Statistical inference for stochastic processes: two sample hypothesis tests

Keywords

Statistical learning
Code:
49/2015
Title:
Statistical inference for stochastic processes: two sample hypothesis tests
Date:
Wednesday 30th September 2015
Author(s):
Ghiglietti, A.; Ieva, F.; Paganoni, A.M.
Download link:
Abstract:
In this paper, we present inferential procedures to compare the means of two samples of functional data. The proposed tests are based on a suitable generalization of Mahalanobis distance to the Hibert space of square integrable function defined on a compact interval. We do not require any specific distributional assumption on the processes generating the data. Test procedures are proposed for both the cases of known and unknown variance-covariance structures, and asymptotic properties of test statistics are deeply studied. A simulation study together with a real case data analysis are also presented.
This report, or a modified version of it, has been also submitted to, or published on
Accepted for publication: "Journal of Statistical Planning and Inference" doi: 10.1016/j.jspi.2016.08.004 (2016)