Professional Documents
Culture Documents
10 Anova
10 Anova
Assumption of Normality:
• Ho : Data follows normal distribution
• Ha : Data does not follow normal distribution
From SPSS (Shapiro-Wilks test)
• Memory drug : P-value = 0.978
• Placebo: P-value = 0.929
• No Treatment: P-value = 0.978
Conclusion: Since p-value is greater than α therefore we fails to reject Ho
and conclude that data follows normal distribution. Therefore we can
proceed to apply a Parametric Test i.e. One Way ANOVA
Outlier
– Box plots show that there is no outlier exist in the data sets
To Do One Way ANOVA
OUT PUT of One Way ANOVA
Step 2 - Descriptive Statistics
Groups N Mean Std. Deviation
Memory Drug 5 83.40 10.597
Placebo 5 50.00 10.440
No Treatment 5 16.60 10.597
Step 3 - Mean Plot
The mean plot shows that there is a negative
linear trend exist between the three groups (i.e.
as the students of no treatment there scores are
decreases.)
Step 4 - Checking for Variance Assumption (Homogeneity
of Variance)
Statement of Hypothesis:
– Ho: Population variances are equal
– H1: Population variances are not equal
Leven’s Test
– From SPSS: p value is 1.000.
Since p value is greater than the α level we fail to reject Ho
and conclude that the population variances are equal for all
groups and the homogeneity of variance assumption is
satisfied.
Steps for Hypothesis Testing in ANOVA
1. Set up the null and alternate (research) hypothesis
– Ho: All population means are equal
– H1: At least one mean is significantly different from the others
2. Level of Significance: α = 0.05
3. Run the appropriate statistical test
– One-way ANOVA (Between Subjects)
4. Critical Region: Reject Ho if P-value ≤ α = 0.05
5. Computation: Obtain the test statistic (F-test) & p-value
6. Conclusion: Decide whether to reject or fail to reject Ho
on the basis of the p value If the p value is very small
(<0.05), reject Ho and conclude that at least one sample
mean is significantly different to the other means
Step 5 - Hypothesis Testing Procedure for Means
1. Statement of Hypothesis:
– H1: At least one mean is different from the other
2. Level of Significance: α = 0.05
3. Choose Test: ONE WAY ANOVA / (F Test)
4. Critical Region: Reject Ho if P-value ≤ α = 0.05
5. Computation: P-value = 0.000 which is write as P-value
<0.001
6. Conclusion: Since P-value is less than α therefore we
reject Ho and there is a sufficient evidence to
conclude that mean scores are significantly different
from the other.
Now which pair of group mean scores are different? We
will apply Post Hoc / Multiple Comparison Test.
One Way ANOVA- post-hoc test
• It is important to realize that the one-way ANOVA
cannot tell you which specific groups were
significantly different from each other; it only
tells you that at least two groups were different.
• Since you may have three, four, five or more
groups in your study design, determining which
of these groups differ from each other is
important. You can do this using a post-hoc test
Commonly Use Post Hoc Tests
• Equal Variances Assumed Test
• For Equal Sample Size:
– Tukey (Priority)
– LSD
• For Equal & Unequal Sample Size:
– LSD
• For Comparison with a Control:
– Dunnett’s Test
• Equal Variances Not Assumed Test
– Games-Howell (Equal/Unequal Sample Size)
Be like the mango tree. Always provide
fruit in spite of evil’s eye