Differential Interval-Wise Testing for the Inferential Analysis of Tongue Profiles

Motivated by the functional data analysis of a data set of tongue profiles, we describe in this talk the differential interval-wise testing (D-IWT), i.e., a local non-parametric inferential technique for testing the distributional equality of two samples of functional data. The described method can impute significant differences between the two samples to specific intervals of the domain and to specific orders of differentiation. D-IWT based inference provides a highly informative and detailed representation of the regions of the tongue where a significant difference between manners of articulation is located.