On Fitting Empirical Data under Interval Error

This paper is devoted to the problem of fitting input-output data by a modeling function, linear in its parameters, in the presence of interval-bounded errors in output variable. A method for outlier detection is proposed. Another issue under consideration is the comparative simulation study of the well-known statistical point estimates (least squares, maximum likelihood) and point estimates calculated as the center of interval hull of uncertainty set. The results of the study allow us to draw the conclusion that non-statistical interval based estimation is a competitive alternative to statistical estimation in some cases.