The Choice of the Parameter Values in a Multivariate Model of a Second Order Surface with Heteroschedastic Error

Gabriele Cantaluppi, Umberto Magagnoli

Risultato della ricerca: Contributo in libroContributo a convegno

Abstract

The paper describes an experimental procedure to choose the values for a multivariate vector x, under these conditions: average of Y(x) equal to a target value and least variance of Y(x), linked to x by a 2nd order model, with a heteroschedastic error. The procedure consists of two steps. In the first step an experimental design (we consider a three level full factorial design, for simplicity) is performed in the feasible space X of the control factors to estimate the parameters characterizing the response surface of the mean. Then a second experimental design is performed on a target set A, subset of X satisfying the condition on the average of Y(x). This second step determines the choice of x using a classification criterion based on the ordering of the sample mean squared errors. In both steps the model parameters are estimated by an iterative method.
Lingua originaleEnglish
Titolo della pubblicazione ospiteFirst joint meeting of the Société Francophone de Classification and the Classification and Data Analysis Group of the Italian Statistical Society, Book of Short Papers
Pagine369-372
Numero di pagine4
Stato di pubblicazionePubblicato - 2008
EventoFirst joint meeting of the Société Francophone de Classification and the Classification and Data Analysis Group of the Italian Statistical Society, Book of Short Papers - Caserta
Durata: 11 giu 200813 giu 2008

Convegno

ConvegnoFirst joint meeting of the Société Francophone de Classification and the Classification and Data Analysis Group of the Italian Statistical Society, Book of Short Papers
CittàCaserta
Periodo11/6/0813/6/08

Keywords

  • Iterative Generalized Least Squares
  • Optimal Experimental Conditions

Fingerprint

Entra nei temi di ricerca di 'The Choice of the Parameter Values in a Multivariate Model of a Second Order Surface with Heteroschedastic Error'. Insieme formano una fingerprint unica.

Cita questo