GLM
  lfri cfri sfri  BY gender task
  /METHOD = SSTYPE(3)
  /INTERCEPT = INCLUDE
  /EMMEANS = TABLES(gender) COMPARE ADJ(LSD)
  /EMMEANS = TABLES(task) COMPARE ADJ(LSD)
  /EMMEANS = TABLES(gender*task) COMPARE(GENDER) ADJ(LSD)
  /CRITERIA = ALPHA(.05)
  /DESIGN = gender task gender*task .

General Linear Model

Notes
Output Created 30-OCT-2006 06:51:42
Comments
Input Data C:\Classes\00 Data Sets\ROLES.sav
Filter <none>
Weight <none>
Split File <none>
N of Rows in Working Data File 60
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 GLM
lfri cfri sfri BY gender task
/METHOD = SSTYPE(3)
/INTERCEPT = INCLUDE
/EMMEANS = TABLES(gender) COMPARE ADJ(LSD)
/EMMEANS = TABLES(task) COMPARE ADJ(LSD)
/EMMEANS = TABLES(gender*task) COMPARE(GENDER) ADJ(LSD)
/CRITERIA = ALPHA(.05)
/DESIGN = gender task gender*task .
Resources Elapsed Time 0:00:00.20

Between-Subjects Factors


N
gender 1.00 30
2.00 30
task 1.00 20
2.00 20
3.00 20

Multivariate Tests(c)
Effect
Value F Hypothesis df Error df Sig.
Intercept Pillai's Trace .948 313.910(a) 3.000 52.000 .000
Wilks' Lambda .052 313.910(a) 3.000 52.000 .000
Hotelling's Trace 18.110 313.910(a) 3.000 52.000 .000
Roy's Largest Root 18.110 313.910(a) 3.000 52.000 .000
gender Pillai's Trace .149 3.044(a) 3.000 52.000 .037
Wilks' Lambda .851 3.044(a) 3.000 52.000 .037
Hotelling's Trace .176 3.044(a) 3.000 52.000 .037
Roy's Largest Root .176 3.044(a) 3.000 52.000 .037
task Pillai's Trace .053 .484 6.000 106.000 .819
Wilks' Lambda .947 .481(a) 6.000 104.000 .821
Hotelling's Trace .056 .477 6.000 102.000 .824
Roy's Largest Root .054 .949(b) 3.000 53.000 .423
gender * task Pillai's Trace .150 1.437 6.000 106.000 .208
Wilks' Lambda .854 1.423(a) 6.000 104.000 .213
Hotelling's Trace .166 1.409 6.000 102.000 .218
Roy's Largest Root .124 2.190(b) 3.000 53.000 .100
a Exact statistic
b The statistic is an upper bound on F that yields a lower bound on the significance level.
c Design: Intercept+gender+task+gender * task

Tests of Between-Subjects Effects
Source Dependent Variable Type III Sum of Squares df Mean Square F Sig.
Corrected Model lfri 19.133(a) 5 3.827 1.062 .392
cfri 28.733(b) 5 5.747 1.767 .135
sfri 21.533(c) 5 4.307 1.516 .200
Intercept lfri 928.267 1 928.267 257.587 .000
cfri 881.667 1 881.667 271.128 .000
sfri 897.067 1 897.067 315.786 .000
gender lfri 1.067 1 1.067 .296 .589
cfri 13.067 1 13.067 4.018 .050
sfri 13.067 1 13.067 4.600 .036
task lfri 2.233 2 1.117 .310 .735
cfri 7.633 2 3.817 1.174 .317
sfri .833 2 .417 .147 .864
gender * task lfri 15.833 2 7.917 2.197 .121
cfri 8.033 2 4.017 1.235 .299
sfri 7.633 2 3.817 1.344 .269
Error lfri 194.600 54 3.604

cfri 175.600 54 3.252

sfri 153.400 54 2.841

Total lfri 1142.000 60


cfri 1086.000 60


sfri 1072.000 60


Corrected Total lfri 213.733 59


cfri 204.333 59


sfri 174.933 59


a R Squared = .090 (Adjusted R Squared = .005)
b R Squared = .141 (Adjusted R Squared = .061)
c R Squared = .123 (Adjusted R Squared = .042)

Estimated Marginal Means

1. gender

Estimates
Dependent Variable gender Mean Std. Error 95% Confidence Interval
Lower Bound Upper Bound
lfri 1.00 3.800 .347 3.105 4.495
2.00 4.067 .347 3.372 4.762
cfri 1.00 3.367 .329 2.707 4.027
2.00 4.300 .329 3.640 4.960
sfri 1.00 3.400 .308 2.783 4.017
2.00 4.333 .308 3.716 4.950

Pairwise Comparisons
Dependent Variable (I) gender (J) gender Mean Difference (I-J) Std. Error Sig.(a) 95% Confidence Interval for Difference(a)
Lower Bound Upper Bound
lfri 1.00 2.00 -.267 .490 .589 -1.249 .716
2.00 1.00 .267 .490 .589 -.716 1.249
cfri 1.00 2.00 -.933 .466 .050 -1.867 .000
2.00 1.00 .933 .466 .050 .000 1.867
sfri 1.00 2.00 -.933(*) .435 .036 -1.806 -.061
2.00 1.00 .933(*) .435 .036 .061 1.806
Based on estimated marginal means
* The mean difference is significant at the .05 level.
a Adjustment for multiple comparisons: Least Significant Difference (equivalent to no adjustments).

Multivariate Tests

Value F Hypothesis df Error df Sig.
Pillai's trace .149 3.044(a) 3.000 52.000 .037
Wilks' lambda .851 3.044(a) 3.000 52.000 .037
Hotelling's trace .176 3.044(a) 3.000 52.000 .037
Roy's largest root .176 3.044(a) 3.000 52.000 .037
Each F tests the multivariate effect of gender. These tests are based on the linearly independent pairwise comparisons among the estimated marginal means.
a Exact statistic

Univariate Tests
Dependent Variable
Sum of Squares df Mean Square F Sig.
lfri Contrast 1.067 1 1.067 .296 .589
Error 194.600 54 3.604

cfri Contrast 13.067 1 13.067 4.018 .050
Error 175.600 54 3.252

sfri Contrast 13.067 1 13.067 4.600 .036
Error 153.400 54 2.841

The F tests the effect of gender. This test is based on the linearly independent pairwise comparisons among the estimated marginal means.

2. task

Estimates
Dependent Variable task Mean Std. Error 95% Confidence Interval
Lower Bound Upper Bound
lfri 1.00 3.850 .424 2.999 4.701
2.00 4.200 .424 3.349 5.051
3.00 3.750 .424 2.899 4.601
cfri 1.00 4.200 .403 3.392 5.008
2.00 3.350 .403 2.542 4.158
3.00 3.950 .403 3.142 4.758
sfri 1.00 3.950 .377 3.194 4.706
2.00 3.700 .377 2.944 4.456
3.00 3.950 .377 3.194 4.706

Pairwise Comparisons
Dependent Variable (I) task (J) task Mean Difference (I-J) Std. Error Sig.(a) 95% Confidence Interval for Difference(a)
Lower Bound Upper Bound
lfri 1.00 2.00 -.350 .600 .562 -1.554 .854
3.00 .100 .600 .868 -1.104 1.304
2.00 1.00 .350 .600 .562 -.854 1.554
3.00 .450 .600 .457 -.754 1.654
3.00 1.00 -.100 .600 .868 -1.304 1.104
2.00 -.450 .600 .457 -1.654 .754
cfri 1.00 2.00 .850 .570 .142 -.293 1.993
3.00 .250 .570 .663 -.893 1.393
2.00 1.00 -.850 .570 .142 -1.993 .293
3.00 -.600 .570 .297 -1.743 .543
3.00 1.00 -.250 .570 .663 -1.393 .893
2.00 .600 .570 .297 -.543 1.743
sfri 1.00 2.00 .250 .533 .641 -.819 1.319
3.00 6.66E-016 .533 1.000 -1.069 1.069
2.00 1.00 -.250 .533 .641 -1.319 .819
3.00 -.250 .533 .641 -1.319 .819
3.00 1.00 -6.66E-016 .533 1.000 -1.069 1.069
2.00 .250 .533 .641 -.819 1.319
Based on estimated marginal means
a Adjustment for multiple comparisons: Least Significant Difference (equivalent to no adjustments).

Multivariate Tests

Value F Hypothesis df Error df Sig.
Pillai's trace .053 .484 6.000 106.000 .819
Wilks' lambda .947 .481(a) 6.000 104.000 .821
Hotelling's trace .056 .477 6.000 102.000 .824
Roy's largest root .054 .949(b) 3.000 53.000 .423
Each F tests the multivariate effect of task. These tests are based on the linearly independent pairwise comparisons among the estimated marginal means.
a Exact statistic
b The statistic is an upper bound on F that yields a lower bound on the significance level.

Univariate Tests
Dependent Variable
Sum of Squares df Mean Square F Sig.
lfri Contrast 2.233 2 1.117 .310 .735
Error 194.600 54 3.604

cfri Contrast 7.633 2 3.817 1.174 .317
Error 175.600 54 3.252

sfri Contrast .833 2 .417 .147 .864
Error 153.400 54 2.841

The F tests the effect of task. This test is based on the linearly independent pairwise comparisons among the estimated marginal means.

3. gender * task

Estimates
Dependent Variable gender task Mean Std. Error 95% Confidence Interval
Lower Bound Upper Bound
lfri 1.00 1.00 3.800 .600 2.596 5.004
2.00 3.400 .600 2.196 4.604
3.00 4.200 .600 2.996 5.404
2.00 1.00 3.900 .600 2.696 5.104
2.00 5.000 .600 3.796 6.204
3.00 3.300 .600 2.096 4.504
cfri 1.00 1.00 3.500 .570 2.357 4.643
2.00 3.400 .570 2.257 4.543
3.00 3.200 .570 2.057 4.343
2.00 1.00 4.900 .570 3.757 6.043
2.00 3.300 .570 2.157 4.443
3.00 4.700 .570 3.557 5.843
sfri 1.00 1.00 3.000 .533 1.931 4.069
2.00 3.600 .533 2.531 4.669
3.00 3.600 .533 2.531 4.669
2.00 1.00 4.900 .533 3.831 5.969
2.00 3.800 .533 2.731 4.869
3.00 4.300 .533 3.231 5.369

Pairwise Comparisons
Dependent Variable task (I) gender (J) gender Mean Difference (I-J) Std. Error Sig.(a) 95% Confidence Interval for Difference(a)
Lower Bound Upper Bound
lfri 1.00 1.00 2.00 -.100 .849 .907 -1.802 1.602
2.00 1.00 .100 .849 .907 -1.602 1.802
2.00 1.00 2.00 -1.600 .849 .065 -3.302 .102
2.00 1.00 1.600 .849 .065 -.102 3.302
3.00 1.00 2.00 .900 .849 .294 -.802 2.602
2.00 1.00 -.900 .849 .294 -2.602 .802
cfri 1.00 1.00 2.00 -1.400 .806 .088 -3.017 .217
2.00 1.00 1.400 .806 .088 -.217 3.017
2.00 1.00 2.00 .100 .806 .902 -1.517 1.717
2.00 1.00 -.100 .806 .902 -1.717 1.517
3.00 1.00 2.00 -1.500 .806 .068 -3.117 .117
2.00 1.00 1.500 .806 .068 -.117 3.117
sfri 1.00 1.00 2.00 -1.900(*) .754 .015 -3.411 -.389
2.00 1.00 1.900(*) .754 .015 .389 3.411
2.00 1.00 2.00 -.200 .754 .792 -1.711 1.311
2.00 1.00 .200 .754 .792 -1.311 1.711
3.00 1.00 2.00 -.700 .754 .357 -2.211 .811
2.00 1.00 .700 .754 .357 -.811 2.211
Based on estimated marginal means
* The mean difference is significant at the .05 level.
a Adjustment for multiple comparisons: Least Significant Difference (equivalent to no adjustments).

Multivariate Tests
task
Value F Hypothesis df Error df Sig.
1.00 Pillai's trace .151 3.082(a) 3.000 52.000 .035
Wilks' lambda .849 3.082(a) 3.000 52.000 .035
Hotelling's trace .178 3.082(a) 3.000 52.000 .035
Roy's largest root .178 3.082(a) 3.000 52.000 .035
2.00 Pillai's trace .067 1.246(a) 3.000 52.000 .303
Wilks' lambda .933 1.246(a) 3.000 52.000 .303
Hotelling's trace .072 1.246(a) 3.000 52.000 .303
Roy's largest root .072 1.246(a) 3.000 52.000 .303
3.00 Pillai's trace .084 1.588(a) 3.000 52.000 .203
Wilks' lambda .916 1.588(a) 3.000 52.000 .203
Hotelling's trace .092 1.588(a) 3.000 52.000 .203
Roy's largest root .092 1.588(a) 3.000 52.000 .203
Each F tests the multivariate simple effects of gender 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 Exact statistic

Univariate Tests
Dependent Variable task
Sum of Squares df Mean Square F Sig.
lfri 1.00 Contrast .050 1 .050 .014 .907
Error 194.600 54 3.604

2.00 Contrast 12.800 1 12.800 3.552 .065
Error 194.600 54 3.604

3.00 Contrast 4.050 1 4.050 1.124 .294
Error 194.600 54 3.604

cfri 1.00 Contrast 9.800 1 9.800 3.014 .088
Error 175.600 54 3.252

2.00 Contrast .050 1 .050 .015 .902
Error 175.600 54 3.252

3.00 Contrast 11.250 1 11.250 3.460 .068
Error 175.600 54 3.252

sfri 1.00 Contrast 18.050 1 18.050 6.354 .015
Error 153.400 54 2.841

2.00 Contrast .200 1 .200 .070 .792
Error 153.400 54 2.841

3.00 Contrast 2.450 1 2.450 .862 .357
Error 153.400 54 2.841

Each F tests the simple effects of gender within each level combination of the other effects shown. These tests are based on the linearly independent pairwise comparisons among the estimated marginal means.