Simultaneous confidence bands in curve prediction applied to load curves

Jean-Marc Azaïs (1) , Sophie Bercu (2) , Jean-Claude Fort (1) , Agnes Lagnoux (1) , Pierre Lé (2)

1 IMT - Institut de Mathématiques de Toulouse UMR5219
2 EDF R&D - EDF R&D

Considering the problem of predicting the whole annual load curve of some Electricité de France (EDF) customers from easily available explanatory variables, we derived simultaneous confidence bands for this prediction. The methodology developed, that can be applied to numerous problems, uses results on the maximum of Gaussian sequences. The paper ends with the applicatiuion to EDF's problem.

Mots clés: Gaussian vectors; maximum of Gaussian sequences; simultaneous confidence bands; thresholding; load curve

Domaines: Statistiques [math.ST]; Théorie [stat.TH]

Jean-Marc Azaïs, Sophie Bercu, Jean-Claude Fort, Agnes Lagnoux, Pierre Lé. Simultaneous confidence bands in curve prediction applied to load curves. Journal of the Royal Statistical Society: Series C Applied Statistics, 2010, 59 (5), pp.889-904. ⟨10.1111/j.1467-9876.2010.00727.x⟩. ⟨hal-00644155⟩