N. D. Gagunashvili, M. Schmelling
A kernel based procedure for correcting experimental data for distortions due to the finite resolution and limited detector acceptance is presented. The unfolding problem is known to be an ill-posed problem that can not be solved without some a priori information about solution such as, for example, smoothness or positivity. In the approach presented here the true distribution is estimated by a weighted sum of kernels, with the width of the kernels acting as a regularization parameter responsible for the smoothness of the result. Cross-validation is used to determine an optimal value for this parameter. A numerical example with a simulation study of systematical and statistical errors is presented to illustrate the procedure.
View original:
http://arxiv.org/abs/1209.3766
No comments:
Post a Comment