Previous work



Reduced Major Axis Regression

Download executable JAR file (double click after saving to run it)


RMA for JAVA v. 1.21: Reduced Major Axis Regression
© C++ code: Andrew J. Bohonak, San Diego State University
© Java code: Kim van der Linde, Florida State University
Usage of the program is free, but citation is appreciated.
The underlying JAVA classes and source code are licensed under the Apache License, Version 2.0 .

For more information, see http://www.bio.sdsu.edu/pub/andy/RMA.html

The program needs the Java Runtime Environment available from the java site of SUN, at least version 1.4.2.

There are two options to run this program:

  • either download it as jar file which enables you to load and save files. To execute it:
    • run it from the command prompt, using: <path to jar file>/java -jar rma.v1.21.jar
    • or let for example windows handle it from the download dialog box (works wonders under my Mozilla and win XP system).
  • or use the java webstart option. As java webstart programs run in a so-called sandbox, it can not access files on the hard disk so it works with an input dialog and can not save the results.
Two remarks: (1) the executables jre, javaw and java are exchangeable. (2) '/' and '\' depend on the platform you use, so change accordingly.

Cite this as:
Andrew J. Bohonak & Kim van der Linde (2004) RMA: Software for Reduced Major Axis regression, Java version. Website: http://www.kimvdlinde.com/professional/rma.html.

See here for a list of articles that cited this software.

Version History:

  • Version 1.21 (4 June 2008):
    • Bug fix, gave incorrect answers when encountering a missing value.
  • Version 1.20 (17 March 2008):
    • Eliminated max limit in cases.
    • Complied in jdk 1.4.2
  • Version 1.19 (14 October 2004):
    • added log 10 -transformation option. This is frequently used for allometric regressions. The output file contains an inserted .log in the filename
  • Version 1.18 (3 September 2004):
    • implemented a different random generator, which is faster and better. The Mersenne Twister is currently one of the most advanced psuedo random generators. See for the accompanying License in the JAR file, or click here. (Source Code is part of RngPack).
    • eliminated error throwing when calculating the standard Confidence intervals for samples smaller than 3 cases..
  • Version 1.17 (4 August 2004):
    • implemented a different algorithm to calculate jack-knifed values for faster execution of the program (Subtraction of the excluded value from the full SS's instead of recalculating while excluding one value).
    • implemented a different random generator based on the "Minimal Standard" multiplicative congruential generator of Park and Miller. [Park, S.K. and K.W. Miller, Communications of the ACM31, 1192-1201 (1988).]Overwritten in 1.18.
    • implemented the heapsort algorithm for faster execution of the program.
  • Versions prior to 1.17 similar as the C++ version of the program. However, not all previous changes are relevant for this JAVA implementation.