GBNLREG(1)

πŸ“¦
version 6.3 Β· 2 versions
  • 6.3 Β· debian bookworm, debian trixie, ubuntu noble, ubuntu questing, ubuntu resolute, ubuntu stonking (latest)
  • 6.0 Β· ubuntu jammy
, in debian bookworm, debian trixie, ubuntu noble, ubuntu questing, ubuntu resolute, ubuntu stonking

✨ GBNLREG β€” bestie edition ✨

okay so this is gbnlreg(1), a User Commands page, and it's literally the moment your data stops being linear and starts being interesting. sit down, hydrate, we're doing nonlinear regression πŸ’–


🌸 NAME 🌸

gbnlreg β€” Non linear regression πŸ¦‹


πŸŽ€ SYNOPSIS πŸŽ€

gbnlreg [options] <function definition>

πŸ’… DESCRIPTION πŸ’…

Non linear least square regression. Read data in columns (X_1 .. X_N). The model is specified by a function f(x1,x2...) using variables names x1,x2,..,xN for the first, second .. N-th column of data. f(x1,x2,...) are assumed i.i.d.

So like β€” your data comes in as columns, X_1 all the way to X_N, and you hand this program a function f(x1,x2...). Those x1,x2,..,xN names are just stand-ins for the 1st, 2nd, … N-th column of your data, no cap. And f(x1,x2,...) is assumed i.i.d. β€” that's the vibe you're signing up for. πŸ‘‘


✨ OPTIONS ✨

  • -O β€” type of output (default 0)
    • 0 β€” parameters
    • 1 β€” parameters and errors
    • 2 β€” <variables> and residuals
    • 3 β€” parameters and variance matrix
    • 4 β€” parameters, errors and s-scores
  • -V β€” variance matrix estimation (default 0)
    • 0 β€” <gradF gradF^t>
    • 1 β€” < J^{-1} >
    • 2 β€” < H^{-1} >
    • 3 β€” < H^{-1} J H^{-1} >
  • -v β€” verbosity level (default 0)
    • 0 β€” just results
    • 1 β€” comment headers
    • 2 β€” summary statistics
    • 3 β€” covariance matrix
    • 4 β€” minimization steps
    • 5 β€” model definition
  • -M β€” estimation method (default 0)
    • 0 β€” ordinary least square (OLS)
    • 1 β€” minimum absolute deviation (MAD)
    • 2 β€” asymmetric MAD
  • -e β€” minimization tolerance (default 1e-5)
  • -i β€” minimization max iterations (default 500)
  • -E β€” restart accuracy (default 1e-5, ignored with option -M 0)
  • -I β€” restart max iterations (default 2000, ignored with option -M 0)
  • -F β€” input fields separators (default " \t")
  • -h β€” this help
heads up bestie: -E and -I are ignored when you're running with option -M 0 β€” they just do nothing there, no drama, but don't be surprised 🫢

🫢 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 Β© 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.


and that's the whole page, bestie 🧚✨ this was gbnlreg version 6.2, from June 2021 β€” go fit something nonlinear and slay πŸ’–πŸ’