Algorithm 616: fast computation of the Hodges-Lehmann location estimator

From MaRDI portal





HLQEST is a FORTRAN function subprogram for computing the estimator of \textit{J. L. Hodges} and \textit{E. L. Lehmann} [Ann. Math. Stat. 34, 598-611 (1963; Zbl 0203.211)] \[ {\hat \mu}\equiv median\{(X_ i+X_ j)/2,\quad 1\leq i\leq j\leq n\}. \] This robust and highly efficient estimator has not been widely used by statisticians because its apparent time computational complexity is \(O(n^ 2 \log n)\). Improvements in computing \({\hat \mu}\) have previously been made with an iterative algorithm and with some fast theoretical techniques. HLQEST is exact and fast, with expected time complexity of O(n log n).











This page was built for publication: Algorithm 616: fast computation of the Hodges-Lehmann location estimator

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3343393)