PLACE:  319 Snedecor

SPEAKER:
Junyuan Wang
Iowa State University

TITLE:
Small Area Estimation in National Resources Inventory

ABSTRACT:

A practical application of small area estimation in the National Resources
Inventory, a large land survey of the nation's non-federal land area, is
described.  Several estimation issues raised by this application are discussed
as motivation for the theoretical investigation of small area estimation.

An approximation for the mean square error (MSE) of the empirical best linear
predictor (EBLUP) when the individual small area sampling variances are
directly estimated is described.  An estimator for the MSE is developed for the
situation with estimated small area variances.  The suggested variance
estimator has smaller over estimation of the MSE than related estimators in the
literature when the between-area variance component is small.

Small area estimation under a restriction is discussed and a criterion that
unifies the derivation of several restricted estimators is proposed.  The
estimator that is the unique ?est?linear unbiased estimator for the criterion
is derived and an approximation for the MSE of the restricted estimator is
presented.  The bias of the EBLUP is assessed for the model in which the
sampling errors are not normally distributed.  The robustness of the MSE
estimator is examined under non-normal error distributions.  Simulations are
used to study the properties of the theoretical approximations.  The
simulations demonstrate that imposing a restriction can reduce the bias when
the errors are not symmetrically distributed.
 
 

COFFEE: 3:45 p.m., 104 Snedecor