A robust scale estimator based on the shortest half
- 1 June 1988
- journal article
- Published by Wiley in Statistica Neerlandica
- Vol. 42 (2) , 103-116
- https://doi.org/10.1111/j.1467-9574.1988.tb01224.x
Abstract
A new robust estimator of scale is considered, which is proportional to the length of the shortest half of the sample. The estimator is compared to the interquartile range and the median absolute deviation, that are also based on order statistics. All three estimators have the same influence function, but their breakdown points differ. It also turns out that one needs a finite‐sample correction factor which depends on mod(sample size, 4) to achieve approximate unbiasedness at normal distributions.Keywords
This publication has 6 references indexed in Scilit:
- The Length of the ShorthThe Annals of Statistics, 1988
- Robust Regression and Outlier DetectionPublished by Wiley ,1987
- Least Median of Squares RegressionJournal of the American Statistical Association, 1984
- Least Median of Squares RegressionJournal of the American Statistical Association, 1984
- Expected values of normal order statisticsBiometrika, 1961
- Expected Values of Normal Order StatisticsBiometrika, 1961