A Complete Class Theorem for Strict Monotone Likelihood Ratio With Applications
Brown, L. D. ; Cohen, Arthur ; Strawderman, W. E.
Ann. Statist., Tome 4 (1976) no. 1, p. 712-722 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Suppose a random variable has a density belonging to a one parameter family which has strict monotone likelihood ratio. For inference regarding the parameter (or a monotone function of the parameter) consider the loss function to be bowl shaped for each fixed parameter and also to have each action be a "point of increase" or a "point of decrease" for some value of the parameter. Under these conditions, given any nonmonotone decision procedure, a unique monotone procedure is constructed which is strictly better than the given procedure for all the above loss functions. This result has application to the following areas: combining data problems, sufficiency, a multivariate one-sided testing problem.
Publié le : 1976-07-14
Classification:  Monotone likelihood ratio,  complete class,  monotone procedure,  sufficiency,  testing,  estimation,  confidence sets,  combined tests,  combined estimators,  62F10,  62F05,  62C07,  62B05,  62H15,  62C15 
@article{1176343543,
     author = {Brown, L. D. and Cohen, Arthur and Strawderman, W. E.},
     title = {A Complete Class Theorem for Strict Monotone Likelihood Ratio With Applications},
     journal = {Ann. Statist.},
     volume = {4},
     number = {1},
     year = {1976},
     pages = { 712-722},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176343543}
}

Brown, L. D.; Cohen, Arthur; Strawderman, W. E. A Complete Class Theorem for Strict Monotone Likelihood Ratio With Applications. Ann. Statist., Tome 4 (1976) no. 1, pp.  712-722. http://gdmltest.u-ga.fr/item/1176343543/