JSM 2005 Online Program

Abstract #303115

This is the preliminary program for the 2005 Joint Statistical Meetings in Minneapolis, Minnesota. 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, 2005); 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.

The Program has labeled the meeting rooms with "letters" preceding the name of the room, designating in which facility the room is located:

Minneapolis Convention Center = “MCC” Hilton Minneapolis Hotel = “H” Hyatt Regency Minneapolis = “HY”

Back to main JSM 2005 Program page

Legend:

= Applied Session,

= Theme Session,

= Presenter

Activity Number:	140
Type:	Contributed
Date/Time:	Monday, August 8, 2005 : 10:30 AM to 12:20 PM
Sponsor:	General Methodology
Abstract - #303115
Title:	Suggested Sample-Size-to-Variable Ratios for Discriminant Analysis
Author(s):	Mercedes Schneider*+ and Holmes Finch
Companies:	Ball State University and Ball State University
Address:	Dept of Ed Psyc, Muncie, IN, 47306, United States
Keywords:	discriminant analysis ; structure coefficients ; sample size ; effect size
Abstract:	The discriminant analysis (DA) literature includes a number of suggestions for minimum sample size based upon the number of p continuous variables in the analysis, including sample-size-to-variable (N:p) ratios of 20:1, 10:1, and "between these two." It appears no simulation research has tested any of these N:p guidelines. Furthermore, none of the above suggestions considers the influences of p-variable intercorrelation and effect size upon suggested N:p ratios. This two-group simulation study tests the above three N:p suggestions, where the "in-between" ratio is set as 15:1. The number of p variables per vector ranges from 2 to 5, variable intercorrelation is set at five levels, ranging from minimal (rho = .00 - .20) to high (rho = .81 - .99). Three levels of effect size are examined: 0 (no effect), .5 (medium effect), and .8 (large effect). Finally, two types of structure coefficients (SCs) are compared: within-matrix and total-matrix. The outcome is the proportion of SCs conforming to the criteria that an SC value > .3 indicates an influential p variable. For a given cell, if the proportion of SCs > .3 equals or exceeds .8, the N:p criteria is judged useful.

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 2005 program