statistics help for the following scenario In a double blind, randomised trial c
ID: 3332820 • Letter: S
Question
statistics help for the following scenario
In a double blind, randomised trial conducted during a flu outbreak, the effect of two drugs (Rimantadine and Amantadine) and a placebo were tested among 450 volunteer subjects. The numbers developing flu-like symptoms are shown in the table below.
Treatment
Placebo
Amantadine
Rimantadine
No Flu
104
128
135
Flu-like symptoms
54
19
10
Total
158
147
145
a) Convert the table above to show the proportion of people with and without flu for each treatment. Fill in the table below.
Treatment
Placebo
Amantadine
Rimantadine
No Flu
Flu-like symptoms
Total
1
1
1
b)Draw an appropriate graph (using Minitab or Excel) that would enable the reader to compare the distribution of the people with and without flu for each treatment.
c)Summarise the main message from the graph
The researchers want to test whether having the flu is independent of treatment.
d)State the null and alternate hypotheses for this test.
e) Use Minitab Express to calculate the Chi-square test statistic. Include the expected number of cases and the contributions from each cell in your Minitab output. Attach your output here
f)Show how the expected number of “no flu” people for Placebo is calculated by hand.
g)Show how the contribution to the Chi-square statistic from “flu-like symptoms” for Placebo is calculated by hand.
h)State the test statistic and its degrees of freedom.
i)Explain whether you have evidence against the null hypothesis or not
j)State your conclusion in context. Which treatment would you recommend?
Treatment
Placebo
Amantadine
Rimantadine
No Flu
104
128
135
Flu-like symptoms
54
19
10
Total
158
147
145
Explanation / Answer
Chi-Square Test helps you determine if two discrete variables are associated :
· If two variables are associated, then the distribution of observations for one variable will differ depending on the category of the second variable.
· If two variables are independent, then the distribution of observations for one variable will be similar for all categories of the second variable.
The table shows the observed counts for each cell (top number of pair), as well as the counts that one would expect if the two variables are independent (expected counts , bottom number of pair).
Chi-Square Test: Placebo, Amantadine, Rimantadine
Expected counts are printed below observed counts
Chi-Square contributions are printed below expected counts
Placebo Amantadine Rimantadine Total
1 104 128 135 367
128.86 119.89 118.26
4.795 0.549 2.371
2 54 19 10 83
29.14 27.11 26.74
21.203 2.428 10.484
Total 158 147 145 450
Chi-Sq = 41.830, DF = 2, P-Value = 0.000
For the umbrella data, chi-square is 41.83 and the p-value is 0.000. Therefore, if you selected an a-level of 0.05 for the test, you would conclude that the variables are associated.
Hope this will be helpful. Thanks and god Bless you:-)
Related Questions
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.