Advanced Distribution Theory for SiZer

SiZer is a powerful method for exploratory data analysis. In this article approximations to the distributions underlying the simultaneous statistical inference are investigated, and large improvements are made in the approximation using extreme value theory. This results in improved size, and also i...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of the American Statistical Association 2006-06, Vol.101 (474), p.484-499
Hauptverfasser:	Hannig, J, Marron, J. S
Format:	Artikel
Sprache:	eng
Schlagworte:	Applications Approximation Curvature Data analysis Data smoothing Density estimation Distribution theory Exact sciences and technology Extreme value theory General topics Inference Kernel smoothing Mathematical models Mathematics Multiple testing adjustment Null hypothesis Pixels Probability and statistics Probability theory and stochastic processes Quantitative analysis Random variables Sample size Sciences and techniques of general use Simulation Simulation techniques SiZer Statistical analysis Statistical methods Statistics Theory and Methods
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	SiZer is a powerful method for exploratory data analysis. In this article approximations to the distributions underlying the simultaneous statistical inference are investigated, and large improvements are made in the approximation using extreme value theory. This results in improved size, and also in an improved global inference version of SiZer. The main points are illustrated with real data and simulated examples.
ISSN:	0162-1459 1537-274X
DOI:	10.1198/016214505000001294