Model Answers to 07 Hypothesis Testing in Six Sigma Statistics using Minitab 17, Green Belt Edition.
Conduct a 2 sample t Test
Analyse the data in File 07Hypothesis Testing.xlsx worksheet Ex 7.11.6 and answer the questions shown below. The data was collected randomly and is recorded in time order.
Is the sample data in columns Freq_A and Freq_B likely to have come from populations with differing means?
If the populations are different, which population mean is greater?
Have the requirements of the test that you have used been met?
What was the Power of the test when you want to detect a difference of 3?
Are there any issues associated with this level of Power ?
Does the Report Card generate any warnings?
1. Click Stat<<Assistant<< Hypothesis Test
2. Click on 2 Sample t Test
2. Complete the menu as shown and click OK to execute the procedure.
Starting from the top left of the Summary Report we cannot conclude that the sample data within columns Freq_A and Freq_B is likely to have come from different populations. There is insufficient evidence to reject the null hypothesis.
From the histograms under the Distribution of Data we can see that the 95% CI for the mean overlap.
The Diagnostic Report shows us that the control chart for Freq_A has one unusual data point. As this does not stand out we do not need to be concerned.
There is no evidence of bimodal distributions in either data set.
The Power Report shows us that under our test conditions we have a 91% chance of spotting a difference if one had existed. This is a good level of Power.
The Report Card does not show any warnings apart from the single data point that was deemed to be Unusual.