It is important that the mean response from a manufacturing process be increased, but any change to the process is expensive to implement. A team listed some changes that they thought would be beneficial. They conducted a test with the current process settings and the new settings. They wanted to be certain that the change would be beneficial before implementing it. For this reason, they decided to keep the current process unless they could prove that the new process would be beneficial at a level of significance of 0.01. Discuss results and assess what should be done.
Current process readings: 98.1, 102.3, 98.5, 101.6, 97.7, 100.0, 103.1, 99.1, 97.7, 98.5
New process readings: 100.9, 101.1, 103.4, 85.0, 103.4, 103.6, 100.0, 99.7, 106.4, 101.2
Let us denote :
d = New process readings - Current process readings
To test
against
Here
sample mean of difference
sample standard deviation of difference
and sample size
The test statistic can be written as
which under H0 follows a t distribution with n-1 df.
We reject H0 at 0.05 level of significance if P-value < 0.05
Now,
The value of the test statistic =
P-value =
Since P-value > 0.05, so we fail to reject H0 at 0.05 level of significance and we can conclude that mean response has not increased significantly by the new process.
It is important that the mean response from a manufacturing process be increased, but any change...