In: Statistics and Probability
A sample of n=12 students were given a test to see how quickly they could solve a task, they were then given feedback and tested again. On average, students completed the task 75 seconds faster with a standard deviation of 20 seconds. Did the feedback help improve task completion in terms of how quickly the task was completed? *We're using t tests, so I'd assume a two sample t test.*
Solution:
Here, we have to use paired t test.
The null and alternative hypotheses for this test are given as below:
Null hypothesis: H0: The feedback does not help improve task completion in terms of how quickly the task was completed.
Alternative hypothesis: Ha: The feedback help improve task completion in terms of how quickly the task was completed.
H0: µd = 0 versus Ha: µd > 0
This is a right tailed test.
We consider difference as time before feedback minus time after feedback.
Test statistic for paired t test is given as below:
t = (Dbar - µd)/[Sd/sqrt(n)]
From given data, we have
Dbar = 75
Sd = 20
n = 12
df = n – 1 = 11
α = 0.05
t = (Dbar - µd)/[Sd/sqrt(n)]
t = (75 – 0)/[20/sqrt(12)]
t = 12.9904
The p-value by using t-table is given as below:
P-value = 0.0000
P-value < α = 0.05
So, we reject the null hypothesis
There is sufficient evidence to conclude that the feedback help improve task completion in terms of how quickly the task was completed.