Interpreting the MANOVA
General Linear Model: RSA, MBP versus SupportCondition
Factor Type Levels Values SupportCondition fixed 3 Emotional, Instrumental, NoSupport
Analysis of Variance for RSA, using Adjusted SS for Tests
Source DF SeqSS AdjSS AdjMS F P SupportCondition 2 55.690 55.690 27.845 11.75 0.000 Error 92 218.081 218.081 2.370 Total 94 273.771
S = 1.53962 R-Sq = 20.34% R-Sq(adj) = 18.61%
Unusual Observations for RSA
Obs RSA Fit SE Fit Residual St Resid
1 3.78335 0.74639 0.27217 3.03695 94 5.81241 0.74639 0.27217 5.06602 95 9.81021 0.74639 0.27217 9.06382
2.00 R 3.34 R 5.98 R
R denotes an observation with a large standardized residual.
Analysis of Variance for MBP, using Adjusted SS for Tests
Source DF SeqSS AdjSS AdjMS F P SupportCondition 2 84880 84880 42440 1.85 0.162 Error 92 2105869 2105869 22890 Total 94 2190750
S = 151.294 R-Sq = 3.87% R-Sq(adj) = 1.78%
Unusual Observations for MBP
Obs MBP Fit SEFit Residual StResid
11 669.531 66.932 26.745 602.599 64 -451.159 -3.683 27.622 -447.476 87 300.000 -3.683 27.622 303.683
4.05 R -3.01 R 2.04 R
R denotes an observation with a large standardized residual.
MANOVA for SupportCondition
s=2 m=-0.5 n=44.5
Test DF Criterion Statistic F Num Denom P
Wilks' 0.76190 6.627 4 182 0.000 Lawley-Hotelling 0.30482 6.859 4 180 0.000
Pillai's 0.24396 6.391 4 184 0.000 Roy's 0.27708
Post-hoc Test: Grouping Information Using Tukey Method and 95.0% Confidence for MBP SupportCondition N Mean Grouping
Emotional NoSupport Instrumental
32 66.932 A 33 51.635 A 30 -3.683 A
Means that do not share a letter are significantly different.
Grouping Information Using Tukey Method and 95.0% Confidence for RSA
SupportCondition N Mean Grouping Emotional 32 0.746 A Instrumental 30 -0.662 B NoSupport 33 -1.012 B
Means that do not share a letter are significantly different.