Necessary conditions for optimal truncated sequential tests. Simple hypothesis.

Enrique Castillo Ron; J. García

Stochastica (1983)

  • Volume: 7, Issue: 1, page 63-81
  • ISSN: 0210-7821

Abstract

top
The paper presents a new methodology to obtain partially sequential truncated tests which are optimum in the sense of minimizing the maximum expected sample number. This methodology is based on a variational approach and uses the Lagrange multipliers technique in order to obtain necessary conditions for a test to be optimum. By means of these conditions the optimum test can be obtained. Finally, the method is applied to the problem of testing the mean of an exponential distribution. As a particular test Wald's tests can be obtained in practice by using a sufficiently large truncation sample size.

How to cite

top

Castillo Ron, Enrique, and García, J.. "Condiciones necesarias para pruebas secuenciales truncadas óptimas. Hipótesis simples.." Stochastica 7.1 (1983): 63-81. <http://eudml.org/doc/38879>.

@article{CastilloRon1983,
author = {Castillo Ron, Enrique, García, J.},
journal = {Stochastica},
keywords = {Prueba secuencial truncada; Muestras; Distribución exponencial; Funciones de distribución; truncated tests; variational approach; Lagrange multipliers; optimum test; mean of an exponential distribution; Wald's tests},
language = {spa},
number = {1},
pages = {63-81},
title = {Condiciones necesarias para pruebas secuenciales truncadas óptimas. Hipótesis simples.},
url = {http://eudml.org/doc/38879},
volume = {7},
year = {1983},
}

TY - JOUR
AU - Castillo Ron, Enrique
AU - García, J.
TI - Condiciones necesarias para pruebas secuenciales truncadas óptimas. Hipótesis simples.
JO - Stochastica
PY - 1983
VL - 7
IS - 1
SP - 63
EP - 81
LA - spa
KW - Prueba secuencial truncada; Muestras; Distribución exponencial; Funciones de distribución; truncated tests; variational approach; Lagrange multipliers; optimum test; mean of an exponential distribution; Wald's tests
UR - http://eudml.org/doc/38879
ER -

NotesEmbed ?

top

You must be logged in to post comments.