1. In the East Mequon Clinic of Aurora Advanced Healthcare in Mequon, WI, the number of males and females represented in the nursing and physician professions was recorded and the following data obtained:
Nursing Profession Physician Profession
Males Females Males Females
3 17 13 5
Run a chi-square analysis on each of these professions to determine if the numbers represent a statistical deviation from an expected equal number of males and females (total subjects divided by two!) in each profession.
a) p value for nursing profession:
b) Null hypothesis decision (accept or reject):
c) p value for physician profession:
d) Null hypothesis decision (accept or reject):
2. Over the past year, the following percentages reflect length of hospital stay for all inpatients at Columbia St. Mary’s Hospital in Mequon, WI:
Less than 3 days = 37%
3-7 days = 42%
More than 7 days = 21%
In the past month, the following percentages reflect length of hospital stay for all inpatients at the same facility:
Less than 3 days = 22%
3-7 days = 39%
More than 7 days = 39%
Run a chi-square analysis to determine if the past month is a statistically significant deviation from the prior year.
a) p value:
b) Null hypothesis decision (accept or reject):
3. Professor Testum wondered if students tended to make better scores on his test depending if the test were taken in the morning or afternoon. From a group of 19 similarly talented students, he randomly selected some to take a test in the morning and some to take it in the afternoon. The scores by groups were:
Morning / Afternoon89.8 / 87.3
90.2 / 87.6
98.1 / 87.3
91.2 / 91.8
88.9 / 86.4
90.3 / 86.4
99.2 / 93.1
94.0 / 89.2
88.7 / 90.1
83.9
As Professor Testum picked a group of similarly talented students, then the sample does not represent a normal distribution and, therefore, a nonparametric test is more appropriate even though the data are ratio variables! As these are independent groups, run a Mann-Whitney U test on these data to determine if the morning and afternoon groups are similar.
a) Mann-Whitney U p value:
b) Null hypothesis decision (accept or reject):
4. A health care practitioner commonly works with both spinal cord and stroke patients. The practitioner was curious as to whether there is a difference in the amount of time spent during initial evaluation for these two diagnoses among the inpatient rehabilitation team members and collected the following data from 15 team members:
Average Time spent completing initial evaluation (minutes)
Team Member Spinal Cord Injury Patients Stroke Patients
1 45 50
2 40 50
3 50 60
4 60 75
5 60 75
6 65 70
7 30 30
8 40 45
9 30 45
10 60 60
11 50 65
12 45 55
13 45 60
14 45 50
15 60 75
Remember: A nonparametric test is used even when the data are ratio or interval if the data cannot be considered normally distributed. In this case, we really don’t know as there is no evidence as to the normal distribution for such information. Therefore, it’s best to use a nonparametric test such as the Wilcoxon Signed-Ranks as these are paired data. Run a Wilcoxon Signed-Ranks test on these data to determine if there is a significant difference in time spent during initial evaluation for these disciplines for the two different diagnoses.
a) Wilcoxon Signed-Ranks p value:
b) Null hypothesis decision (accept or reject):