Some researchers (see, for example, Cassidy and Jones, 2001) have suggested that blood pressure may tend to be higher on average when measured on a subject's right arm than on their left arm. A doctor decided to investigate this conjecture by taking readings of the systolic blood pressure on both arms of a random selection of twelve patients at his practice. Suppose the data gathered, in mm Hg, are as given below:



Cassidy, P. and Jones, K. (2001): A study of inter-arm blood pressure differences in primary care. J. Hum. Hypertens. 15, 519-522.

Part a)
In order to explore the variable of interest here, which graphical method would be best?

A. A boxplot of the within-patient differences.
B. A bar chart.
C. A scatter plot of the left arm blood pressure against the right arm blood pressure.
D. Two histograms plotted on the same axis, one for the left arm data and one for the right arm data.
E. Side-by-side boxplots of the left and right arm blood pressures.


Part b)
If performing a hypothesis test of interest here using the above data, which of the following would be most useful?

A. Signed rank test
B. Two-sample t-test
C. Rank sum test
D. Kruskal-Wallis test


Part c) In conducting a hypothesis test here, would the doctor take a one-sided or two-sided alternative hypothesis?

A. Two-sided
B. One-sided


Part d)
Perform your test in R or R Cmdr. Provide the P-value of your test to 3 decimal places.


Part e)
Would you reject or not reject your null hypothesis at the 5% significance level?

A. Not reject
B. Reject