1、 Advances in Psychological Science 593 ( 510631) ( ) ( ) 1 latent variable Structural Equation Modeling, SEM . X 1 X 2 Y X 1 X 2 X 1 X 2 A B 2 3 ( SPSS, SAS) X 1 X 2 ( ) X 1 X 2 4,5 * mail: . e X X X X Y + + + + = 2 1 3 2 2 1 1 0 b b b b , (1) X 1 X 2 X 1 X 2 H 0 3 =0 t X 1 X 2 ( 3 0 ) X 1 X 2 X 2 Y
2、 X 1 1 1 indicator 1 x 2 x y h 1. Bagozzi Baumgartner Yi 6 (K) (P) (T) 7 1 7 (K) : K 1 K 2 (P) P1 P2 (T) T1 T2 T3 1 K, P, T (K) (P) (T) T 3 T ( ) (2 K1 K2 1 K) (2 P1 P2 1 P) (3 T1 T2 T3 1 T ) Anderson Rubin 7 SPSS 1 1 1.2 e KP P K T + + + + = 3 2 1 0 b b b b Joreskog 8 LISREL9 SPSS 3 b se( 3 b ) K,
3、P T 1.3 Joreskog 9 , Bagozzi Yi10 , MacKenzie Spreng 11 ( 2 x ) 2 x 1 (K) 2 1 K K + 2 1 k k + 2 1 k k + 2 1 k k + ( ) ( ) (T) (P) z g a + + = P T . SEM ( LISREL 8.3 AMOS 4.0 EQS 6.0) (subgroup multigroup) 2 2 2 2 2 2 SEM 2 1 x x ( 2 1 x x ) 12 ( ) Kenny Judd 131984 y 1 x 1 x , 2 x ; 2 x 3 x , 4 x (
4、) ( ) 1 1 1 d x + = x , 2 1 2 2 d x l + = x ; 3 2 3 d x + = x , 4 2 4 4 d x l + = x . ( 2) z x x g x g x g + + + = 2 1 3 2 2 1 1 y , ( 3) 2 1 x x 1 x 2 x y (3) (1) (3) 1 x 2 x 2 1 x x 3 1 x x , 4 1 x x , 3 2 x x , 4 2 x x 2 1 x x y, 1 x , 2 x , 3 x , 4 x ( constraint) 3 1 1 2 3 1 2 1 3 1 d d d x d x
5、 x x + + + = x x , (4) 3 1 x x 2 1 x x 1 COSAN LISREL Kenny Judd ( ) 1987 Hayduk 14 LISREL Kenny Judd 1995 Jaccard Wan 15 LISREL8 Kenny Judd h y ( 3) z x x g x g x g h + + + = 2 1 3 2 2 1 1(5) (4) 2 4 3 3 1 (4) 13 2 1 3 1 3 1 d x x l l + = x x , (6) ) var( ) var( ) var( ) var( ) var( ) var( ) var( 3
6、 1 1 2 2 3 3 1 2 1 13 d d d x l d x l d + + = ( 7) 1 2 1 1 Jaccard Wan Kenny-Judd 1996 Joreskog Yang 16 1 x 2 x 2 1 x x ) , cov( ) ( ) ( ) , cov( ) ( 2 1 2 1 2 1 2 1 x x x x x x x x = + = E E E Kenny-Judd SEM ( 2 1 2 1 , , x x x x ) ) , 0 , 0 ( 21 f Joreskog-Yang 1 7 Kenny-Judd (specify) 1 2 2001 Al
7、gina Moulder 17 Joreskog-Yang Algina-Moulder Joreskog-Yang 1 SEM SEM ( ) ( ) SEM LMS 19,23,24 SEM SEM Wall Amemiya GAPI 25 Kenny-Judd Marsh Wen Hau 26 Kenny-Judd 1 Bollen K A. Structural equations with latent variables. New York: Wiley, 1989 2 . . 1994 3 . . 1997 4 Aiken L S, West S G. Multiple regr
8、ession: Testing and interpreting interactions. Newbury Park, CA: Sage, 1991 5 Cohen J, Cohen P. Applied multiple regression / correlational analysis for the behavioral science. Hillsdale, NJ: Erlbaum, 1975 6 Bagozzi R P, Baumgartner H, Yi Y. State versus action orientation and the theory of reasoned
9、 action: An application to coupon usage. Journal of Consumer Research, 1992, 18: 505518 7 Anderson T W, Rubin H. Statistical inference in factor analysis. In Proceedings of the third Berkeley symposium (Vol. V). Berkeley, CA: University of California Press, 1956. 111150 8 Joreskog K G . Interaction
10、and nonlinear modeling: issue and approaches. In: Schumacker R E, Marcoulides G A ed. Interaction and nonlinear effects in structural equation modeling. Mahwah, NJ: Erlbaum, 1998. 239250 9 Joreskog K G. Simultaneous factor analysis in several populations. Psychometrika, 1971, 36: 409426 10 Bagozzi R
11、 P, Yi Y. On the use of structural equation models in experimental designs. Journal of Marketing Research, 1989, 26(3): 271284 11 MacKenzie S B, Spreng R A. How does motivation moderate the impact of central and peripheral processing on brand attitudes and intentions. Journal of Consumer Research, 1
12、992, 18(1): 519529 12 Hanushek E A, Jackson J E. Statistical methods for social scientists. New York: Academic Press, 1977 13 Kenny D A, Judd C M. Estimating the nonlinear and interactive effects of latent variables. Psychological Bulletin, 1984, 9: 201210 14 Hayduk L A. Structural equation modeling
13、 with LISREL: Essential and advances. Baltimore: Johns Hopkins University Press, 1987 15 Jaccard J, Wan C K. Measurement error in the analysis of interaction effects between continuous predictors using multiple regression: multiple indicator and structural equation approaches. Psychological Bulletin
14、, 1995, 117(2): 348357 16 Joreskog K G, Yang F. Nonlinear structural equation models: The Kenny-Judd model with interaction effects. In: Marcoulides G A, Schumacker R E ed. Advanced structural equation modeling: Issued and techniques. Mahwah, NJ: Erlbaum, 1996. 5788 17 Algina J, Moulder B C. A note
15、on estimating the Joreskog-Yang model for latent variable interaction using LISREL 8.3. Structural Equation Modeling, 2001, 8(1): 4052 18 Bollen K A, Paxton P. Two -stage least squares estimation of interaction effects. In: Schumacker R E , Marcoulides G A ed. Interaction and nonlinear effects in st
16、ructural equation modeling. Mahwah, NJ: Lawrence Erlbaum Associates, 1998. 125151 19 Schermelleh-Engel K, Klein A, Moosbrugger H. Estimating nonlinear effects using a latent moderated structural equations approach. In: Schumacker R E, Marcoulides G A ed. Interaction and nonlinear effects in structur
17、al equation modeling. Mahwah, NJ: Erlbaum, 1998. 203238 20 Laplante B, Sabourin S, Cournoyer L G , Wright J. Estimating nonlinear effects using a structured means intercept approach. In: Schumacker R E , Marcoulides G A ed. Interaction and nonlinear effects in structural equation modeling. Mahwah, N
18、J: Lawrence Erlbaum Associates, 1998. 183202 21 Wall M M, Amemiya Y. Estimation for polynomial structural equation models. The Journal of the American Statistical Association, 2000, 95: 929940 22 Moulder B C, Algina J. Comparison of methods for estimating and testing latent variable interactions. St
19、ructural Equation Modeling, 2002, 9(1): 119 23 Moosbrugger H, Schermelleh-Engel K, Klein A. Methodological problems of estimating latent interaction effects. Methods of Psychological Research Online, 2, 95111 24 Klein A, Moosbrugger H. Maximum likelihood estimation of latent interaction effects with the LMS method. Psychometrika, 2000, 65(4): 457474 25 Wall M M, Amemiya Y. Generalized appended product indicator procedure for nonlinear structural equation analysis. Journal of Educational and Behavioral Statistics, 2001, 26(1): 129 26
