WorkbookExercise 18
Exercise18

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 the exercise to calculate the group df and the error df.
Group df = group numbers inthe study – 1 = 3 – 1 = 2.
Error df = number ofparticipants in the study – group numbers in the study = 255 – 3= 252 error df.

What is the F value and p value for spiritual needpatient? What do the results mean?
The F value and pvalue forspiritual needpatient are 38.1 and < 0.0001 respectively. Theresult is statistically substantial since pvalue is less than orequal to 0.05. Therefore, there is a statistically substantialdifference among the three groups of hospice, hospital with LCP andhospital without LCP in terms of spiritual needpatient.

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 forfacilities for hospitals with Liverpool Care Pathway (LCP) versushospitals without LCP is p = 0.85 which is greater than 0.05 meaningit is not statistically significant. Therefore, there isn`t asignificant difference between the hospital with LCP and the hospitalwithout LCP groups in terms of facilities.

What are the assumptions for use of ANOVA?
The assumptions for using theAnalysis of Variance (ANOVA) test are that random samples arenormally distributed, the groups in a study are not influenced byother groups and have equal mean square, the observations made areindependent, and the dependent variable is expressed at ratio level.

What variable on Table 3 has the result F = 10.6, p < 0.0001? What does the result mean?
Symptom management is thevariable on Table 2 that has the result F = 10.6 (p < 0.0001).This result is statistically significant meaning there is asignificant difference among the three groups of hospice, hospitalwith LCP, and hospital without LCP with regard to the symptommanagement.

ANOVA was used for analysis by Mayland et al. (2014). Would ttests have also been appropriate? Provide a rationale for your answer.
The ttest would not have beenappropriate since it can only compare two groups at a time,therefore, using it would require performing multiple tests whichwould inflate the Type I. Type I error is whereby the results mayindicate a significant difference among the three groups when theyare not different. The ANOVA test curbs these errors so as to ensurethe Type I error is maintained at 5% thus preserving confidence inthe results obtained.

What type of post hoc analysis was performed? Is the post hoc analysis performed more or less conservative than the Scheffe test?
The Turkey HSD (HonestlySignificant Difference) was performed. The Turkey HSD is lessconservative than the Scheffe Test.

State the null hypothesis for care for the three study groups (see Table 2). Should the null hypothesis be accepted or rejected? Provide a rationale for your answer.
The null hypothesis is: “Thethree care groups of hospice, hospital with LCP and hospital withoutLCP have no difference in care scores for the nextofkin of patientswho had died of cancer.” According to Table 2, F = 35.9, p <0.0001, for composite scale care. This F value is statisticallysignificant because the pvalue is less than α = 0.05 that wasdetermined for this study. The null hypothesis was rebuffed sincethere was a statistically substantial difference among the threegroups for care as indicated by the results.

What are the post hoc results for care? Which results are statistically significant? What do the results mean?
The post hoc results for careare: p = 0.0001 for hospice versus hospital with LCP and p = 0.0001for hospice versus hospital without LCP. These results identifystatistically significant differences for care among these identifiedgroups since p values are less than α = 0.05. The post hoc result ofp = 0.05 for the hospital with LCP versus hospital without LCP isequal to 0.05 and is not statistically significant. Therefore, thereisn’t a substantial difference between the hospital with LCP andthe hospital without LCP groups with regard to care.

In your opinion, do the study findings presented in Table 2 and 3 have implications for end of life care? Provide a rationale for your answer.
The study findings presentedin Table 2 and 3 have implications for the end of life care sincethey can provide family members with good suggestions on whichprogram performs best in terms of ward environment, facilities, care,and communication.