! Fitting univariate models to raw ordinal data - rectangular data files
!
! probit.mx
!
!
The following MX script lines were read for group 1
#NGROUPS 1
Note: #NGroup set number of groups to 1
ANALYSIS OF HIGUCHI ADH1B DATA
DATA NINPUTVARS=5
ORDINAL FILE=ADH2.DAT
Ordinal data read initiated
NOTE: Rectangular file contained 6 records with data
that contained a total of 30 observations
LABELS GTYPE STATUS FREQ ADD DOM
DEFINITION_VARIABLES GTYPE FREQ ADD DOM ;
NOTE: Definition yields 6 data vectors for analysis
NOTE: Vectors contain a total of 6 observations
BEGIN MATRICES;
V LOWER 1 1 ! VARIANCE (CONSTRAINED TO UNITY)
M FULL 1 1 FREE ! VECTOR OF THRESHOLDS (INTERCEPTS)
B FULL 1 2 FREE ! VECTOR OF REGRESSION COEFFICIENTS
K FULL 2 1 ! MATRIX FOR DEFINITION VARIABLES
W FULL 1 1 ! MATRIX FOR FREQUENCY WEIGHT
END MATRICES;
SPECIFY M 101
SPECIFY B 102 103
SPECIFY K ADD DOM
SPECIFY W FREQ
MATRIX V 1.0
START 0 M 1 1
START 0.20 B 1 1
START 0.10 B 1 2
FREQUENCY W ;
COVARIANCES V ;
THRESHOLDS -M- B*K;
OPTIONS RSIDUALS
INTERVAL B 1 1 B 1 2 M 1 1
END
Summary of VL file data for group 1
DOM ADD FREQ GTYPE STATUS
Code -4.0000 -3.0000 -2.0000 -1.0000 1.0000
Number 6.0000 6.0000 6.0000 6.0000 6.0000
Mean 0.3333 1.0000 140.6667 2.0000 0.5000
Variance 0.2222 0.6667 4243.5556 0.6667 0.2500
Minimum 0.0000 0.0000 20.0000 1.0000 0.0000
Maximum 1.0000 2.0000 207.0000 3.0000 1.0000
PARAMETER SPECIFICATIONS
GROUP NUMBER: 1
Analysis of Higuchi ADH1B data
MATRIX B
This is a FULL matrix of order 1 by 2
1 2
1 102 103
MATRIX K
This is a FULL matrix of order 2 by 1
1
1 -3
2 -4
MATRIX M
This is a FULL matrix of order 1 by 1
1
1 101
MATRIX V
This is a LOWER TRIANGULAR matrix of order 1 by 1
It has no free parameters specified
MATRIX W
This is a FULL matrix of order 1 by 1
1
1 -2
Mx starting optimization; number of parameters = 3
MX PARAMETER ESTIMATES
GROUP NUMBER: 1
Analysis of Higuchi ADH1B data
MATRIX B
This is a FULL matrix of order 1 by 2
1 2
1 0.5430 -0.2676
MATRIX K
This is a FULL matrix of order 2 by 1
1
1 0.0000
2 0.0000
MATRIX M
This is a FULL matrix of order 1 by 1
1
1 0.1810
MATRIX V
This is a LOWER TRIANGULAR matrix of order 1 by 1
1
1 1.0000
MATRIX W
This is a FULL matrix of order 1 by 1
1
1 155.0000
Matrix of EXPECTED thresholds
STATUS
Threshold 1 -0.1810
EXPECTED COVARIANCE MATRIX
STATUS
STATUS 1.0000
Function value of this group: 984.8588
Where the fit function is -2 * Log-likelihood of raw ordinal
Your model has 3 estimated parameters and 6 Observed statistics
-2 times log-likelihood of data >>> 984.859
Degrees of freedom >>>>>>>>>>>>>>>> 3
3 Confidence intervals requested in group 1
Matrix Element Int. Estimate Lower Upper Lfail Ufail
B 1 1 1 95.0 0.5430 0.4096 0.6816 0 0 0 0
B 1 1 2 95.0 -0.2676 -0.4715 -0.0652 0 0 0 0
M 1 1 1 95.0 0.1810 0.0512 0.3113 0 0 0 0
This problem used 0.0% of my workspace
Task Time elapsed (DD:HH:MM:SS)
Reading script & data 0: 0: 0: 0.26
Execution 0: 0: 0: 0.11
TOTAL 0: 0: 0: 0.37
Total number of warnings issued: 0
______________________________________________________________________________