Question 2

A group of researchers wish to learn whether online safety training is as effective as in-person training. The researchers randomly assigned a group of 20 workers to two groups, and had one group complete online training and the other complete in-person training. The same post-quiz was given to both groups.

The researchers are testing whether the delivery of the training material may be a factor in ability of the student to correctly answer the questions on the post-quiz. Their hypothesis is: The mean grade of those completing the online training is different than the mean grade of those completing the in-person training.

A t-test can be used to test the probability that the two means do not differ. The alternative is that the means differ. Post-quiz grades from both groups are as follows:

Group A - Online	Group B - In Person
83	73
78	81
75	72
68	67
70	98
62	66
89	74
95	79
72	60
97	97

This is a two-tailed test because the researcher is interested in whether delivery mode affects grades.

1. Describe your statistical results in narrative (sentence)
2. Interpret the results of each statistically analysis (do you reject the null; do you accept the null?). Explain in lay terms what rejecting/accepting the null means in your case.
3. Look at the means of each group. Is this what you expected the outcome to be?
4. What are some limitations of using the outcome of these test results? What might some additional variables be that weren't accounted for? Is this sample size powerful enough to make a determination about the larger population?