TY - JOUR
T1 - Higher order factor structure of a self-control test
T2 - Evidence from confirmatory factor analysis with polychoric correlations
AU - Flora, David B.
AU - Finkel, Eli J.
AU - Foshee, Vangie A.
PY - 2003/1/1
Y1 - 2003/1/1
N2 - The self-control test developed by Grasmick, Tittle, Bursik, and Arneklev was designed to measure each of six components of self-control, namely, impulsivity, a preference for simple rather than complex tasks, risk seeking, a preference for physical rather than cerebral activities, a self-centered orientation, and a volatile temper. This conceptualization clearly suggests that self-control may be defined as a higher order construct that leads to each of these components, which in turn may be represented as first-order factors or constructs. However, due to various limitations, previous analyses of the test failed to establish this factor structure. By employing proper methods for the factor analysis of Likert-type items and explicitly testing a higher order structure, the authors show that the self-control test may provide more valid measurement of the psychological constructs it was intended to measure than previous research suggests.
AB - The self-control test developed by Grasmick, Tittle, Bursik, and Arneklev was designed to measure each of six components of self-control, namely, impulsivity, a preference for simple rather than complex tasks, risk seeking, a preference for physical rather than cerebral activities, a self-centered orientation, and a volatile temper. This conceptualization clearly suggests that self-control may be defined as a higher order construct that leads to each of these components, which in turn may be represented as first-order factors or constructs. However, due to various limitations, previous analyses of the test failed to establish this factor structure. By employing proper methods for the factor analysis of Likert-type items and explicitly testing a higher order structure, the authors show that the self-control test may provide more valid measurement of the psychological constructs it was intended to measure than previous research suggests.
KW - Factor analysis
KW - Higher order models
KW - Self-control
KW - Weighted least squares
UR - http://www.scopus.com/inward/record.url?scp=0037273472&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0037273472&partnerID=8YFLogxK
U2 - 10.1177/0013164402239320
DO - 10.1177/0013164402239320
M3 - Article
AN - SCOPUS:0037273472
VL - 63
SP - 112
EP - 127
JO - Education and Psychological Measurement
JF - Education and Psychological Measurement
SN - 0013-1644
IS - 1
ER -