A bias reducing technique in kernel distribution function estimation (Q2463670)

A bias reducing technique in kernel distribution function estimation is studied by using a convex combination technique of skewed estimators. The proposed estimator reduces the bias from \(O(h^2)\) to \(O(h^4)\), where \(h\) is the bandwidth, while the variance remains at the same order as the kernel distribution function estimator. Numerical results, based on simulation studies, validate the obtained theoretical results.