ANCHOR Model Implementation
This archive contains Matlab software implementing the ANCHOR model of category rating and absolute identification. The defining article is:
- Petrov, A. & Anderson, J. R. (2005)
-
The Dynamics of Scaling: A Memory-Based Anchor Model of
Category Rating and Absolute Identification.
Psychological Review, 112(2), 383-416.
Abstract Reprint (pdf)
Contents of This Package
The main directory contains the implementation of the ANCHOR model itself
(anchor2.m) as well as a model-tracking version
(anchor2mt.m) for parameter fitting
(Petrov, 2001).
The finalsim directory provides tools for analysing the
stimulus-response sequences generated by the model and comparing them to human data.
The finalsim/hier directory contains the simulation results with a
hierarchy of nested models on a battery of measures of various phenomena.
These results are reported in Table 4 of
Petrov & Anderson (2005)
and are provided here as a research-grade example of how to use the ANCHOR software.
The utils directory and its subdirectory contains a
library of utilities
used by the model code. See the Contents.m files in these
respective directories for a list of the individual files and for examples
of their use. Each .m file contains extensive comments too.
Finally, finalsim/hier directory contains several transcripts
(*.txt files), scripts (.m), and data (.mat)
taken during the development and fitting of the model. Use them as guidance.
ANCHOR was developed and run on Matlab ver 5.3.0.10183 (R11) for Windows.
The implementation ported flawlessly to Matlab 7.2 (R2006b) for Mac OS X.
It depends on my
UTILS Toolbox
distributed free under the terms of the GNU GPL.
The relevant utilities are included in the anchor-v2.2.zip,
although newer versions may be available from my
software page.
The parameter search routines depend on Matlab's stats and
optim Toolboxes, although the stats dependency
probably is minimal.
For a basic installation, simply unzip the archive in a directory of your
choice and add anchor and utils/general to Matlab's path.
To fit parameters, the path should also include utils/paramsearch,
utils/regression, and anchor/finalsim. See
Contents.m
for specific examples.
There are also examples in many of the individual .m files.
Please notify me of any bugs, notes, comments or suggested changes, particularly of any useful changes you may have made to your own copy of the software.
Thank you for your interest in ANCHOR. Happy modeling!
License
This software 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 and the Free Software Foundation for more details.
The software is freely available and freely redistributable, according to the conditions of the GNU General Public License. You may not distribute the software, in whole or in part, in conjunction with proprietary code. That means you only have my permission to distribute a program that uses my code if you also make freely available (under the terms of the GNU GPL) the source code for your whole project. You may not pass on the software to another party in its current form or any altered, embellished or reduced form, without acknowledging the author, citing Petrov & Anderson (2005), and including a copy of the GNU GPL.
