Goodness-of-fit tests in reverberation chambers: is sample independence necessary?

F. Monsef; R. Serra; A. Cozza

doi:10.1109/TEMC.2015.2451211

Goodness-of-fit tests in reverberation chambers: is sample independence necessary?

F. Monsef, R. Serra, A. Cozza

Electrical Energy Systems

Research output: Contribution to journal › Article › Academic › peer-review

8 Citations (Scopus)

Abstract

Goodness-of-fit (GoF) tests are interesting tools to test the overmodedness of the field inside a reverberation chamber (RC). In the definition of GoF tests independent and identically distributed samples are required. In this study, we focus on the effect of partial data correlation on GoF tests. We analyze the sensitivity of the most common GoF tests used in electromagnetic compatibility. The results presented herein are based on numerical and experimental data. We show that most of GoF tests are insensitive to correlations up to rather high values depending on the type of GoF test chosen. Implications for practical applications are discussed.

Original language	English
Article number	7172502
Pages (from-to)	1748-1751
Number of pages	4
Journal	IEEE Transactions on Electromagnetic Compatibility
Volume	57
Issue number	6
DOIs	https://doi.org/10.1109/TEMC.2015.2451211
Publication status	Published - 1 Dec 2015

Keywords

Autocorrelation coefficient
data independence
random fields
reverberation chambers (RC)
statistical electromagnetism

Access to Document

10.1109/TEMC.2015.2451211

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Goodness-of-fit tests in reverberation chambers: is sample independence necessary?'. Together they form a unique fingerprint.

Cite this

@article{a12305d7b979464fa0d58e5151755225,

title = "Goodness-of-fit tests in reverberation chambers: is sample independence necessary?",

abstract = "Goodness-of-fit (GoF) tests are interesting tools to test the overmodedness of the field inside a reverberation chamber (RC). In the definition of GoF tests independent and identically distributed samples are required. In this study, we focus on the effect of partial data correlation on GoF tests. We analyze the sensitivity of the most common GoF tests used in electromagnetic compatibility. The results presented herein are based on numerical and experimental data. We show that most of GoF tests are insensitive to correlations up to rather high values depending on the type of GoF test chosen. Implications for practical applications are discussed.",

keywords = "Autocorrelation coefficient, data independence, random fields, reverberation chambers (RC), statistical electromagnetism",

author = "F. Monsef and R. Serra and A. Cozza",

year = "2015",

month = dec,

day = "1",

doi = "10.1109/TEMC.2015.2451211",

language = "English",

volume = "57",

pages = "1748--1751",

journal = "IEEE Transactions on Electromagnetic Compatibility",

issn = "0018-9375",

publisher = "Institute of Electrical and Electronics Engineers",

number = "6",

}

TY - JOUR

T1 - Goodness-of-fit tests in reverberation chambers

T2 - is sample independence necessary?

AU - Monsef, F.

AU - Serra, R.

AU - Cozza, A.

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Goodness-of-fit (GoF) tests are interesting tools to test the overmodedness of the field inside a reverberation chamber (RC). In the definition of GoF tests independent and identically distributed samples are required. In this study, we focus on the effect of partial data correlation on GoF tests. We analyze the sensitivity of the most common GoF tests used in electromagnetic compatibility. The results presented herein are based on numerical and experimental data. We show that most of GoF tests are insensitive to correlations up to rather high values depending on the type of GoF test chosen. Implications for practical applications are discussed.

AB - Goodness-of-fit (GoF) tests are interesting tools to test the overmodedness of the field inside a reverberation chamber (RC). In the definition of GoF tests independent and identically distributed samples are required. In this study, we focus on the effect of partial data correlation on GoF tests. We analyze the sensitivity of the most common GoF tests used in electromagnetic compatibility. The results presented herein are based on numerical and experimental data. We show that most of GoF tests are insensitive to correlations up to rather high values depending on the type of GoF test chosen. Implications for practical applications are discussed.

KW - Autocorrelation coefficient

KW - data independence

KW - random fields

KW - reverberation chambers (RC)

KW - statistical electromagnetism

UR - http://www.scopus.com/inward/record.url?scp=84938504934&partnerID=8YFLogxK

U2 - 10.1109/TEMC.2015.2451211

DO - 10.1109/TEMC.2015.2451211

M3 - Article

AN - SCOPUS:84938504934

VL - 57

SP - 1748

EP - 1751

JO - IEEE Transactions on Electromagnetic Compatibility

JF - IEEE Transactions on Electromagnetic Compatibility

SN - 0018-9375

IS - 6

M1 - 7172502

ER -