* Define locations of files used in examples -- CHANGE THIS.
FILE HANDLE example /NAME = "C:\Dropbox\14_Psyc930MLM\Download\SPSS".
* SPSS code to import data.
GET FILE = "example/Example4.sav".
DATASET NAME Example4 WINDOW=FRONT.
* Adding another version of predictors to be coded 0/1 for low/high.
RECODE freq size (-.5=0) (.5=1) INTO freq01 size01.
EXECUTE.
******************************************************************************
******
EXAMPLE 4 MODELS
******
******************************************************************************.
DATASET ACTIVATE Example4 WINDOW=FRONT.
TITLE "SPSS Empty Means Model: No Random Intercepts (E only)".
SPSS Empty Means Model: No Random Intercepts (E only)
MIXED rt BY Subject Item
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = .
Mixed Model Analysis
Notes
|
Output Created
|
9-MAY-2014 11:15:25
|
Comments
|
|
Input
|
Data
|
C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
|
Active Dataset
|
Example4
|
Filter
|
<none>
|
Weight
|
<none>
|
Split File
|
<none>
|
N of Rows in Working
Data File
|
1392
|
Missing Value
Handling
|
Definition of
Missing
|
User-defined missing
values are treated as missing.
|
Cases Used
|
Statistics are based
on all cases with valid data for all variables in the model.
|
Syntax
|
MIXED rt BY Subject Item
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = .
|
Resources
|
Processor Time
|
00:00:00.00
|
Elapsed Time
|
00:00:00.05
|
|
[Example4] C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
Warnings
|
A(n) FIXED subcommand
has no specifications and will therefore be ignored.
|
|
Model Dimensiona
|
|
Number of Levels
|
Number of Parameters
|
Fixed Effects
|
Intercept
|
1
|
1
|
Residual
|
|
1
|
Total
|
1
|
2
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
|
|
|
|
Information Criteriaa
|
-2 Restricted Log
Likelihood
|
17820.703
|
Akaike's
Information Criterion (AIC)
|
17822.703
|
Hurvich
and Tsai's Criterion (AICC)
|
17822.706
|
Bozdogan's Criterion (CAIC)
|
17828.941
|
Schwarz's Bayesian
Criterion (BIC)
|
17827.941
|
The information
criteria are displayed in smaller-is-better forms.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Fixed Effects
Type III Tests of Fixed Effectsa
|
Source
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
Intercept
|
1
|
1391
|
26085.502
|
.000
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Estimates of Fixed Effectsa
|
Parameter
|
Estimate
|
Std. Error
|
df
|
t
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Intercept
|
632.382902
|
3.915440
|
1391
|
161.510
|
.000
|
624.702099
|
640.063706
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Covariance Parameters
Estimates of Covariance Parametersa
|
Parameter
|
Estimate
|
Std. Error
|
Wald Z
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Residual
|
21340.288219
|
809.192248
|
26.372
|
.000
|
19811.801766
|
22986.697861
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
TITLE.
TITLE "SPSS Random Intercept for Subjects Model".
SPSS Random Intercept for Subjects Model
MIXED rt BY Subject Item
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED =
/RANDOM = INTERCEPT | SUBJECT(Subject) COVTYPE(UN).
Mixed Model Analysis
Notes
|
Output Created
|
9-MAY-2014 11:15:25
|
Comments
|
|
Input
|
Data
|
C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
|
Active Dataset
|
Example4
|
Filter
|
<none>
|
Weight
|
<none>
|
Split File
|
<none>
|
N of Rows in Working
Data File
|
1392
|
Missing Value
Handling
|
Definition of
Missing
|
User-defined missing
values are treated as missing.
|
Cases Used
|
Statistics are based
on all cases with valid data for all variables in the model.
|
Syntax
|
MIXED rt BY Subject Item
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED =
/RANDOM = INTERCEPT | SUBJECT(Subject)
COVTYPE(UN).
|
Resources
|
Processor Time
|
00:00:00.03
|
Elapsed Time
|
00:00:00.06
|
|
[Example4] C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
Warnings
|
A(n) FIXED subcommand
has no specifications and will therefore be ignored.
|
The covariance
structure for random effect with only one level will be changed to
Identity.
|
|
Model Dimensiona
|
|
Number of Levels
|
Covariance Structure
|
Number of Parameters
|
Subject Variables
|
Fixed Effects
|
Intercept
|
1
|
|
1
|
|
Random Effects
|
Intercept
|
1
|
Identity
|
1
|
subject
|
Residual
|
|
|
1
|
|
Total
|
2
|
|
3
|
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Information Criteriaa
|
-2 Restricted Log
Likelihood
|
17540.265
|
Akaike's
Information Criterion (AIC)
|
17544.265
|
Hurvich
and Tsai's Criterion (AICC)
|
17544.273
|
Bozdogan's Criterion (CAIC)
|
17556.740
|
Schwarz's Bayesian
Criterion (BIC)
|
17554.740
|
The information
criteria are displayed in smaller-is-better forms.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Fixed Effects
Type III Tests of Fixed Effectsa
|
Source
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
Intercept
|
1
|
37.004
|
2698.945
|
.000
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Estimates of Fixed Effectsa
|
Parameter
|
Estimate
|
Std. Error
|
df
|
t
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Intercept
|
631.416650
|
12.153993
|
37.004
|
51.951
|
.000
|
606.790400
|
656.042900
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Covariance Parameters
Estimates of Covariance Parametersa
|
Parameter
|
Estimate
|
Std. Error
|
Wald Z
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Residual
|
16307.206194
|
626.735712
|
26.019
|
.000
|
15123.951954
|
17583.034822
|
Intercept [subject =
subject]
|
Variance
|
5167.095849
|
1305.102184
|
3.959
|
.000
|
3149.564504
|
8477.006735
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
|
|
|
|
|
|
|
|
TITLE.
TITLE "SPSS Random Intercepts for Subjects and Items: Crossed Model".
SPSS Random Intercepts for Subjects and Items: Crossed Model
MIXED rt BY Subject Item
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED =
/RANDOM = INTERCEPT | SUBJECT(Subject) COVTYPE(UN)
/RANDOM = INTERCEPT | SUBJECT(Item) COVTYPE(UN).
Mixed Model Analysis
Notes
|
Output Created
|
9-MAY-2014 11:15:25
|
Comments
|
|
Input
|
Data
|
C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
|
Active Dataset
|
Example4
|
Filter
|
<none>
|
Weight
|
<none>
|
Split File
|
<none>
|
N of Rows in Working
Data File
|
1392
|
Missing Value
Handling
|
Definition of
Missing
|
User-defined missing
values are treated as missing.
|
Cases Used
|
Statistics are based
on all cases with valid data for all variables in the model.
|
Syntax
|
MIXED rt BY Subject Item
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED =
/RANDOM = INTERCEPT | SUBJECT(Subject) COVTYPE(UN)
/RANDOM = INTERCEPT | SUBJECT(Item) COVTYPE(UN).
|
Resources
|
Processor Time
|
00:00:00.13
|
Elapsed Time
|
00:00:00.45
|
|
[Example4] C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
Warnings
|
A(n) FIXED subcommand
has no specifications and will therefore be ignored.
|
The covariance
structure for random effect with only one level will be changed to
Identity.
|
The covariance
structure for random effect with only one level will be changed to
Identity.
|
|
Model Dimensiona
|
|
Number of Levels
|
Covariance Structure
|
Number of Parameters
|
Subject Variables
|
Fixed Effects
|
Intercept
|
1
|
|
1
|
|
Random Effects
|
Intercept
|
1
|
Identity
|
1
|
subject
|
Intercept
|
1
|
Identity
|
1
|
item
|
Residual
|
|
|
1
|
|
Total
|
3
|
|
4
|
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Information Criteriaa
|
-2 Restricted Log
Likelihood
|
17439.865
|
Akaike's
Information Criterion (AIC)
|
17445.865
|
Hurvich
and Tsai's Criterion (AICC)
|
17445.883
|
Bozdogan's Criterion (CAIC)
|
17464.579
|
Schwarz's Bayesian
Criterion (BIC)
|
17461.579
|
The information
criteria are displayed in smaller-is-better forms.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Fixed Effects
Type III Tests of Fixed Effectsa
|
Source
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
Intercept
|
1
|
59.436
|
1937.371
|
.000
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Estimates of Fixed Effectsa
|
Parameter
|
Estimate
|
Std. Error
|
df
|
t
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Intercept
|
635.327726
|
14.434156
|
59.436
|
44.016
|
.000
|
606.449476
|
664.205976
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Covariance Parameters
Estimates of Covariance Parametersa
|
Parameter
|
Estimate
|
Std. Error
|
Wald Z
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Residual
|
14343.045155
|
559.960379
|
25.614
|
.000
|
13286.481550
|
15483.628494
|
Intercept [subject =
subject]
|
Variance
|
5166.696188
|
1292.716758
|
3.997
|
.000
|
3164.031182
|
8436.942613
|
Intercept [subject =
item]
|
Variance
|
2414.111146
|
680.217164
|
3.549
|
.000
|
1389.685887
|
4193.704980
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
TITLE.
TITLE "SPSS Random Intercepts for Subjects and Items Crossed Predictive Model".
>Warning # 2003. Command name: TITLE
>The title given exceeds 60 characters in length. The first 60 characters will
>be used.
SPSS Random Intercepts for Subjects and Items Crossed Predic
SUBTITLE "Using BY statement to get cell means and comparisons via EMMEANS".
>Warning # 2004. Command name: SUBTITLE
>The subtitle given exceeds 60 characters in length. The first 60 characters
>will be used.
SPSS Random Intercepts for Subjects and Items Crossed Predic
Using BY statement to get cell means and comparisons via EMM
MIXED rt BY Subject Item freq01 size01
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = freq01 size01 freq01*size01
/RANDOM = INTERCEPT | SUBJECT(Subject) COVTYPE(UN)
/RANDOM = INTERCEPT | SUBJECT(Item) COVTYPE(UN)
/EMMEANS = TABLES(freq01)
/EMMEANS = TABLES(size01)
/EMMEANS = TABLES(freq01*size01) COMPARE(freq01)
/EMMEANS = TABLES(freq01*size01) COMPARE(size01).
Mixed Model Analysis
Notes
|
Output Created
|
9-MAY-2014 11:15:26
|
Comments
|
|
Input
|
Data
|
C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
|
Active Dataset
|
Example4
|
Filter
|
<none>
|
Weight
|
<none>
|
Split File
|
<none>
|
N of Rows in Working
Data File
|
1392
|
Missing Value
Handling
|
Definition of
Missing
|
User-defined missing
values are treated as missing.
|
Cases Used
|
Statistics are based
on all cases with valid data for all variables in the model.
|
Syntax
|
MIXED rt BY Subject Item freq01 size01
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = freq01 size01 freq01*size01
/RANDOM = INTERCEPT | SUBJECT(Subject) COVTYPE(UN)
/RANDOM = INTERCEPT | SUBJECT(Item) COVTYPE(UN)
/EMMEANS = TABLES(freq01)
/EMMEANS = TABLES(size01)
/EMMEANS = TABLES(freq01*size01) COMPARE(freq01)
/EMMEANS = TABLES(freq01*size01) COMPARE(size01).
|
Resources
|
Processor Time
|
00:00:00.22
|
Elapsed Time
|
00:00:00.59
|
|
[Example4] C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
Warnings
|
The covariance
structure for random effect with only one level will be changed to
Identity.
|
The covariance
structure for random effect with only one level will be changed to
Identity.
|
|
Model Dimensiona
|
|
Number of Levels
|
Covariance Structure
|
Number of Parameters
|
Subject Variables
|
Fixed Effects
|
Intercept
|
1
|
|
1
|
|
freq01
|
2
|
|
1
|
|
size01
|
2
|
|
1
|
|
freq01 * size01
|
4
|
|
1
|
|
Random Effects
|
Intercept
|
1
|
Identity
|
1
|
subject
|
Intercept
|
1
|
Identity
|
1
|
item
|
Residual
|
|
|
1
|
|
Total
|
11
|
|
7
|
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Information Criteriaa
|
-2 Restricted Log
Likelihood
|
17402.447
|
Akaike's
Information Criterion (AIC)
|
17408.447
|
Hurvich
and Tsai's Criterion (AICC)
|
17408.465
|
Bozdogan's Criterion (CAIC)
|
17427.154
|
Schwarz's Bayesian
Criterion (BIC)
|
17424.154
|
The information
criteria are displayed in smaller-is-better forms.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Fixed Effects
Type III Tests of Fixed Effectsa
|
Source
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
Intercept
|
1
|
53.854
|
2122.653
|
.000
|
freq01
|
1
|
31.777
|
5.360
|
.027
|
size01
|
1
|
31.781
|
4.622
|
.039
|
freq01 * size01
|
1
|
31.781
|
6.012
|
.020
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Estimates of Fixed Effectsa
|
Parameter
|
Estimate
|
Std. Error
|
df
|
t
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Intercept
|
618.207726
|
19.151364
|
58.826
|
32.280
|
.000
|
579.883557
|
656.531895
|
[freq01=.00]
|
2.009733
|
20.947786
|
31.194
|
.096
|
.924
|
-40.702794
|
44.722261
|
[freq01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[size01=.00]
|
67.595626
|
21.119320
|
32.151
|
3.201
|
.003
|
24.584900
|
110.606352
|
[size01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[freq01=.00] *
[size01=.00]
|
-72.030574
|
29.378049
|
31.781
|
-2.452
|
.020
|
-131.887905
|
-12.173243
|
[freq01=.00] *
[size01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[freq01=1.00] *
[size01=.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[freq01=1.00] *
[size01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
b. This parameter is
set to zero because it is redundant.
|
|
Covariance Parameters
Estimates of Covariance Parametersa
|
Parameter
|
Estimate
|
Std. Error
|
Wald Z
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Residual
|
14341.038968
|
559.786607
|
25.619
|
.000
|
13284.796444
|
15481.260819
|
Intercept [subject =
subject]
|
Variance
|
5168.472035
|
1293.103401
|
3.997
|
.000
|
3165.187920
|
8439.657882
|
Intercept [subject =
item]
|
Variance
|
1692.415074
|
526.770726
|
3.213
|
.001
|
919.532574
|
3114.918238
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Estimated Marginal Means
1. freq01a
|
freq01
|
Mean
|
Std. Error
|
df
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
.00
|
618.000
|
15.501
|
62.462
|
587.018
|
648.982
|
1.00
|
652.006
|
15.733
|
63.506
|
620.571
|
683.440
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
2. size01a
|
size01
|
Mean
|
Std. Error
|
df
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
.00
|
650.793
|
15.559
|
63.345
|
619.703
|
681.883
|
1.00
|
619.213
|
15.675
|
62.646
|
587.884
|
650.541
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
3. freq01 * size01
Estimatesa
|
freq01
|
size01
|
Mean
|
Std. Error
|
df
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
.00
|
.00
|
615.783
|
18.575
|
60.661
|
578.636
|
652.929
|
1.00
|
620.217
|
18.549
|
60.333
|
583.118
|
657.317
|
1.00
|
.00
|
685.803
|
18.742
|
62.663
|
648.346
|
723.261
|
1.00
|
618.208
|
19.151
|
58.826
|
579.884
|
656.532
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Pairwise Comparisonsa
|
size01
|
(I) freq01
|
(J) freq01
|
Mean Difference (I-J)
|
Std. Error
|
df
|
Sig.c
|
95% Confidence Interval for Differencec
|
Lower Bound
|
Upper Bound
|
.00
|
.00
|
1.00
|
-70.021*
|
20.597
|
32.401
|
.002
|
-111.955
|
-28.087
|
1.00
|
.00
|
70.021*
|
20.597
|
32.401
|
.002
|
28.087
|
111.955
|
1.00
|
.00
|
1.00
|
2.010
|
20.948
|
31.194
|
.924
|
-40.703
|
44.722
|
1.00
|
.00
|
-2.010
|
20.948
|
31.194
|
.924
|
-44.722
|
40.703
|
Based on estimated
marginal means
|
*. The mean
difference is significant at the .05 level.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
c. Adjustment for
multiple comparisons: Least Significant Difference (equivalent to no
adjustments).
|
|
Univariate Testsa
|
size01
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
.00
|
1
|
32.401
|
11.557
|
.002
|
1.00
|
1
|
31.194
|
.009
|
.924
|
Each F tests the
simple effects of freq01 within each level combination of the other effects
shown. These tests are based on the linearly independent pairwise
comparisons among the estimated marginal means.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
4. freq01 * size01
Estimatesa
|
freq01
|
size01
|
Mean
|
Std. Error
|
df
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
.00
|
.00
|
615.783
|
18.575
|
60.661
|
578.636
|
652.929
|
1.00
|
620.217
|
18.549
|
60.333
|
583.118
|
657.317
|
1.00
|
.00
|
685.803
|
18.742
|
62.663
|
648.346
|
723.261
|
1.00
|
618.208
|
19.151
|
58.826
|
579.884
|
656.532
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Pairwise Comparisonsa
|
freq01
|
(I) size01
|
(J) size01
|
Mean Difference (I-J)
|
Std. Error
|
df
|
Sig.c
|
95% Confidence Interval for Differencec
|
Lower Bound
|
Upper Bound
|
.00
|
.00
|
1.00
|
-4.435
|
20.422
|
31.392
|
.829
|
-46.065
|
37.195
|
1.00
|
.00
|
4.435
|
20.422
|
31.392
|
.829
|
-37.195
|
46.065
|
1.00
|
.00
|
1.00
|
67.596*
|
21.119
|
32.151
|
.003
|
24.585
|
110.606
|
1.00
|
.00
|
-67.596*
|
21.119
|
32.151
|
.003
|
-110.606
|
-24.585
|
Based on estimated
marginal means
|
*. The mean
difference is significant at the .05 level.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
c. Adjustment for
multiple comparisons: Least Significant Difference (equivalent to no
adjustments).
|
|
Univariate Testsa
|
freq01
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
.00
|
1
|
31.392
|
.047
|
.829
|
1.00
|
1
|
32.151
|
10.244
|
.003
|
Each F tests the
simple effects of size01 within each level combination of the other effects
shown. These tests are based on the linearly independent pairwise
comparisons among the estimated marginal means.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
TITLE.
SUBTITLE.
TITLE "SPSS Dropping Random Item Intercept".
SPSS Dropping Random Item Intercept
MIXED rt BY Subject Item freq01 size01
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = freq01 size01 freq01*size01
/RANDOM = INTERCEPT | SUBJECT(Subject) COVTYPE(UN).
Mixed Model Analysis
Notes
|
Output Created
|
9-MAY-2014 11:15:26
|
Comments
|
|
Input
|
Data
|
C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
|
Active Dataset
|
Example4
|
Filter
|
<none>
|
Weight
|
<none>
|
Split File
|
<none>
|
N of Rows in Working
Data File
|
1392
|
Missing Value
Handling
|
Definition of
Missing
|
User-defined missing
values are treated as missing.
|
Cases Used
|
Statistics are based
on all cases with valid data for all variables in the model.
|
Syntax
|
MIXED rt BY Subject Item freq01 size01
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = freq01 size01 freq01*size01
/RANDOM = INTERCEPT | SUBJECT(Subject)
COVTYPE(UN).
|
Resources
|
Processor Time
|
00:00:00.02
|
Elapsed Time
|
00:00:00.08
|
|
[Example4] C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
Warnings
|
The covariance
structure for random effect with only one level will be changed to
Identity.
|
|
Model Dimensiona
|
|
Number of Levels
|
Covariance Structure
|
Number of Parameters
|
Subject Variables
|
Fixed Effects
|
Intercept
|
1
|
|
1
|
|
freq01
|
2
|
|
1
|
|
size01
|
2
|
|
1
|
|
freq01 * size01
|
4
|
|
1
|
|
Random Effects
|
Intercept
|
1
|
Identity
|
1
|
subject
|
Residual
|
|
|
1
|
|
Total
|
10
|
|
6
|
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Information Criteriaa
|
-2 Restricted Log
Likelihood
|
17466.439
|
Akaike's
Information Criterion (AIC)
|
17470.439
|
Hurvich
and Tsai's Criterion (AICC)
|
17470.447
|
Bozdogan's Criterion (CAIC)
|
17482.910
|
Schwarz's Bayesian
Criterion (BIC)
|
17480.910
|
The information
criteria are displayed in smaller-is-better forms.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Fixed Effects
Type III Tests of Fixed Effectsa
|
Source
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
Intercept
|
1
|
37.021
|
2713.236
|
.000
|
freq01
|
1
|
1351.312
|
20.218
|
.000
|
size01
|
1
|
1351.380
|
15.967
|
.000
|
freq01 * size01
|
1
|
1351.388
|
23.062
|
.000
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Estimates of Fixed Effectsa
|
Parameter
|
Estimate
|
Std. Error
|
df
|
t
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Intercept
|
618.003421
|
13.520869
|
56.829
|
45.707
|
.000
|
590.926583
|
645.080258
|
[freq01=.00]
|
2.063022
|
9.441030
|
1351.114
|
.219
|
.827
|
-16.457648
|
20.583693
|
[freq01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[size01=.00]
|
59.206965
|
9.763967
|
1351.547
|
6.064
|
.000
|
40.052788
|
78.361142
|
[size01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[freq01=.00] *
[size01=.00]
|
-64.634293
|
13.459164
|
1351.388
|
-4.802
|
.000
|
-91.037417
|
-38.231169
|
[freq01=.00] *
[size01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[freq01=1.00] *
[size01=.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
[freq01=1.00] *
[size01=1.00]
|
0b
|
0
|
.
|
.
|
.
|
.
|
.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
b. This parameter is
set to zero because it is redundant.
|
|
Covariance Parameters
Estimates of Covariance Parametersa
|
Parameter
|
Estimate
|
Std. Error
|
Wald Z
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Residual
|
15688.046349
|
603.608405
|
25.990
|
.000
|
14548.502640
|
16916.847345
|
Intercept [subject =
subject]
|
Variance
|
5171.988151
|
1302.293769
|
3.971
|
.000
|
3157.381696
|
8472.039178
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
|
|
|
|
|
|
|
|
TITLE.
TITLE "SPSS Random Slope for Effect of Freq over Subjects".
SPSS Random Slope for Effect of Freq over Subjects
SUBTITLE "Removed Freq and Size from BY statement to fit random slope".
SPSS Random Slope for Effect of Freq over Subjects
Removed Freq and Size from BY statement to fit random slope
MIXED rt BY Subject Item WITH freq01 size01
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = freq01 size01 freq01*size01
/RANDOM = INTERCEPT freq01 | SUBJECT(Subject) COVTYPE(UN)
/RANDOM = INTERCEPT | SUBJECT(Item) COVTYPE(UN).
Mixed Model Analysis
Notes
|
Output Created
|
9-MAY-2014 11:15:26
|
Comments
|
|
Input
|
Data
|
C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
|
Active Dataset
|
Example4
|
Filter
|
<none>
|
Weight
|
<none>
|
Split File
|
<none>
|
N of Rows in Working
Data File
|
1392
|
Missing Value
Handling
|
Definition of
Missing
|
User-defined missing
values are treated as missing.
|
Cases Used
|
Statistics are based
on all cases with valid data for all variables in the model.
|
Syntax
|
MIXED rt BY Subject Item WITH freq01 size01
/METHOD = REML
/PRINT = SOLUTION TESTCOV
/FIXED = freq01 size01 freq01*size01
/RANDOM = INTERCEPT freq01 | SUBJECT(Subject)
COVTYPE(UN)
/RANDOM = INTERCEPT | SUBJECT(Item) COVTYPE(UN).
|
Resources
|
Processor Time
|
00:00:00.37
|
Elapsed Time
|
00:00:01.37
|
|
[Example4] C:\Dropbox\14_Psyc930MLM\Download\SPSS\Example4.sav
Warnings
|
The covariance
structure for random effect with only one level will be changed to
Identity.
|
|
Model Dimensiona
|
|
Number of Levels
|
Covariance Structure
|
Number of Parameters
|
Subject Variables
|
Fixed Effects
|
Intercept
|
1
|
|
1
|
|
freq01
|
1
|
|
1
|
|
size01
|
1
|
|
1
|
|
freq01 * size01
|
1
|
|
1
|
|
Random Effects
|
Intercept + freq01b
|
2
|
Unstructured
|
3
|
subject
|
Interceptb
|
1
|
Identity
|
1
|
item
|
Residual
|
|
|
1
|
|
Total
|
7
|
|
9
|
|
a. Dependent
Variable: Response Time in Milliseconds.
|
b. As of version
11.5, the syntax rules for the RANDOM subcommand have changed. Your command
syntax may yield results that differ from those produced by prior versions.
If you are using version 11 syntax, please consult
the current syntax reference guide for more information.
|
|
Information Criteriaa
|
-2 Restricted Log
Likelihood
|
17397.573
|
Akaike's
Information Criterion (AIC)
|
17407.573
|
Hurvich
and Tsai's Criterion (AICC)
|
17407.616
|
Bozdogan's Criterion (CAIC)
|
17438.751
|
Schwarz's Bayesian
Criterion (BIC)
|
17433.751
|
The information
criteria are displayed in smaller-is-better forms.
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Fixed Effects
Type III Tests of Fixed Effectsa
|
Source
|
Numerator df
|
Denominator df
|
F
|
Sig.
|
Intercept
|
1
|
55.823
|
1178.579
|
.000
|
freq01
|
1
|
33.532
|
11.212
|
.002
|
size01
|
1
|
31.393
|
.047
|
.829
|
freq01 * size01
|
1
|
31.784
|
6.002
|
.020
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Estimates of Fixed Effectsa
|
Parameter
|
Estimate
|
Std. Error
|
df
|
t
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Intercept
|
615.849527
|
17.938879
|
55.823
|
34.330
|
.000
|
579.911115
|
651.787939
|
freq01
|
69.845213
|
20.859538
|
33.532
|
3.348
|
.002
|
27.431708
|
112.258718
|
size01
|
4.443322
|
20.447926
|
31.393
|
.217
|
.829
|
-37.239364
|
46.126009
|
freq01 * size01
|
-72.068788
|
29.416249
|
31.784
|
-2.450
|
.020
|
-132.003692
|
-12.133884
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
Covariance Parameters
Estimates of Covariance Parametersa
|
Parameter
|
Estimate
|
Std. Error
|
Wald Z
|
Sig.
|
95% Confidence Interval
|
Lower Bound
|
Upper Bound
|
Residual
|
14244.420795
|
563.573340
|
25.275
|
.000
|
13181.578916
|
15392.960515
|
Intercept + freq01
[subject = subject]
|
UN (1,1)
|
4266.009507
|
1163.641605
|
3.666
|
.000
|
2499.419402
|
7281.225833
|
UN (2,1)
|
872.281398
|
512.695308
|
1.701
|
.089
|
-132.582941
|
1877.145736
|
UN (2,2)
|
371.653931
|
447.450882
|
.831
|
.406
|
35.102570
|
3934.943948
|
Intercept [subject =
item]
|
Variance
|
1700.411356
|
528.092211
|
3.220
|
.001
|
925.121146
|
3125.427187
|
a. Dependent
Variable: Response Time in Milliseconds.
|
|
TITLE.
SUBTITLE.