A regression model on distributional data in a context of functional data analysis through an appropriate LDQ transformation

R. Verde, A. Balzanella, G. Borrata

The results of the model in terms of the original distributional variable, can be obtained, minus a constant, by applying the inverse transformation of the LDQ. To this end, a minimum value estimation model of the original quantile functions is proposed to estimate the constant lost in the reconstruction.
Finally, we show the performance of the regression model on real and simulated data.

Keywords: Distributional data analysis, regression model, LDQ transformation

FENStatS-SEIO: Statistics and Data Science
June 11, 2025  10:30 AM
Auditorio 1. Ricard Vinyes

P. Lacroix, B. Michel, F. Picard, V. Rivoirard

I. Pereira, M. Monteiro

P. Delicado, C. Pachón García

I. Willems, J. Beyhum, I. Van Keilegom