Sei sulla pagina 1di 5

MANOVA

A Multivariate Analysis of Variance (MANOVA) is often used as a multivariate


analog of the ANOVA, but when there are multiple dependent variables. (Note
that an ANOVA can handle multiple independent variables, but only one
dependent variable at a time.) I will have much to say in lecture about the
limited appropriateness of MANOVA, however you should know of its existence
since it is used often. These are the SPSS instructions and an example of a
simple MANOVA.
For a simple oneway MANOVA, the data set should have one independent
variable (grouping variable) and at least two dependent variables. In the
example herein I use gender as the IV and the GRE verbal and quantitative
(grev and greq) scores as DVs. The data set used herein (DESC.sav) is included
in this MANOVA folder.
Click Analyze/General Linear Model/Multivariate. Place the dependent
variables in the box labeled such and the independent variable in the "Fixed
Factors" box. Open "Options" and check the boxes as denoted in the screen shot
showing all of this below.

Click "Continue" in the Options window and "OK" in the "Multivariate" window
and your job will run. The output for this run is:

General Linear Model


Between-Subjects Factors
Value Label
GENDER

1.00

female

2.00

male

N
193
45

Descriptive Statistics
GENDER

GRE- VERBAL

GRE-QUANTITATIVE

Mean

Std. Deviation

female

493.8860

90.35767

193

male

470.8889

93.07432

45

Total

489.5378

91.12631

238

female

485.1813

95.87912

193

male

525.7778

118.92490

45

Total

492.8571

101.62098

238

Box's Test of Equality of Covariance Matrices(a)


Box's M

3.722

1.219

df1

df2

86913.177

Sig.

.301

Tests the null hypothesis that the observed covariance matrices of the dependent variables are equal across
groups.
a Design: Intercept+GENDER
Multivariate Tests(c)
Effect

Value

Intercept Pillai's
Trace
Wilks'
Lambda

.959

F
2771.204(b
)

.041 2771.204(b
)

Hypothesis
df

Error
df

2.000 235.000
2.000 235.000

Sig.

Partial
Eta
Squared

Noncent.
Parameter

Observed
Power(a)

.
000

.959

5542.409

1.000

.959

5542.409

1.000

.
000

GENDE
R

Hotelling's
Trace

23.58 2771.204(b
5
)

2.000 235.000

.
000

.959

5542.409

1.000

Roy's
Largest
Root

23.58 2771.204(b
5
)

2.000 235.000

.
000

.959

5542.409

1.000

Pillai's
Trace

.054

6.707(b)

2.000 235.000

.
001

.054

13.415

.913

Wilks'
Lambda

.946

6.707(b)

2.000 235.000

.
001

.054

13.415

.913

Hotelling's
Trace

.057

6.707(b)

2.000 235.000

.
001

.054

13.415

.913

Roy's
Largest
Root

.057

6.707(b)

2.000 235.000

.
001

.054

13.415

.913

a Computed using alpha = .05


b Exact statistic
c Design: Intercept+GENDER
Levene's Test of Equality of Error Variances(a)
F

df1

GRE- VERBAL
GRE-QUANTITATIVE

df2

Sig.

.001

236

.976

3.443

236

.065

Tests the null hypothesis that the error variance of the dependent variable is equal across groups.
a Design: Intercept+GENDER
Tests of Between-Subjects Effects

Source

Dependent
Variable

Type III
Sum of
Squares

df

Mean
Square

Partial
Observe
Noncent.
Eta
d
Sig.
Paramete
Square
Power(a
r
d
)

19299.223(b
)

19299.223

2.337

.
128

.010

2.337

.331

60140.712(c
)

60140.712

5.945

.
015

.025

5.945

.680

GRE- VERBAL

33966035.35
7

33966035.35 4113.39
.
7
8 000

.946

4113.398

1.000

Intercept GREQUANTITATIV
E

37295811.30
0

37295811.30 3686.90
.
0
6 000

.940

3686.906

1.000

GRE- VERBAL

19299.223

19299.223

2.337

.
128

.010

2.337

.331

GREQUANTITATIV

60140.712

60140.712

5.945

.025

5.945

.680

GRE- VERBAL
Correcte
d Model GREQUANTITATIV
E

GENDE
R

.
015

E
GRE- VERBAL

1948749.937

23
6

8257.415

GREQUANTITATIV
E

2387316.431

23
6

10115.748

GRE- VERBAL

59004100.00
0

23
8

GREQUANTITATIV
E

60259600.00
0

23
8

GRE- VERBAL

1968049.160

Correcte
GREd Total
QUANTITATIV
E

23
7

2447457.143

23
7

Error

Total

a Computed using alpha = .05


b R Squared = .010 (Adjusted R Squared = .006)
c R Squared = .025 (Adjusted R Squared = .020)

Interpretation
An assumption of the MANOVA is that the covariance matrices of the dependent
variables are the same across groups (determined by levels of the independent
variable) in the population. This is the multivariate analog of the assumption of
equal variances for the ANOVA. Box's M tests that assumption. In the case at
hand the p value of .301 suggests that the hypothesis of equal covariance
matrices can not be rejected. So we have not violated an assumption of
MANOVA, and may feel confident in continuing (at least in respect to this
assumption).
The Multivariate Tests (Pillai's, Wilks', Hotelling's, and Roy's) all test the
MANOVA null hypothesis -- that the mean on the composite variable is the same
across groups. In the multivariate case, these tests can, in general, provide
different results. In our present simple example contrasting across two groups,
they are necessarily the same. Thus we find the multivariate hypothesis that the
mean on the composite is the same across groups rejected. Remember that this
is a test of the equality of a composite of the means (optimized to yield the
maximum possible F-ratio) across groups.
Almost all MANOVA programs provide univariate tests for each of the
dependent variables used in the MANOVA. This is probably done for a bad
reason, as the practice has been to only pursue univariate tests if the multivariate
test is significant (in an incorrect attempt to protect against a Type I error).

For this reason, we have the standard Levene's test of the assumption of equal
variances for each of our dependent variables as this is an assumption of the
ANOVA. For both grev and greq, the test produces an nonsignificant p value,
so the null hypotheses regarding equal variances can not be rejected for either
dependent variable, thus ANOVA is fine.
We can, however, consider these univariate tests if we wish (although we should
realize that they are not directly related to the multivariate test), as long as we
treat the error rate appropriately. A simple (although not necessarily optimal)
way to adjust the error rate is to use the Bonferroni inequality, thus we test each
of our two null hypotheses regarding each of our two dependent variables at the
/2 level. For the sake of demonstration, let =.05, thus the adjusted error rate is
.025. We see (under the Tests of Between-Subjects Effects") that, using this
modified , the null hypothesis regarding greq would be rejected (and looking at
the means we see that the males were superior), but that the null for grev would
not be rejected.

Potrebbero piacerti anche