Robust smoothed canonical correlation analysis for functional data

BOENTE GRACIELA; KUDRASZOW NADIA L.

STATISTICA SINICA

STATISTICA SINICA

Lugar: Taiwan; Año: 2022 vol. 32 p. 1 - 25

1017-0405

This paper provides robust estimators for the first canonical correlation anddirections of random elements on Hilbert separable spaces by using robust association and scale measures combined with basis expansion and/or penalizations as a regularization tool. Under regularity conditions, the resulting estimators are consistent. The finitesample performance of our proposal is illustrated through a simulation study that showsthat, as expected, the robust method outperforms the existing classical procedure whenthe data are contaminated. A real data example is also presented.