Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Update to -chaid- on SSC
From
Joseph Luchman <[email protected]>
To
statalist <[email protected]>
Subject
st: Update to -chaid- on SSC
Date
Mon, 31 Mar 2014 08:17:34 -0700
With many thanks to Kit Baum, an update to the program - chaid - is
available on SSC
The -chaid- command implements Kass' (1980) CHi-square Automated
Interaction Detection (i.e., CHAID) algorithm. CHAID is a decision
tree or machine learning algorithm for exploratory data analysis (or
data mining) that recursively searches through possible splits in the
data to uncover an optimal "decision tree" that explains the dependent
variable. CHAID is also used for clustering or segmentation purposes
as it divides the estimation sample into discrete groups based on the
decision tree results and is a "part prediction - part clustering"
algorithm.
Updates to - chaid - include:
1) updated display showing the hierarchy of the tree structure
(explained in greater detail in the helpfile).
2) Incorporation of fweights - as the algorithm requires categorical
data, using - collapse - on the dataset and using fweights can speed
along the algorithm.
3) "remerging" step described by Kass (1980) implemented as an option.
4) predicted values available as an option.
5) additional returned values (see helpfile).
To update type:
adoupdate chaid, update
- joe
Joseph Nicholas Luchman, Ph.D.
----
Behavioral Statistics Lead | Fors Marsh Group
Email: [email protected]
forsmarshgroup.com
https://www.researchgate.net/profile/Joseph_Luchman/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/