Mplus VERSION 6
MUTHEN & MUTHEN
04/25/2010 10:57 PM
INPUT INSTRUCTIONS
TITLE:
cat4
2-group mimic for dichotomous outcomes
DATA:
FILE IS wmimicd.dat;
VARIABLE:
NAMES ARE x1-x3 y1-y16;
USEV = y6-y10 x4 x6 x7;
CATEGORICAL = y6-y10;
! the next statement defines the 2 groups (groupA and groupB):
GROUPING = x3 (1 = groupA 2 = groupB);
DEFINE: x4 = 89 - x1;
x6 = 0; if (x2 eq 2) then x6 = 1;
x7 = 0; if (x2 eq 1) then x7 = 1;
ANALYSIS:
TYPE = MGROUP MEANSTRUCTURE;
! type = mgroup gives multiple-group analysis
MODEL:
! The statement MODEL:
! defines the general model that holds for both groups.
! the default is that there are group-invariant thresholds
! and loadings
f1 BY y6-y10;
f1 ON x4 x6 x7;
! Because x variables are present, the analysis assumes
! conditional normality of latent response variables given the x's
! in line with probit analysis. this analysis makes less strong
! normality assumptions than using tetrachoric
! and biserial correlations. Given that the model is fitted to
! estimates from probit regressions, the computations are, however,
! more time consuming than when x's are not present, especially
! for large sample sizes (as in this case) and a large number of
! outcome variables.
OUTPUT: standardized;
*** 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.
1 WARNING(S) FOUND IN THE INPUT INSTRUCTIONS
cat4
2-group mimic for dichotomous outcomes
SUMMARY OF ANALYSIS
Number of groups 2
Number of observations
Group GROUPA 2508
Group GROUPB 2534
Number of dependent variables 5
Number of independent variables 3
Number of continuous latent variables 1
Observed dependent variables
Binary and ordered categorical (ordinal)
Y6 Y7 Y8 Y9 Y10
Observed independent variables
X4 X6 X7
Continuous latent variables
F1
Variables with special functions
Grouping variable X3
Estimator WLSMV
Maximum number of iterations 1000
Convergence criterion 0.500D-04
Maximum number of steepest descent iterations 20
Parameterization DELTA
Input data file(s)
wmimicd.dat
Input data format FREE
UNIVARIATE PROPORTIONS AND COUNTS FOR CATEGORICAL VARIABLES
Group GROUPA
Y6
Category 1 0.969 2431.000
Category 2 0.031 77.000
Y7
Category 1 0.960 2407.000
Category 2 0.040 101.000
Y8
Category 1 0.979 2456.000
Category 2 0.021 52.000
Y9
Category 1 0.986 2472.000
Category 2 0.014 36.000
Y10
Category 1 0.933 2341.000
Category 2 0.067 167.000
Group GROUPB
Y6
Category 1 0.995 2521.000
Category 2 0.005 13.000
Y7
Category 1 0.984 2494.000
Category 2 0.016 40.000
Y8
Category 1 0.992 2514.000
Category 2 0.008 20.000
Y9
Category 1 0.992 2514.000
Category 2 0.008 20.000
Y10
Category 1 0.978 2478.000
Category 2 0.022 56.000
THE MODEL ESTIMATION TERMINATED NORMALLY
TESTS OF MODEL FIT
Chi-Square Test of Model Fit
Value 49.011*
Degrees of Freedom 37
P-Value 0.0894
Chi-Square Contributions From Each Group
GROUPA 33.967
GROUPB 15.044
* 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 2912.914
Degrees of Freedom 50
P-Value 0.0000
CFI/TLI
CFI 0.996
TLI 0.994
Number of Free Parameters 23
RMSEA (Root Mean Square Error Of Approximation)
Estimate 0.011
WRMR (Weighted Root Mean Square Residual)
Value 1.053
MODEL RESULTS
Two-Tailed
Estimate S.E. Est./S.E. P-Value
Group GROUPA
F1 BY
Y6 1.000 0.000 999.000 999.000
Y7 1.039 0.063 16.586 0.000
Y8 1.086 0.066 16.511 0.000
Y9 1.027 0.069 14.874 0.000
Y10 0.935 0.058 16.012 0.000
F1 ON
X4 -0.028 0.014 -1.966 0.049
X6 0.091 0.075 1.207 0.227
X7 0.136 0.089 1.526 0.127
Intercepts
F1 0.000 0.000 999.000 999.000
Thresholds
Y6$1 0.799 0.545 1.468 0.142
Y7$1 1.793 0.527 3.403 0.001
Y8$1 1.349 0.628 2.148 0.032
Y9$1 1.815 0.665 2.731 0.006
Y10$1 0.146 0.470 0.312 0.755
Residual Variances
F1 0.665 0.062 10.666 0.000
Scales
Y6 1.000 0.000 999.000 999.000
Y7 1.000 0.000 999.000 999.000
Y8 1.000 0.000 999.000 999.000
Y9 1.000 0.000 999.000 999.000
Y10 1.000 0.000 999.000 999.000
Group GROUPB
F1 BY
Y6 1.000 0.000 999.000 999.000
Y7 1.039 0.063 16.586 0.000
Y8 1.086 0.066 16.511 0.000
Y9 1.027 0.069 14.874 0.000
Y10 0.935 0.058 16.012 0.000
F1 ON
X4 -0.028 0.020 -1.360 0.174
X6 0.050 0.070 0.709 0.478
X7 0.024 0.093 0.259 0.796
Intercepts
F1 0.365 0.624 0.585 0.559
Thresholds
Y6$1 0.799 0.545 1.468 0.142
Y7$1 1.793 0.527 3.403 0.001
Y8$1 1.349 0.628 2.148 0.032
Y9$1 1.815 0.665 2.731 0.006
Y10$1 0.146 0.470 0.312 0.755
Residual Variances
F1 0.331 0.324 1.024 0.306
Scales
Y6 1.478 0.725 2.040 0.041
Y7 1.531 0.733 2.089 0.037
Y8 1.422 0.690 2.061 0.039
Y9 1.486 0.718 2.070 0.038
Y10 1.712 0.830 2.062 0.039
STANDARDIZED MODEL RESULTS
StdYX Std
Estimate Estimate
Group GROUPA
F1 BY
Y6 0.817 0.820
Y7 0.849 0.852
Y8 0.886 0.890
Y9 0.838 0.842
Y10 0.764 0.766
F1 ON
X4 -0.077 -0.034
X6 0.049 0.111
X7 0.061 0.166
Intercepts
F1 0.000 0.000
Thresholds
Y6$1 0.797 0.799
Y7$1 1.786 1.793
Y8$1 1.343 1.349
Y9$1 1.808 1.815
Y10$1 0.146 0.146
Residual Variances
F1 0.989 0.989
Scales
Y6 1.000 1.000
Y7 1.000 1.000
Y8 1.000 1.000
Y9 1.000 1.000
Y10 1.000 1.000
Group GROUPB
F1 BY
Y6 0.852 0.579
Y7 0.917 0.602
Y8 0.890 0.629
Y9 0.879 0.595
Y10 0.922 0.542
F1 ON
X4 -0.108 -0.048
X6 0.037 0.086
X7 0.015 0.042
Intercepts
F1 0.630 0.630
Thresholds
Y6$1 1.176 0.799
Y7$1 2.731 1.793
Y8$1 1.908 1.349
Y9$1 2.682 1.815
Y10$1 0.249 0.146
Residual Variances
F1 0.987 0.987
Scales
Y6 1.000 1.478
Y7 1.000 1.531
Y8 1.000 1.422
Y9 1.000 1.486
Y10 1.000 1.712
R-SQUARE
Group GROUPA
Observed Residual
Variable Estimate Variance
Y6 0.667 0.335
Y7 0.720 0.282
Y8 0.786 0.216
Y9 0.703 0.300
Y10 0.584 0.419
Latent
Variable Estimate
F1 0.011
Group GROUPB
Observed Residual
Variable Estimate Variance
Y6 0.726 0.126
Y7 0.841 0.069
Y8 0.792 0.104
Y9 0.773 0.104
Y10 0.851 0.052
Latent
Variable Estimate
F1 0.013
QUALITY OF NUMERICAL RESULTS
Condition Number for the Information Matrix 0.105E-04
(ratio of smallest to largest eigenvalue)
Beginning Time: 22:57:56
Ending Time: 22:57:56
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