Visualizing and Mining Repeated Measure Data: Generalizability Theory

• Activity Number: 43
• Type: Contributed
• Date/Time: Sunday, August 11, 2002 : 4:00 PM to 5:50 PM
• Sponsor: Section on Statistical Graphics*
• Author(s): Christopher Chiu*+ and Ronald Fecso
• Affiliation(s): Law School Admission Council and National Science Foundation
• Keywords: visualization ; data mining & marketing ; longitudinal survey data ; psychometric ; admission testing & repeated test-taker ; matrix statistics

Abstract

Researchers in social, behavioral, economical, psychometrical, financial, and marketing sciences often need a tool for visualizing and mining longitudinal survey data. The paper introduces a visualization technique, SEER, developed for policy makers and researchers to graphically analyze and explore massive amounts of data. The SEER technique: (a) produces panels of graphs for multiple group analysis, where the groups do not have to be mutually exclusive; (b) profiles change patterns observed in longitudinal (repeated measure) data; and (c) clusters data into groups to enable policy makers or researchers to determine the factors associated with the changing patterns. Matrix notations of the method are provided in light of enabling one to implement the method in any computer packages (e.g., EXCEL, SAS, SPSS, MATLAB, Visual C++) that supports scatter plots, sorting, and selecting. The visualization technique draws on the theory of generalizability. Two national data sets are used to illustrate the SEER method: Law School Admission Test (LSAT) and the Survey of Doctorate Recipients (SDR).