JSM 2004 Online Program

Abstract #300646

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page

Activity Number:	111
Type:	Contributed
Date/Time:	Monday, August 9, 2004 : 10:30 AM to 12:20 PM
Sponsor:	Section on Statistical Graphics
Abstract - #300646
Title:	Comparison of Data-driven vs. Theory-driven Method: Decision-tree Models as Data Discovery Tools in Social Science Research
Author(s):	Bonita J. Soley*+ and Krista L. Langkamer
Companies:	U.S. Army Research Institute for the Behavioral and Social Sciences and George Mason University
Address:	ATTN: DAPE-ARI-PS, Arlington, VA, 22202-3926,
Keywords:	comparative methods ; data-mining ; decision tree analysis ; multivariate data visualization ; classification tree ; predictive analysis
Abstract:	Social science research often takes a purely replicative, theory-driven approach. However, with a large database, it may be possible to utilize a more exploratory, or data-mining, approach. This research examines the use of one type of data-mining, decision-tree analysis, on an Army survey database. The objective is to determine if informed, data-driven exploratory research can replicate as well as build upon previous research by identifying trends not discovered by using strictly theory-driven methods. SPSS AnswerTree software, which has the capability of creating CHAID, Exhaustive CHAID, C&RT, and QUEST models, is used to test a model of factors related to soldier retention in the military. This model was chosen because there are numerous studies available on the topic for our comparisons. We will build multiple decision-tree models using an identical variable set; compare our models to each other; and compare our models to existing strictly theory-driven models to examine how ours are similar to, or build upon, strictly theory-driven models. Finally, the implications of using a combination data-driven, theoretical approach when analyzing large databases are discussed.

The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program