Minitab Notes for Activity 5

Constructing a Confidence Interval for a Proportion (Question 5)

Go to Stat / Basic Statistics / 1 Proportion
Click on the Summarized data radio button
Enter 50 for the number of trials
Enter the number of strawberry (pink wrapper) candies that you found in your bag for the number of successes.
Click on Options.
1. Make sure the confidence level is set to 95 (for 95%)
2. Check the box for "Use test and interval based on normal distribution"
3. Click OK
Click OK

Note that the confidence interval will appear as ( #### , #### ) where there ####'s are the lower and upper limits of the interval. These are given as proportions (decimals) not percents. If you convert them to percents, be sure to write the % sign after them. If the computer says (0.3215,0.6521), then write it on your paper as "0.3215 < p < 0.6521" or "32.15% < p < 65.21%".

Hypothesis Test (Question 8)

The place to test the hypothesis that 35% of the candies are strawberry is from the same procedure we just used to find the confidence interval. The only differences are in the Options screen.

We want to test a proportion of 0.35 (35%), not 0.5 (50%), so change that. Also, for this part of the question, we want the Alternative to be "not equal" (which is should be), but we will change that later.

Completing the Sentences (Question 8c)

The probability value (p-value) is the chance of getting the results we obtained if the null hypothesis is true. For our data, that means the chance of getting your results if the true percentage of strawberry candies is 35%. Some of the sentences will require you to re-run the hypothesis test after changing the alternative hypothesis under Options.

Here are some guidelines to help you answer the sentences.

Look at the claim in the conclusion and determine whether it is the null hypothesis or the alternative hypothesis.
- The null hypothesis is the assumed or normal condition, a statement of no change. It contains the equal sign when written symbolically.
- The alternative hypothesis is a changed from the assumed or normal condition. It never contains the equal sign when written symbolically.
If your alternative hypothesis is a less than or a greater than, be sure to go into the Options screen and change it appropriately. The p-values aren't the same for all four sentences.
Look at the p-value to determine whether or not there is enough evidence.
- You only have enough evidence when the p-value is small and the results are unusual. This means that there is enough evidence. There may be enough evidence to support the alternative hypothesis or to reject the null hypothesis, but there is enough evidence.
- When the p-value is large, your results have a pretty good chance of happening by random fluctuations alone and so there is not enough evidence to do anything. You won't be able to support the alternative hypothesis or reject the null hypothesis.
You only support the alternative hypothesis, never the null hypothesis. You can only reject the null hypothesis, never support it. Now, it's possible that there may not be enough evidence to reject the null hypothesis, but that's not the same as supporting it. Your book uses the word "retain" for this situation, but that's not an option on the activity sheet, so don't use it here.