Assessment and Modeling of Interval-Valued Variables in Generalized Linear Models

نویسندگان

1 دانشگاه آزاد اسلامی

doi
10.22054/jcsm.2021.52523.1020
چکیده

Interval-valued data are observed as ranges instead of single values and contain richer information than single-valued data. Meanwhile, interval-valued data are used for interval-valued characteristics. An interval generalized linear model is proposed for the first time in this research. Then a suitable model is presented to estimate the parameters of the interval generalized linear model. The two models are provided on the basis of the interval arithmetic. The estimation procedure of the parameters of the suitable model is as the estimation procedure of the parameters of the interval generalized linear model. The least-squares (LS) estimation of the suitable model is developed according to a nice distance in the interval space. The LS estimation is resolved analytically through a constrained minimization problem. Then some desirable properties of the estimators are checked. Finally, both the theoretical and the empirical performance of the estimators are investigated.