Statistical Modelling 6 (2006), 321–336
Use of auxiliary data in semi-parametric spatial regression with
nonignorable missing responses
Marco Geraci
Department of Biostatistics and Epidemiology
University of South Carolina
800 Sumter Street
Columbia, SC 29208
USA
eMail:
geraci@gwm.sc.edu
Matteo Bottai
Department of Biostatistics and Epidemiology
University of South Carolina
Columbia, SC 29208
USA
Abstract:
We propose a method for reducing the error of the prediction of a
quantity of interest when the outcome has missing values that are
suspected to be nonignorable and the data are correlated in space.
We develop a maximum likelihood approach for the parameter estimation
of semi-parametric regressions in a mixed model framework. We apply
the proposed method to phytoplankton data collected at fixed stations
in the Chesapeake Bay, for which chlorophyll data coming from remote
sensing are available. A simulation study is also performed. The
availability of a variable correlated to the response allows us to
achieve a substantial reduction of the prediction error of the
expected value of the smoother, without having to specify a
nonignorable model.
Keywords:
auxiliary data; correlated data; missing data;
Monte Carlo EM algorithm; radial smoother
Downloads:
Data
and R-code in zipped archive
back