Exercise 18
1. Mayland et al. (2014) do not provide the degrees of freedom ( df ) in their study. Use the
degrees of freedom formulas provided at the beginning of this exercise to calculate the group df
and the error
...
Exercise 18
1. Mayland et al. (2014) do not provide the degrees of freedom ( df ) in their study. Use the
degrees of freedom formulas provided at the beginning of this exercise to calculate the group df
and the error df .
The degrees of freedom are calculated by subtracting k, the number of groups in the study
(which is 3) by the number N of participants. 255 – 3. df = 252. The error df is done by the
formula k – 1, so 3 – 1 = 2. The error df is 2
2. What is the F value and p value for spiritual need—patient? What do these results mean?
The F = 38.1, p = <0.0001. These results mean that there is a very significant difference
between one of the groups compared to the other two groups in the study. Post-hoc analysis will
determine where the significance lies.
3. What is the post hoc result for facilities for the hospital with LCP vs. the hospital without LCP
(see Table 2 )? Is this result statistically significant? In your opinion, is this an expected finding?
The post-hoc result for facilities for the hospital with LCP vs. the hospital without LCP is
p = 0.85. This is above the alpha level of significance and means that there is no difference in the
means for this comparison. In my opinion, this should be an expected finding because all
hospital facilities have to have a standard of care, which would mean that all facilities should be
similar.
4. What are the assumptions for use of ANOVA?
Assumptions for use of ANOVA include:
1. The sample is of a normal distributions.
2. The groups are mutually exclusive.
3. The groups have equal variance.
4. The observations are independent.
5. The dependent variable is an interval or ratio.
5. What variable on Table 3 has the result F = 10.6, p < 0.0001? What does the result mean?
Symptom management had this result. This result indicates that one of the groups
measured is significantly different than the others. This could mean that one group had
significantly better symptom management at end of life, or possibly worse symptom
management.
6. ANOVA was used for analysis by Mayland et al. (2014). Would t-tests have also been
appropriate? Provide a rationale for your answer.
While t-tests could have been used to analyze the data, they would not have been
appropriate because in this experiment, multiple groups are being compared to each other. T-tests
can only compare two means, so multiple t-tests would have to have been done. This would raise
the probability of a Type I error where significant results are found, but they are not truly
significant.
7. What type of post hoc analysis was performed? Is the post hoc analysis performed more or less
[Show More]