Scroll to navigation

GBMODES(1) User Commands GBMODES(1)


gbmodes - Analyze multimodality in univariate data


gbmodes [options]


Multimodality analysis via kernel density estimation. Compute the maximal kernel bandwidth h_c(M) for which #(modes in the estimated density)>M.The significance of h_c is computed via smoothed bootstrap. Read data from std. input. Print the couple h_c p(h_c) and the modal values (set with -O).


number of equispaced points where the density is computed (default 100)
number of modes (default 1)
search range for modes; comma separated couple 'data_min,data_max'
scale the search range to [min*s+(1-s)*Max,Max*s+(1-s)*min] (default 1)
relative tolerance on h_c value (default 1e-6)
significance level (for Hall-York correction) (default .05)
number of bootstrap trials used for significance computation (default 1000)
RNG seed for bootstrap trials (default 0)
choose the kernel to use: 0 Gaussian or 1 Laplacian (default 0)
verbose mode (more verbose if provided 2 times)
output type (default 0)
h_c p(h_c) [modes locations]
h_c [modes locations and heights]
specify the input fields separators (default " \t")
this help


Written by Giulio Bottazzi


Report bugs to <>

Package home page <>


Copyright © 2001-2018 Giulio Bottazzi This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License (version 2) as published by the Free Software Foundation;

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

March 2018 gbmodes 5.7.1