In: Statistics and Probability
A researcher carried out an investigation of the extra sleep produced by drug A and drug B. The data from the experiment in hours are shown. Drug A 0.7 −1.6 −0.2 −1.2 −0.1 3.4 3.7 0.8 0.0 2.0 Drug B 1.9 0.8 1.1 0.1 −0.1 4.4 5.5 1.6 4.6 3.4 The data for both treatment groups are not normally distributed. To determine if the mean sleep response (extra hours of sleep produced) differs between drug A and drug B, a permutation test was performed. This was done by pooling both groups of data and randomly reassigning half the observations to the drug A group, and the other half to the drug B group. The difference of means for these two groups, ?⎯⎯⎯⎯?−?⎯⎯⎯⎯? , was then calculated and recorded. This permutation process was repeated a large number of times. The histogram shows the resulting distribution of values for the mean difference for all the permutations. Nearly symmetric histogram centered at 0 with vertical dashed lines at -1.8 and +1.8, separating the critical region from the non-critical region With a null hypothesis of no difference in the amount of extra sleep between the two drugs, and a two‑sided alternative hypothesis, determine if the actual observed difference is statistically significant. The dashed lines represent the critical values at −1.8 and 1.8, and the total area in the tails of the histogram is 0.05 , which represents the critical (rejection) region.
Compute the difference of the means of the two drugs for the observed data. Give your answer to two decimal places.
H0: There is no significant difference in the amount of extra sleep between the two drugs
H1: There is significant difference in the amount of extra sleep between the two drugs
two saple t-test
Drug A | Drug B |
0.7 | 1.9 |
-1.6 | 0.8 |
-0.2 | 1.1 |
-1.2 | 0.1 |
-0.1 | -0.1 |
3.4 | 4.4 |
3.7 | 5.5 |
0.8 | 1.6 |
0 | 4.6 |
2 | 3.4 |
A | B | |
avg | 0.75 | 2.33 |
sd | 1.789 | 2.0022 |
n | 10 | 10 |
Sp^2 =
((10-1)*1.789^2+(10-1)*2.0022^2)/(10+10+-2)
=3.6047
t = (0.75-2.33)/SQRT(3.6047*((1/10)+(1/10)))
= -1.8608
df = 10+10-2 =18
P-value = 2*(1-T.DIST(abs(-1.8608),18,1))
=0.0792
With t=-1.8608 and p-value =0.0792 > 0.05 we do not reject H0 at the 5% significance level
There is no significant difference between mean amount of extra sleep between the two drugs
________________________________________________________________
If you have any doubt please let me know through comment
Please give positive vote if you find this solution helpful. Thank
you!