assumption, one will be tempted to regard the extreme observations as outliers. It is shown that the discarding of the outlying observations gives an underestimation of the expectation, variance and 99 percentile of the actual distribution.

AB - Let x1…, xn be a sample from a distribution with infinite expectation, then for n→∞ the sample average Xn tends to +∞ with probability 1 (see [4]). Sometimes Xn contains high jumps due to large observations. In this paper we consider samples from the "absolute Cauchy" distribution. In practice, on may consider the logarithm of the observations as a sample from a normal distribution. So we found in our simulation. After rejecting the log-normality assumption, one will be tempted to regard the extreme observations as outliers. It is shown that the discarding of the outlying observations gives an underestimation of the expectation, variance and 99 percentile of the actual distribution.

KW - IR-70658

U2 - 10.1111/j.1467-9574.1968.tb01359.x

DO - 10.1111/j.1467-9574.1968.tb01359.x

M3 - Article

VL - 22

SP - 97

EP - 101

JO - Statistica Neerlandica

JF - Statistica Neerlandica

SN - 0039-0402

IS - 2

ER -