Smooth Estimation of GPD Shape Parameter

Given independent and identically distributed observations X(1), ..., X(n) from a Generalized Pareto distribution with shape parameter gamma in [-1,0], offers several estimates to compute estimates of gamma. The estimates are based on the principle of replacing the order statistics by quantiles of a distribution function based on a log--concave density function. This procedure is justified by the fact that the GPD density is log--concave for gamma in [-1,0].


smoothtail_2.0.5 (2016)

  • Minor updates.

smoothtail_2.0.4 (2015)

  • Properly import globals.

smoothtail_2.0.3 (2014)

  • Updated NAMESPACE.

smoothtail_2.0.2 (2013)

  • Corrected a few typos.

smoothtail_2.0.1 (November 29, 2011)

  • Added Namespace.
  • Updated coordinates of KR.

smoothtail_2.0.0 (August 30, 2010)

  • Updated to reflect recent changes in logcondens 2.0.0.

smoothtail_1.1.4 (October 15, 2009)

  • Updated references.

smoothtail_1.1.3 (June 4, 2009)

  • Updated references.

smoothtail_1.1.2 (Aug 23, 2008)

  • Added Seger's estimator (functions generalizedPick, lambdaGenPick)
  • Updated references.

smoothtail_1.1.1 (Oct 4, 2007)

  • Updated contact informations.

smoothtail_1.1.0 (Aug 17, 2007):

  • Corrected bug in qgpd: max(p) instead of max(x).
  • Updated references.
  • Modified Pickands' estimator according to paper.

smoothtail 1.0 (initial version, Nov 27, 2006)

  • Provide functions to estimate the shape parameter gamma of a Generalized Pareto Distribution based on the fact that its density is log-concave for gamma in [-1,0]. Depends on the package logcondens.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


2.0.5 by Kaspar Rufibach, 5 years ago,

Browse source code at

Authors: Kaspar Ru{f}{i}bach <[email protected]> and Samuel Mueller <[email protected]>

Documentation:   PDF Manual  

GPL (>= 2) license

Imports stats

Depends on logcondens

See at CRAN