Mplus VERSION 6
MUTHEN & MUTHEN
04/25/2010 10:57 PM
INPUT INSTRUCTIONS
TITLE: cat5
path analysis with a final dependent variable that is binary
DATA: FILE IS big.dat;
FORMAT IS
2f5,f2,t14,5f7,t50,f8,t60,6f1.0,t67,2f2.0,t71,8f1.0,t79,f2.0,t82,4f2.0;
VARIABLE: NAMES ARE
g1-g9
y1 y2 y3 y4 y5 y6
y7 y8 x1-x13;
USEOBS = g3 EQ 64 ;
USEVAR ARE y5 y8 x1-x4 x8;
MISSING ARE .;
CATEGORICAL IS y8;
DEFINE: CUT y8(1.5);
! y8 is originally a continuous outcome variable with a strong floor
! effect. It is dichotomized by the CUT option above.
ANALYSIS: TYPE=MEANSTRUCTURE;
MODEL: y8 ON y5 x8;
y5 ON x1-x4 x8;
! this is a path analysis model, where the influence of x1-x4 on the
! dichotomous outcome y8 is mediated by the continuous outcome y5 and
! where x8 has a direct influence on y8. While y5 is related to x1-x4 and
! x8 by an ordinary linear regression, y8 is related to y5 and x8 by a
! probit regression. The model imposes 4 restrictions (4 d.f.) in that
! x1-x4 are not influencing y8 directly.
OUTPUT: sampstat;
*** WARNING in ANALYSIS command
Starting with Version 5, TYPE=MEANSTRUCTURE is the default for all
analyses. To remove means from the model, use
MODEL=NOMEANSTRUCTURE in the ANALYSIS command.
*** WARNING
Data set contains cases with missing on x-variables.
These cases were not included in the analysis.
Number of cases with missing on x-variables: 40
*** WARNING
Data set contains cases with missing on all variables except
x-variables. These cases were not included in the analysis.
Number of cases with missing on all variables except x-variables: 40
3 WARNING(S) FOUND IN THE INPUT INSTRUCTIONS
cat5
path analysis with a final dependent variable that is binary
SUMMARY OF ANALYSIS
Number of groups 1
Number of observations 1185
Number of dependent variables 2
Number of independent variables 5
Number of continuous latent variables 0
Observed dependent variables
Continuous
Y5
Binary and ordered categorical (ordinal)
Y8
Observed independent variables
X1 X2 X3 X4 X8
Estimator WLSMV
Maximum number of iterations 1000
Convergence criterion 0.500D-04
Maximum number of steepest descent iterations 20
Maximum number of iterations for H1 2000
Convergence criterion for H1 0.100D-03
Parameterization DELTA
Input data file(s)
big.dat
Input data format
(2F5,F2,T14,5F7,T50,F8,T60,6F1.0,T67,2F2.0,T71,8F1.0,T79,F2.0,T82,4F2.0)
SUMMARY OF DATA
Number of missing data patterns 3
COVARIANCE COVERAGE OF DATA
Minimum covariance coverage value 0.100
PROPORTION OF DATA PRESENT
Covariance Coverage
Y5 Y8
________ ________
Y5 0.979
Y8 0.824 0.846
UNIVARIATE PROPORTIONS AND COUNTS FOR CATEGORICAL VARIABLES
Y8
Category 1 0.881 883.000
Category 2 0.119 119.000
SAMPLE STATISTICS
ESTIMATED SAMPLE STATISTICS
MEANS/INTERCEPTS/THRESHOLDS
Y5 Y8$1
________ ________
1 0.525 1.494
SLOPES
X1 X2 X3 X4 X8
________ ________ ________ ________ ________
Y5 0.751 -0.317 -0.167 0.322 0.048
Y8 0.451 -0.109 -0.171 0.246 0.353
CORRELATION MATRIX (WITH VARIANCES ON THE DIAGONAL)
Y5 Y8
________ ________
Y5 1.910
Y8 0.310
THE MODEL ESTIMATION TERMINATED NORMALLY
TESTS OF MODEL FIT
Chi-Square Test of Model Fit
Value 9.140*
Degrees of Freedom 4
P-Value 0.0577
* The chi-square value for MLM, MLMV, MLR, ULSMV, WLSM and WLSMV cannot be used
for chi-square difference testing in the regular way. MLM, MLR and WLSM
chi-square difference testing is described on the Mplus website. MLMV, WLSMV,
and ULSMV difference testing is done using the DIFFTEST option.
Chi-Square Test of Model Fit for the Baseline Model
Value 168.946
Degrees of Freedom 11
P-Value 0.0000
CFI/TLI
CFI 0.967
TLI 0.911
Number of Free Parameters 10
RMSEA (Root Mean Square Error Of Approximation)
Estimate 0.033
WRMR (Weighted Root Mean Square Residual)
Value 0.772
MODEL RESULTS
Two-Tailed
Estimate S.E. Est./S.E. P-Value
Y8 ON
Y5 0.245 0.027 9.086 0.000
X8 0.341 0.130 2.620 0.009
Y5 ON
X1 0.796 0.094 8.430 0.000
X2 -0.322 0.110 -2.925 0.003
X3 -0.187 0.122 -1.529 0.126
X4 0.343 0.105 3.251 0.001
X8 0.048 0.101 0.478 0.633
Intercepts
Y5 0.526 0.103 5.096 0.000
Thresholds
Y8$1 1.623 0.103 15.707 0.000
Residual Variances
Y5 1.893 0.079 23.941 0.000
R-SQUARE
Observed Residual
Variable Estimate Variance
Y5 0.099
Y8 0.141 0.887
QUALITY OF NUMERICAL RESULTS
Condition Number for the Information Matrix 0.418E-01
(ratio of smallest to largest eigenvalue)
Beginning Time: 22:57:57
Ending Time: 22:57:57
Elapsed Time: 00:00:00
MUTHEN & MUTHEN
3463 Stoner Ave.
Los Angeles, CA 90066
Tel: (310) 391-9971
Fax: (310) 391-8971
Web: www.StatModel.com
Support: Support@StatModel.com
Copyright (c) 1998-2010 Muthen & Muthen
Back to table of examples