Isotonic Regression Estimators For Simultaneous Estimation of Order Restricted Location/Scale Parameters of a Bivariate Distribution: A Unified Study

Publication date 2 January 2023

Statistical decision theory (62C99) Point estimation (62F10) Parametric inference under constraints (62F30)

Abstract: The problem of simultaneous estimation of location/scale parameters

h e t a_{1}

and

h e t a_{2}

of a general bivariate location/scale model, when the ordering between the parameters is known apriori (say,

h e t a_{1} l e q h e t a_{2}

), has been considered. We consider isotonic regression estimators based on the best location/scale equivariant estimators (BLEEs/BSEEs) of

h e t a_{1}

and

h e t a_{2}

with general weight functions. Let

m a t h c a l D

denote the corresponding class of isotonic regression estimators of

(h e t a_{1}, h e t a_{2})

. Under the sum of the weighted squared error loss function, we characterize admissible estimators within the class

m a t h c a l D

, and identify estimators that dominate the BLEE/BSEE of (

h e t a_{1}

,

h e t a_{2}

). Our study unifies several studies reported in the literature for specific probability distributions having independent marginals. We also report a generalized version of the Katz (1963) result on the inadmissibility of certain estimators under a loss function that is weighted sum of general loss functions for component problems. A simulation study is also carried out to validate the findings of the paper.

This page was built for publication: Isotonic Regression Estimators For Simultaneous Estimation of Order Restricted Location/Scale Parameters of a Bivariate Distribution: A Unified Study

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6422337)