TY - JOUR
AU1 - Raîche, Gilles
AU2 - Walls, Theodore A.
AU3 - Magis, David
AU4 - Riopel, Martin
AU5 - Blais, Jean-Guy
AB - Most of the strategies that have been proposed to determine the number ofcomponents that account for the most variation in a principal componentsanalysis of a correlation matrix rely on the analysis of the eigenvalues and onnumerical solutions. The Cattell’s scree test is a graphical strategywith a nonnumerical solution to determine the number of components to retain.Like Kaiser’s rule, this test is one of the most frequently usedstrategies for determining the number of components to retain. However, thegraphical nature of the scree test does not definitively establish the number ofcomponents to retain. To circumvent this issue, some numerical solutions areproposed, one in the spirit of Cattell’s work and dealing with thescree part of the eigenvalues plot, and one focusing on the elbow part of thisplot. A simulation study compares the efficiency of these solutions to those ofother previously proposed methods. Extensions to factor analysis are possibleand may be particularly useful with many low-dimensional components.
TI - Non-Graphical Solutions for Cattell’s Scree Test
JF - Methodology: European Journal of Research Methods for the Behavioral and Social Sciences
DO - 10.1027/1614-2241/a000051
DA - 2013-01-31
UR - https://www.deepdyve.com/lp/american-psychological-association/non-graphical-solutions-for-cattell-s-scree-test-7k7Msz0LCy
SP - 23
EP - 29
VL - 9
IS - 1
DP - DeepDyve
ER -