TY - JOUR
AU1 - Cudeck, Robert
AU2 - Henly, Susan J.
AB - Complex models for covariance matrices are structures that specify manyparameters, whereas simple models requaire only a few. When a set of models ofdiffering complexity is evaluated by means of some goodness of fit indices,structures with many parameters are more likely to be selected when the numberof observations is large, regardless of other utility considerations. This isknown as the sample size problem in model selection decisions. This articleargues that this influence of sample size is not necessarily undesirable. Therationale behind this point of view is described in terms of the relationshipsamong the population covariance matrix and 2 model-based estimates of it. Theimplications of these relationships for practical use are discussed.
TI - Model Selection in Covariance Structures Analysis and the “Problem” of Sample Size: A Clarification
JF - Psychological Bulletin
DO - 10.1037/0033-2909.109.3.512
DA - 1991-05-01
UR - https://www.deepdyve.com/lp/american-psychological-association/model-selection-in-covariance-structures-analysis-and-the-problem-of-8w34gChPhH
SP - 512
EP - 519
VL - 109
IS - 3
DP - DeepDyve
ER -