Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
MANOVS.pptx
1. 1
MANOVA BY GROUP 3
Multivariate Analysis of Variance (MANOVA)
BY GROUP 3 MEMBERS
Tefera Bala
Nebiyou Simegnew
Sheka Shemsi
Mohammed
Mohamed Oumer
Nafkot Berhanu
2. 2
MANOVA BY GROUP 3
outlines
1
2
3
4
What is MANOVA?
When Should MANOVA Is Used?
.
What are the assumptions to be Fulfilled in MANOVA ?
How to Conduct MANOVA Analysis?
3. 3
MANOVA BY GROUP 3
At the end of this presentation you will be able to:
Define MANOVA
List types of MANOVA
List the assumptions of MANOVA
Conduct the MANOVA analysis
Objective of presentation
4. 4
MANOVA BY GROUP 3
What is MANOVA?
MANOVA is an extension of the ANOVA
ANOVA deals with only ONE Dependent Variable.
MANOVA accounts for multiple Dependent variable at once.
MANOVA is statistical method for testing if there are mean differences across groups on
multiple DVs.
Tests the hypothesis that one or more independent variables, have an effect on a set of
two or more dependent variables
Similar to ANOVAs, there are between and within subjects in MANOVAs
5. 5
MANOVA BY GROUP 3
We do a MANOVA instead of a series of one-at-a-time ANOVAs for two main
reasons:
To reduce the experiment-wise level of Type I error (rejecting the null hypothesis
when it is in fact true) -protects against this inflated error probability only when
the null hypothesis is true.
None of the individual ANOVAs may produce a significant main effect on the DV, but
in combination they might, which suggests that the variables are more meaningful
taken together than considered separately.
MANOVA takes into account the intercorrelations among the DVs.
Why Should We Do a MANOVA?
6. 6
MANOVA BY GROUP 3
TYPES OF MANOVA
ONE-WAY MANOVA
TWO-WAY MANOVA
One categorical IDVs
Continuous DV
Categorical IDV
Continuous DV
Continuous DV
Categorical IDV continuous DV
effects
effects
effects
7. 7
MANOVA BY GROUP 3
Assumptions to be fulfilled in Manova
1. Normality (Shapiro Wilk)
2. Univariate Outliers (Boxplots)
3. Multivariate Outliers (Mahalanobis Distances)
4. Multicollinearity (Correlation)
5. Linearity (Scatterplot)
6. Homogeneity of variance-covariance matrices (Box’s M)
7. Independency of observation
8. 8
MANOVA BY GROUP 3
ONE WAY MANOVA
Eg: If someone is interested to know the effects of exercise on SBP and FBS
among individual who have both HTN and DM.
The exercise program are 15 minutes, 30 minutes and 45 minutes combined
with routine treatment.
The patients will be randomly assigned to each of 3 exercise programs and then
test will be performed to see if there are mean differences across 3 groups on
SBP and FBS.
If there are 21 patients, for each 3-exercise program pts will 7 be randomly
assigned.
At the end of exercise intervention, the pt’s SBP & FBS will be measure to see if
there are mean differences across the three exercise groups.
1 IDV with 3 category 2 Continuous DV
9. 9
MANOVA BY GROUP 3
Normality test
normally distributed
MANOVA is generally robust to a
moderate violation of normality
10. 10
MANOVA BY GROUP 3
Univariate Outliers (Boxplots)
Not univariate outliers
11. 11
MANOVA BY GROUP 3
This assumption can be tested via the Mahalanobis Distances
Analyze -> Regression -> Linear
Multivariate Outliers
Move ‘SBP’ and ‘FBS’ to the Independent(s) box, and ‘EXERCISE’ to the Dependent
box
12. 12
MANOVA BY GROUP 3
Multivariate Outliers
Under Residuals Statistics, Maximum Malal.
Distance = 5.466
This value is smaller than the chi-square
value at df = 2, α = .05, which is 5.99
*Refer to a the critical value in the Chi-Square table; df =
number of DVs
This indicates no multivariate outlier
13. 13
MANOVA BY GROUP 3
The assumption of multicollinearity can be checked via a correlation
analysis
• Go to Analyze -> Correlate -> Bivariate
Multicollinearity
In the Correlations table, two DVs are not correlated, r = -.285 (p:0.21)
Therefore, no violation of multicollinearity
14. 14
MANOVA BY GROUP 3
This assumption can be tested using scatterplots
Graphs -> Legacy Dialogs -> Scatter/Dot -> Simple Scatter -> Define
linearity
If the lines are roughly straight, we conclude
that the assumption of linearity is satisfied
15. 15
MANOVA BY GROUP 3
• Analyze -> General Linear Model -> Multivariate
Homogeneity of variance-covariance matrices
In order to satisfy this assumption, the Box’s M value should be non-significant at α = .001
A significant value of .061 indicates that the assumption has not been violated
16. 16
MANOVA BY GROUP 3
• Analyze -> General Linear Model -> Multivariate
How to conduct MANOVA Analysis on SPSS?
Looking at Wilk’s lambda, F(2,34) = 13.534, p < .001.
There is a statistically significant difference in SBP and FBS
across types of Exercise.
17. 17
MANOVA BY GROUP 3
To investigate the effects of each DV, look at the Tests of
Between-Subjects Effects table
There is a main effect of exercise (15 or 30 or 45 min) on SBS, p
< .001, but not FBS, p = .180
To investigate which level of the IV significantly affected
the DV? Conduct Post Hoc Comparison
Analyse -> General linear model -> Multivariate -> Post-Hoc -
TUKEY
18. 18
MANOVA BY GROUP 3
• MANOVA yields more reliable level of type I error than ANOVA
• MANOVA is statistically more efficient than ANOVA
However, there are some disadvantages of MANOVA
• Complex design, ambiguous analytic results subjected to personal
assumptions.
• One degree of freedom is lost for each additional DV
• Assumption about normality is violated in the presence of outliers.
MANOVA Vs ANOVA
Univariate and multivariate analysis of variance (ANOVA and MANOVA), as well as analysis of covariance (ANCOVA) form cornerstones of applied statistics
A covariate is a variable that is related to the DV, which you can’t manipulate, but you want to removes its (their) relationship from the DV before assessing differences on the IVs.
.
8 F tests at .05 each means the experiment-wise probability of making a Type I error (rejecting the null hypothesis when it is in fact true) is 40%!
A test that mixes both between AND within IVs is called mixed MANOVA
Under Options, select Homogeneity tests
Continue, and OK
This can be done by going to
-> Analyse -> General linear model -> Multivariate -> Post-Hoc -> Moving the IV to ‘Post Hoc Tests for:’ -> Selecting a preferred post hoc test (common test is Tukey)