Functional data analysis is a sub-field of statistics concerned
with data generated by stochastic processes 𝑋 (𝑡) ∈ 𝐿2 (𝐼), 𝑡 ∈ 𝐼, where 𝐼 represents an (in-)finite interval. Unlike traditional multivariate observations, functional data are observed at individual time points throughout the interval 𝐼. This unique data structure necessitates novel approaches for analysis. The robustness of these methods is crucial to ensure reliable
results, particularly in the presence of anomalies arising from measurement errors or high data variability. This study explores various frameworks designed to address these challenges, demonstrating their efficacy through simulations and real-world data analysis.
en
dc.description.sponsorship
FWF - Österr. Wissenschaftsfonds
-
dc.language.iso
en
-
dc.subject
functional data
en
dc.subject
functional depth
en
dc.subject
principal component analysis
en
dc.subject
Mahalanobis distance
en
dc.title
Functional Outlier Detection
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.relation.grantno
I 5799-N
-
dc.type.category
Conference Presentation
-
tuw.publication.invited
invited
-
tuw.project.title
Generalisierte relative Daten und Robustheit in Bayes Räumen
