Regression with fuzzy random data

Different approaches to deal with regression analysis when the data are fuzzy are presented. It summarizes recent results and considers them in a more general context which allows to evaluate the different methods. Starting with necessary notions on regression and on fuzzy sets, three approaches are presented: at first a pure descriptive statistical approach, secondly statistical regression when the output is modeled by a fuzzy random variable (FRV) and finally regression between two FRVs.