Several new kernel estimators for population abundance

Abstract

The parameter f(0) is crucial in line transect sampling which is regularly used for computing population abundance in wildlife. The usual kernel estimator of f(0) has a high negative bias. Our study proposes several new estimators which are shown to be more efficient than the usual kernel estimator. A simulation technique is adopted to compare the performance of the proposed estimators with the classical kernel estimator. An application of the new estimators on real data set is discussed.