NAME

gbacorr - Compute auto/cross-correlation coefficients

SYNOPSIS

gbacorr [options]

DESCRIPTION

Compute auto/cross-correlation coefficients

If the input is a single columns x_1...X_T, the autocorrelation function c(t) is printed, defined as

c_{t} = 1/(T-t-1) \sum_i (x_i-m) (x_{i+t}-m) /s^2

where m is the sample average and s the standard deviation. With a second column y_1...y_T, the cross-correlation

c_{t} = 1/(T-t-1) \sum_i (x_i-mx) (y_{i+t}-my) /(sx sy)

is printed where mx and my are the average values of the two columns and sx and sy their standard deviations. With -M 1 it is mx=my=0, the st.dev. is computed accordingly and in the previous formula T-t-1 is replaced by T-t. The range of t is set by option -t. Options

-M

choose the method (default '0'):

0

auto/cross-correlation with mean removal,

1

auto/cross-correlation without mean removal

-t

set range of t (default '0,10'), accept negative integers

-p

specify the confidence level in (0,1). Interval ac_low,ac_hi has a probability 1-confidence to contain the true value. With this option the output becomes: lag ac ac_low ac_hi.

-F

specify the input fields separators (default " \t")

-h

this help

EXAMPLES

gbacorr -t 0,2 'file(1)'

first three a.c. coeff. of the first data column

gbacorr -p 0.05 'file(1:2)' x-corr of the first two columns together with

their 5% confidence intervals

AUTHOR

Written by Giulio Bottazzi

REPORTING BUGS

Report bugs to <gbutils@googlegroups.com>

Package home page <http://cafim.sssup.it/~giulio/software/gbutils/index.html>

COPYRIGHT

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.