naa a22 4500 510776612 CHVBK 20180411083232.0 cr unu---uuuuu 180411e20130301xx s 000 0 eng 10.3758/s13428-012-0206-0 doi (NATIONALLICENCE)springer-10.3758/s13428-012-0206-0 Jung Sunho School of Management, Kyung Hee University, Seoul, South Korea aut Structural equation modeling with small sample sizes using two-stage ridge least-squares estimation [Elektronische Daten] [Sunho Jung] In covariance structure analysis, two-stage least-squares (2SLS) estimation has been recommended for use over maximum likelihood estimation when model misspecification is suspected. However, 2SLS often fails to provide stable and accurate solutions, particularly for structural equation models with small samples. To address this issue, a regularized extension of 2SLS is proposed that integrates a ridge type of regularization into 2SLS, thereby enabling the method to effectively handle the small-sample-size problem. Results are then reported of a Monte Carlo study conducted to evaluate the performance of the proposed method, as compared to its nonregularized counterpart. Finally, an application is presented that demonstrates the empirical usefulness of the proposed method. Psychonomic Society, Inc., 2012 Two-stage least squares nationallicence Structural equation models nationallicence Misspecification nationallicence Small sample size nationallicence Ridge-type regularization nationallicence Two-stage ridge least squares nationallicence Behavior Research Methods Springer-Verlag 45/1(2013-03-01), 75-81 45:1<75 2013 45 13428 https://doi.org/10.3758/s13428-012-0206-0 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.3758/s13428-012-0206-0 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Jung Sunho School of Management, Kyung Hee University, Seoul, South Korea aut NATIONALLICENCE 773 0- Behavior Research Methods Springer-Verlag 45/1(2013-03-01), 75-81 45:1<75 2013 45 13428 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer