Part 2F: Check your understanding: Creating Graphs

Use the above Racer App2 to check your understanding

Name (if more than one name, separate each name with a comma)

Instructor's Email Address

Enter the PlayerID you used to play the game


A. Using the suggested settings for the app, determine how many players are shown with the Group ID = sample2?
12 15 18 21 24
B. Change the X Variable to Player ID. Identify the two players that have times that could be considered outliers.

a and c c and d d and k c and k
C. After removing two Player IDs that reflect potential outliers, conduct a two-sample hypothesis test to determine if there is a difference between the mean Finish Time of the two cars. What is the p-value?

0.0999 0.0425 0.4294 0.7312
D. After removing two Player IDs that reflect potential outliers, conduct a paired t-test to determine if there is a difference between then mean Finish Time of the two cars. What is the p-value? For paired tests, the Clean Data must be checked, then Player IDs can be removed.

0.0999 0.0425 0.4294 0.7312
E. Based on the previous hypothesis tests, what can you conclude? Check all that apply.

We do not have enough evidence to conclude that there is a difference in the mean Finish Times. We have evidence that the mean Finish Times of the two cars are the same. There is evidence to support a difference between the mean Finish Times of the two cars. A paired test is the most appropriate for this analysis. A two sample t-test is most appropriate or this analysis. None of the above.
F. Is it more appropriate to remove the two Player IDs with high Finish Times before conducting a hypothesis test? Check all appropriate answers.

The smaller dataset should be used because it gives a smaller p-value. The full dataset should be used because it gives a smaller p-value. Either dataset can be used as long as the data cleaning process is transparent to all who are asked to interpret the p-value. Both p-values could be reported so the readers can see the results of the data cleaning. We should typically try to clean our data in a way that gives us a small p-value. While it is typically possible to clean our data to get a small p-value, the focus should always be on getting meaningful data that accurately represents the population.