The following module was proposed for inclusion in the Module List:
modid: Statistics::LineFit
DSLIP: bdpOp
description: Weighted/unweighted least-squares line fit
userid: RANDERSON (Richard Anderson)
chapterid: 6 (Data_Type_Utilities)
communities:
comp.lang.perl.modules
similar:
Statistics::OLS
rationale:
The module name is Statistics::LineFit because it uses statistics
(linear regression using the method of least squares) to do line
fitting to a set of (x,y) points.
Statistics::LineFit was inspired by and borrows some ideas from the
venerable Statistics::OLS module. The significant differences
between Statistics::LineFit and Statistics::OLS are:
* Statistics::LineFit is more robust. For certain datasets
Statistics::OLS will return incorrect results (e.g., only two data
points). Statistics::OLS does not deep copy its input arrays, which
can lead to subtle bugs. The Statistics::OLS installation test has
only one test and does not verify that the regression returned
correct results. In contrast, Statistics::LineFit has over 200
installation tests that use various datasets / calling sequences and
it verifies the accuracy of the regression to within 1.0e-10.
* Statistics::LineFit is faster. For a sequence of calls to new(),
setData([EMAIL PROTECTED], [EMAIL PROTECTED]) and regress(), Statistics::LineFit
is faster than
Statistics::OLS by factors of 2.0, 1.6 and 2.4 for array lengths of
5, 100 and 10000, respectively.
* Statistics::LineFit can do weighted or unweighted regression.
Statistics::OLS lacks this option.
* Statistics::LineFit has a better (or at least different)
interface.
Once you call the Statistics::LineFit::setData() method, you can
call the other methods in any order and call methods multiple times
without invoking redundant calculations. Statistics::LineFit lets
you enable or disable data verification or error messages.
* Statistics::LineFit has better code and documentation. The code
in Statistics::LineFit is more readable, more object oriented and
more compliant with Perl coding standards than the code in
Statistics::OLS. The documentation for Statistics::LineFit is more
detailed and complete.
enteredby: RANDERSON (Richard Anderson)
enteredon: Mon Nov 17 23:53:50 2003 GMT
The resulting entry would be:
Statistics::
::LineFit bdpOp Weighted/unweighted least-squares line fit RANDERSON
Thanks for registering,
--
The PAUSE
PS: The following links are only valid for module list maintainers:
Registration form with editing capabilities:
https://pause.perl.org/pause/authenquery?ACTION=add_mod&USERID=68500000_b7a82c7734bd92ed&SUBMIT_pause99_add_mod_preview=1
Immediate (one click) registration:
https://pause.perl.org/pause/authenquery?ACTION=add_mod&USERID=68500000_b7a82c7734bd92ed&SUBMIT_pause99_add_mod_insertit=1
