Cat. Diack et C. Thomasagnan, A NONPARAMETRIC TEST OF THE NONCONVEXITY OF REGRESSION, Journal of nonparametric statistics (Print), 9(4), 1998, pp. 335-362
This paper proposes a nonparametric test of the non-convexity of a smo
oth regression function based on least squares or hybrid splines. By a
simple formulation of the convexity hypothesis in the lcass of all po
lynomial cubic splines, we build a test which has an asymptotic size e
qual to the nominal level. It is shown that the test is consistent and
is robust to nonnormality. The behavior of the lest under the local a
lternatives is studied.