Testing convexity of a discrete distribution

Fadoua Balabdaoui (1) , Cécile Durot (2) , François Koladjo (3)

1 Université Paris Dauphine-PSL
2 MODAL'X - Modélisation aléatoire de Paris X
3 MIA - Unité de recherche Mathématiques et Informatique Appliquées

Based on the convex least-squares estimator, we propose two different procedures for testing convexity of a probability mass function supported on N with an unknown finite support. The procedures are shown to be asymptotically calibrated.

Domaines: Théorie [stat.TH]

Fadoua Balabdaoui, Cécile Durot, François Koladjo. Testing convexity of a discrete distribution. 2018. ⟨hal-01693857⟩