Test of hypotheses expressed by one or many explicative variables and referred to efficiency functions of productive systems or apparatuses has a great operative interest. This paper considers unilateral tests in a model of polynomial regression (of the second degree) with heteroscedastic error components. The work shows an operative decision proposal to accept the null hypothesis, based on a change made to the confidence regions proper in the homoscedastic situation and it gives the main statistical properties of the proposal obtained by numerical simulations based on Monte Carlo Methods. Moreover, it presents a digital procedure of easy implementation.
Magagnoli, U., Chiodini, P. (2007). Unilateral Hypothesis Tests of Efficiency Functions with Heteroscedastic Errors: an Iterative Procedure. In Classification and data analysis 2007 (pp.665-668).
Unilateral Hypothesis Tests of Efficiency Functions with Heteroscedastic Errors: an Iterative Procedure
CHIODINI, PAOLA MADDALENA
2007
Abstract
Test of hypotheses expressed by one or many explicative variables and referred to efficiency functions of productive systems or apparatuses has a great operative interest. This paper considers unilateral tests in a model of polynomial regression (of the second degree) with heteroscedastic error components. The work shows an operative decision proposal to accept the null hypothesis, based on a change made to the confidence regions proper in the homoscedastic situation and it gives the main statistical properties of the proposal obtained by numerical simulations based on Monte Carlo Methods. Moreover, it presents a digital procedure of easy implementation.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
