Question

A researcher believes that alcohol intoxication might severely impair driving ability. To test this, she subjects 10 volunteers to a driving simulation test, first when sober, and then, after drinking amounts sufficient to raise their blood alcohol to .04. The researcher measures performance as the number of simulated obstacles with which the driver collides. Thus, the higher the number, the poorer the driving. The data is in the Excel file in the tab labeled Question 4. Test whether there are differences before and after drinking. Conduct a t-test: Two-Sample for Means.

Before Drinking:

1
2
0
0
2
1
4
0
1
2
0

After drinking:

4
2
1
2
5
3
3
2
4
3
1

a. What is the null hypothesis?

b. What is the research hypothesis?

c. Why run a Two-Sample for Means t-test?

d. Interpret the findings. What are the results of the hypothesis test? Can you reject the null hypothesis?

Answer 1

One should use a two sample paired t test in this case.

Let us denote

d = before drinking - after drinking