Estimation of the distribution function using auxiliary information

                    Juan Jose' Goyeneche
                      Iowa State University 


The estimation of the finite population distribution function of
a variable y is studied for the situation in which auxiliary
information is available for each element in the population.  We
introduce an estimator of the finite population distribution
function, called the local-residuals estimator, based on the
distribution of the residuals from the regression of the variable
of interest, y, on the vector of auxiliary variables, x.  The
asymptotic properties of the local-residuals estimator are
studied under different superpopulation models and conditions for
consistency and asymptotic normality of the estimator are
established. Model consistent estimators of the variance of the
local-residuals estimator are proposed. The local-residuals
estimator performs well in a Monte Carlo study.