Given a sample of Pareto-tailed samples (positive tail index),
compute the trimmed Hill estimator. If \(k0=k\), the estimator
reduces to Hill's estimator for the shape index
Usage
shape.trimhill(xdat, k, k0, sorted = FALSE)
Arguments
- xdat
[numeric] vector of positive observations
- k
[integer] number of order statistics for the threshold
- k0
[integer] number of largest order statistics, strictly less than k
- sorted
[logical] if TRUE
, data are assumed to be sorted in decreasing order
Value
a scalar with the shape parameter estimate
References
Bhattacharya, S., Kallitsis, M. and S. Stoev, (2019) Data-adaptive trimming of the Hill estimator and detection of outliers in the extremes of heavy-tailed data. Electronic Journal of Statistics 13, 1872–1925