An adaptive method for bandwidth selection in circular kernel
density estimation

J 2023

An adaptive method for bandwidth selection in circular kernel density estimation

ZÁMEČNÍK, Stanislav, Ivanka HOROVÁ, Stanislav KATINA a Kamila HASILOVÁ

Základní údaje

Originální název

An adaptive method for bandwidth selection in circular kernel density estimation

Autoři

ZÁMEČNÍK, Stanislav (703 Slovensko, domácí), Ivanka HOROVÁ (203 Česká republika, domácí), Stanislav KATINA (703 Slovensko, domácí) a Kamila HASILOVÁ (203 Česká republika)

Vydání

Computational Statistics, Springer, 2023, 0943-4062

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10103 Statistics and probability

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 1.300 v roce 2022

Kód RIV

RIV/00216224:14310/23:00134765

Organizační jednotka

Přírodovědecká fakulta

DOI

http://dx.doi.org/10.1007/s00180-023-01401-0

UT WoS

001072240200001

Klíčová slova anglicky

Circular density; Bandwidth selector; Adaptive kernel estimator; Von Mises density; Smoothed cross validation

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 24. 5. 2024 13:56, Mgr. Marie Šípková, DiS.

Anotace

V originále

Kernel density estimations of circular data are an effective type of nonparametric estimation. The performance of these estimations depends significantly on a smoothing parameter referred to as bandwidth. Selecting suitable bandwidths for these types of estimation pose fundamental challenges, therefore fixed bandwidth selectors are often the initial choice. The study investigates common bandwidth selection methods and proposes novel methods which adopt the idea from the linear case. The attention is also paid to variable bandwidth selection. Using simulations which incorporate a range of circular distributions that exhibit multimodality, peakedness and skewness, the proposed methods were evaluated and then compared with other bandwidth selectors to determine their potential advantages. Two real datasets, one containing animal movements and the other wind direction data, were applied to illustrate the utility of the proposed methods.

Návaznosti

MUNI/A/1418/2019, interní kód MU

Název: Matematické a statistické modelování 4 (Akronym: MaStaMo4)

Investor: Masarykova univerzita, Matematické a statistické modelování 4, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

Citovat

ZÁMEČNÍK, Stanislav, Ivanka HOROVÁ, Stanislav KATINA a Kamila HASILOVÁ. An adaptive method for bandwidth selection in circular kernel density estimation. Computational Statistics. Springer, 2023, roč. 39, č. 4, s. 1709-1728. ISSN 0943-4062. Dostupné z: https://dx.doi.org/10.1007/s00180-023-01401-0.

@article{2325437,
   author = {Zámečník, Stanislav and Horová, Ivanka and Katina, Stanislav and Hasilová, Kamila},
   article_number = {4},
   doi = {http://dx.doi.org/10.1007/s00180-023-01401-0},
   keywords = {Circular density; Bandwidth selector; Adaptive kernel estimator; Von Mises density; Smoothed cross validation},
   language = {eng},
   issn = {0943-4062},
   journal = {Computational Statistics},
   title = {An adaptive method for bandwidth selection in circular kernel density estimation},
   url = {https://link.springer.com/article/10.1007/s00180-023-01401-0},
   volume = {39},
   year = {2023}
}

TY  - JOUR
ID  - 2325437
AU  - Zámečník, Stanislav - Horová, Ivanka - Katina, Stanislav - Hasilová, Kamila
PY  - 2023
TI  - An adaptive method for bandwidth selection in circular kernel density estimation
JF  - Computational Statistics
VL  - 39
IS  - 4
SP  - 1709-1728
EP  - 1709-1728
PB  - Springer
SN  - 09434062
KW  - Circular density
KW  - Bandwidth selector
KW  - Adaptive kernel estimator
KW  - Von Mises density
KW  - Smoothed cross validation
UR  - https://link.springer.com/article/10.1007/s00180-023-01401-0
N2  - Kernel density estimations of circular data are an effective type of nonparametric estimation. The performance of these estimations depends significantly on a smoothing parameter referred to as bandwidth. Selecting suitable bandwidths for these types of estimation pose fundamental challenges, therefore fixed bandwidth selectors are often the initial choice. The study investigates common bandwidth selection methods and proposes novel methods which adopt the idea from the linear case. The attention is also paid to variable bandwidth selection. Using simulations which incorporate a range of circular distributions that exhibit multimodality, peakedness and skewness, the proposed methods were evaluated and then compared with other bandwidth selectors to determine their potential advantages. Two real datasets, one containing animal movements and the other wind direction data, were applied to illustrate the utility of the proposed methods.
ER  -

ZÁMEČNÍK, Stanislav, Ivanka HOROVÁ, Stanislav KATINA a Kamila HASILOVÁ. An adaptive method for bandwidth selection in circular kernel density estimation. \textit{Computational Statistics}. Springer, 2023, roč.~39, č.~4, s.~1709-1728. ISSN~0943-4062. Dostupné z: https://dx.doi.org/10.1007/s00180-023-01401-0.

Podrobný výpis o publikaci