ANOVA 2 Omkumar
ANOVA 2 Omkumar
I have selected the file bankloan_cs.sav to perform an ANOVA test to compare the
means of household income across the different bank branches. But first, the data
needs to check and cleared of outliers. After that I will check assumptions of ANOVA
test and after that I will perform The ANOVA test.
House ho T d Income tn thousands
15
25
572
Branch
75
For this data set, we know that it is simple random so assumption 1 is met. We know that the
samples are independent from each other as the household income of branch 3 will have no
effect on the household income of branch 13 and etc. The 2 remaining assumptions are normal
populations and equal standard deviations which we will check.
Normal Q-Q Plot of Household income in thousands
for branch= 3
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 13
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 15
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 20
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 25
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 49
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 60
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 64
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 68
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 73
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 74
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 75
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 76
E
o
Observed Value
Normal Q-Q Plot of Household income in thousands
for branch= 77
E
o
Observed Value
All the above normal QQ plot diagrams shows that the data for each branch is approximately
normally distributed. Since the test is robust against violations of normality, we can carry out and
perform the ANOVA test now.
null hypothesis: average household income across all the bank branches are the same.
alternative hypothesis: average household income across all the bank branches are not
the same
N Mean Std. Deviation Std. Error 95% Confidence Interval for Mean Minimum Maximum
Lower Bound Upper Bound
The table above shows the test results of some descriptive. We have in total 15 bank branches
and 1290 observations. The mean column shows the average income of household for different
branches.
3.
ANOVA
Household income in thousands
Sum of Squares df Mean Square F Sig.
4. The above is the ANOVA table. The calculated F-statistic is 1.557 with a df = (14,1275) and
the P-value is 0.085.
5. Using the p-value approach, the calculated p value is greater than 0.05
6. At the 5% significance level, we accept the null hypothesis and conclude that the average
household income across the 15 bank branches are the same.