Evaluating the stability of the classification of community
data

J 2011

Evaluating the stability of the classification of community data

TICHÝ, Lubomír; Milan CHYTRÝ a Petr ŠMARDA

Základní údaje

Originální název

Evaluating the stability of the classification of community data

Název česky

Hodnocení stability klasifikace dat o společenstvech

Autoři

TICHÝ, Lubomír; Milan CHYTRÝ a Petr ŠMARDA

Vydání

Ecography, 2011, 0906-7590

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10600 1.6 Biological sciences

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

Fulltext on Wiley Online Library

Impakt faktor

Impact factor: 4.188

Kód RIV

RIV/00216224:14310/11:00050300

Organizační jednotka

Přírodovědecká fakulta

DOI

https://doi.org/10.1111/j.1600-0587.2010.06599.x

UT WoS

000296972200011

Klíčová slova anglicky

Clustering methods; Vegetation classification strategies; Validation; Bootstrap; Algorithm; Fidelity

Štítky

AKR, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 3. 1. 2012 11:01, prof. RNDr. Milan Chytrý, Ph.D.

Anotace

V originále

We propose a method for a posteriori evaluation of classification stability which compares the classification of sites in the original data set (a matrix of species by sites) with classifications of subsets of its sites created by without-replacement bootstrap resampling. Site assignments to clusters of the original classification and to clusters of the classification of each subset are compared using Goodman-Kruskal's lambda index. Many resampled subsets are classified and the mean of lambda values calculated for the classifications of these subsets is used as an estimation of classification stability. Furthermore, the mean of the lambda values based on different resampled subsets, calculated for each site of the data set separately, can be used as a measure of the influence of particular sites on classification stability. This method was tested on several artificial data sets classified by commonly used clustering methods and on a real data set of forest vegetation plots.

Návaznosti

GA206/09/0329, projekt VaV

Název: Vegetace České republiky: dokončení národního přehledu rostlinných společenstev

Investor: Grantová agentura ČR, Vegetace České republiky: dokončení národního přehledu rostlinných společenstev

MSM0021622416, záměr

Název: Diverzita biotických společenstev a populací: kauzální analýza variability v prostoru a čase

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Diverzita biotických společenstev: kauzální analýza variability v prostoru a čase

Citovat

TICHÝ, Lubomír; Milan CHYTRÝ a Petr ŠMARDA. Evaluating the stability of the classification of community data. Ecography. 2011, roč. 34, č. 5, s. 807-813. ISSN 0906-7590. Dostupné z: https://doi.org/10.1111/j.1600-0587.2010.06599.x.

@article{964377,
   author = {Tichý, Lubomír and Chytrý, Milan and Šmarda, Petr},
   article_number = {5},
   doi = {https://doi.org/10.1111/j.1600-0587.2010.06599.x},
   keywords = {Clustering methods; Vegetation classification strategies; Validation; Bootstrap; Algorithm; Fidelity},
   language = {eng},
   issn = {0906-7590},
   journal = {Ecography},
   title = {Evaluating the stability of the classification of community data},
   url = {http://onlinelibrary.wiley.com/doi/10.1111/j.1600-0587.2010.06599.x/abstract},
   volume = {34},
   year = {2011}
}

TY  - JOUR
ID  - 964377
AU  - Tichý, Lubomír - Chytrý, Milan - Šmarda, Petr
PY  - 2011
TI  - Evaluating the stability of the classification of community data
JF  - Ecography
VL  - 34
IS  - 5
SP  - 807-813
EP  - 807-813
SN  - 09067590
KW  - Clustering methods
KW  - Vegetation classification strategies
KW  - Validation
KW  - Bootstrap
KW  - Algorithm
KW  - Fidelity
UR  - http://onlinelibrary.wiley.com/doi/10.1111/j.1600-0587.2010.06599.x/abstract
N2  - We propose a method for a posteriori evaluation of classification stability which compares the classification of sites in the original data set (a matrix of species by sites) with classifications of subsets of its sites created by without-replacement bootstrap resampling. Site assignments to clusters of the original classification and to clusters of the classification of each subset are compared using Goodman-Kruskal's lambda index. Many resampled subsets are classified and the mean of lambda values calculated for the classifications of these subsets is used as an estimation of classification stability. Furthermore, the mean of the lambda values based on different resampled subsets, calculated for each site of the data set separately, can be used as a measure of the influence of particular sites on classification stability. This method was tested on several artificial data sets classified by commonly used clustering methods and on a real data set of forest vegetation plots.
ER  -

TICHÝ, Lubomír; Milan CHYTRÝ a Petr ŠMARDA. Evaluating the stability of the classification of community data. \textit{Ecography}. 2011, roč.~34, č.~5, s.~807-813. ISSN~0906-7590. Dostupné z: https://doi.org/10.1111/j.1600-0587.2010.06599.x.

Přehled o publikaci