Researcher Johns set the alpha level for his clinical trial at the standard 0.05. When he ran his data, the difference between groups was found to be p = 0.002. Johns was elated! He interpreted this finding to mean his results:

• A.Were highly clinically significant
• B.Were statistically more significant and important
• C.Had 2 chances out of 1000 of finding the difference (results) by random error
• D.Had really found the truth to his question

Nurse Chapman was interested in the effectiveness of three regimes to increase mobility in frail elders. She recruited 100 subjects and each subject received all treatments over time and thus served as his or her own control. Each subject was randomly assigned to the order of the treatment he or she would receive (walking, swimming, and meditation). Each subject completed the first treatment over six weeks, and then after a wash out period of three weeks went to the next treatment, eventually completing all treatments. Subjects were asked not to participate in earlier treatments once the six week trial of each was completed. Mobility was measured at the end of each treatment using an interval like scale. Assuming that all assumptions of the statistical test were met, which of the following statistical tests should be used?

• A.Chi-square
• B.Paired t-test
• C.Mann Whitney U
• D.Repeated measures analysis of variance (RANOVA)

Professor Smith ran a simple regression equation using midterm exam scores to predict final exam scores. The R-square was .91 and this was statistically significant (p=.0001). Using the following regression equation generated by Professor Smith, predict the final exam score (y) when the midterm score is 86: y=1.5 + .9 (x)

• A.About 55
• B.About 69
• C.About 79
• D.About 82

In the following hypothesis what is being asked? Post- surgery, eligible patients who have their indwelling urinary catheter removed within 24 hours will have lower rates of urinary tract infections than eligible patients who have their indwelling urinary catheter removed after 24 hours.

• A.To describe infection rates
• B.To determine if there is a relationship between time and infection rates
• C.To predict who will get urinary tract infections
• D.To determine if there is a difference in urinary tract infection rates between two groups

Dr. Casey was interested in treatments for insomnia, and whether different treatments would improve daytime fatigue. She compared the differences on daytime fatigue scores (measured with an interval like scale) among three independent and mutually exclusive groups who received different treatments for insomnia. Since the assumptions of the test were met, she ran a one-way ANOVA. Overall, she found a statistically significant difference among groups (p=.003). The next step for Dr. Casey is to:

• A.Report that the treatments were all different.
• B.Run a post-hoc test such as the Tukey or Scheffe to determine which groups differed.
• C.Recommend a change in the treatment of insomnia based on her findings
• D.Re-run the data using the Kurskal-Wallis test.

You are part of a team that is doing osteoporosis testing for women. Part of the data collected is information regarding strength and speed. Because both are measured as continuous level variables, the statistician runs a correlation to evaluate the association between strength and speed. You get the following information to interpret:

r = .48

p = .02

r2= .23

How much variability in speed is explained by strength?

• A.48%
• B.2.0%
• C.23%
• D.71%

In the t-test, the independent or 'explanatory' variable is measured at what level?

• A.Nominal
• B.Ordinal
• C.Interval
• D.Ratio

A nurse researcher conducts a descriptive study among a sample of multiple myeloma cancer survivors at his local institution. His main finding is that women are less likely than men to be diagnosed with multiple myeloma. Which of the following would you expect to see for an odds ratio = .70 for gender?

• A.The odds of a woman being diagnosed with multiple myeloma are 30% less than men.
• B.The odds of a man being diagnosed with multiple myeloma are 70% more than women.
• C.Neither is correct

In chi-square tests, the data are assumed to be:

• A.Frequency
• B.Continuous
• C.Both A and B
• D.Neither A nor B

Power is calculated to determine the probability of committing a type II error. In most cases, a power of 0.8 is acceptable. With a power of 0.8:

• A.We are certain to make a type II error
• B.We are likely to make a type II error 2 times out of 10
• C.We have a weak possibility of finding a statistical significance, even if there really is a difference
• D.We are likely to make a type II error 8 times out of 10