In: Math
A statistics instructor wonders whether significant differences exist in her students’ final exam scores in her three different sections. She randomly selects the scores from 10 students in each section. A portion of the data is shown in the accompanying table. Assume exam scores are normally distributed.
Section 1 | Section 2 | Section 3 |
82 | 50 | 72 |
76 | 51 | 79 |
63 | 59 | 96 |
90 | 76 | 86 |
61 | 74 | 54 |
79 | 50 | 86 |
56 | 73 | 78 |
59 | 63 | 83 |
79 | 84 | 95 |
89 | 78 | 95 |
Construct an ANOVA table. (Round "Sum Sq" and "Mean Sq" to 1 decimal place, "F value" to 3, and "p-value" to 3 decimal places. Before fitting your model, type options(scipen=10) and options(digits=10) into your R console.)
ANOVA | |||||
Source of Variation | Df | Sum Sq | Mean Sq | F value | Pr(>F) |
Section | |||||
Residuals |
Solution:
We can use R to find the ANOVA values. The R code and output is given below:
R-Code:
options(scipen=10)
options(digits=10)
Section_1 <-c(82,76,63,90,61,79,56,59,79,89)
Section_2 <-c(50,51,59,76,74,50,73,63,84,78)
Section_3 <-c(72,79,96,86,54,86,78,83,95,95)
combined_groups<-data.frame(cbind(Section_1,Section_2,Section_3))
stacked_groups<-stack(combined_groups)
Anova_Results<-aov(values ~ind, data=stacked_groups)
summary(Anova_Results)
The R-output is given below:
Therefore, the ANOVA table is: