First the given data was input into vectors pa and pb
pa <- c(15,26,13,28,17,20,7,36,12,18) # sample A
pb <- c(13,20,10,21,17,22,5,30,7,11) # sample B
The null hypothesis is that the means are the same. The alternative is that there is a diffrence in the means. Thus this is a two sided T-test. \[H_o:\mu_1=\mu_2 \\ H_a:\mu_1\neq \mu_2 \]
A paired T-test is done
t.test(pa,pb,paired= T)
##
## Paired t-test
##
## data: pa and pb
## t = 3.6742, df = 9, p-value = 0.005121
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## 1.383548 5.816452
## sample estimates:
## mean difference
## 3.6
The P-value from paired T-test is 0.005121 thus the null is rejected!
For a two sample T-test,
t.test(pa,pb)
##
## Welch Two Sample t-test
##
## data: pa and pb
## t = 0.9802, df = 17.811, p-value = 0.3401
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -4.12199 11.32199
## sample estimates:
## mean of x mean of y
## 19.2 15.6
From the two sample T-test the P-value is 0.3401 thus the null hypothesis would not be rejected.
We want to test:
\[H_o:\mu_1=\mu_2 \\ H_a:\mu_1\neq \mu_2 \] where \(\mu_1\) is the mean of infants for active exercise and \(\mu_2\) is the mean of infants for no exercise group.
#Creating the data
grp1 <- c(9.5,10,9.75,9.75,9,13)
grp2 <- c(11.5,12,13.25,11.50,13,9)
#Checking for normality
qqnorm(grp1)
qqline(grp1)
qqnorm(grp2)
qqline(grp2)
We will use a non parametric method because the data does not looks normal and we do not have enough data points.
#Performing the test
wilcox.test(grp1,grp2)
##
## Wilcoxon rank sum test with continuity correction
##
## data: grp1 and grp2
## W = 9, p-value = 0.1705
## alternative hypothesis: true location shift is not equal to 0
We failed to reject the null hypotheses based on the Mann-Whitney test with a p-value of 0.1705.
pa <- c(15,26,13,28,17,20,7,36,12,18) # sample A
pb <- c(13,20,10,21,17,22,5,30,7,11) # sample B
t.test(pa,pb,paired= T)
t.test(pa,pb)
grp1 <- c(9.5,10,9.75,9.75,9,13)
grp2 <- c(11.5,12,13.25,11.50,13,9)
qqnorm(grp1)
qqline(grp1)
qqnorm(grp2)
qqline(grp2)
wilcox.test(grp1,grp2)