In: Statistics and Probability
College students were asked to rate the spring festivals at
university in years 2016, 2017, and 2018. The following table shows
the students’ ratings on a scale from 0 to 100 where larger values
are assigned to better activities. Construct an ANOVA table and
determine whether there is a significant difference among the student
appreciation of spring festivals for different years. Assume a
significance level of α = 0.05.
2016 | 2017 | 2018 |
72 | 93 | 87 |
58 | 70 | 70 |
71 | 76 | 90 |
56 | 69 | 85 |
45 | 86 | 76 |
73 | 65 | 94 |
68 | 70 | 85 |
Hypothesis:
H0: The mean rating for the three years is the same.
H1: The mean rating for the three years is not the same.
Let ratings of 2016 be represented by Group A =((72, 58, 71, 56, 45, 73, 68))
Let ratings of 2017 be represented by Group B = (93, 70, 76, 69, 86, 65, 70)
Let ratings of 2018 be represented by Group C= (87, 70, 90, 85, 76, 94, 85)
(g represents grand total)
We find the mean of both groups and the the entire data
No of observation in each group
no. of groups = k = 3
Next we find the difference between each observation in the group with mean of the group and square it up.
example In group A we take the first observation and minus it the group mean (72-63.28)^2,this is done for each observation and for every group and summed up
Sum of square within the groups
Mean sum of square within the groups
Sum of square between the groups
Mean sum of square between the groups
Using the F table we find pvalue with df1 = 2 and df2=18
pvalue = 0.00340
Since the pvalue is less than 0.05, we reject the null hypothesis and conclude that the mean rating for the three years is not the same.