In: Statistics and Probability
A researcher wants to determine whether or not a given drug has any effect on the score of a human subject performing a task of ESP sensitivity. He randomly assigns his subjects to one of two groups. 900 subjects in group 1 (treatment group) receive the drug. In contrast, 1000 subjects in group 2 (control group) receive a placebo. For the drug group, the mean score on the ESP test was 15, SD=4. For the no-drug group, the mean =9, SD=9. Does taking this drug increase test scores? Test your hypothesis at 5% significance level. (Include null and alternative hypothesis, test statistic, p-value, and conclusion)
We want to test that taking this drug increase test scores
u1:- population mean test score of after taking the drug
u2:- Population mean score test score of not taking the drug
The null & alternative hypothesis
Ho:- u1-u2 = 0 vs Ha:- u1 - u2 > 0
Group 1: treatment group: who takes drug before the test
Group 2: control group: who takes doesn't take the drug before the test
P- value :
P-value = P(tn1+n2-2 > t )
= P(t900+1000-2 > 18.429)
= P(t1898 > t )
=0
The decision:- Reject Ho if P-value < alpha
Alpha = 0.05
P-value= 0 < alpha = 0.05
So we reject Ho
Conclusion:- We may conclude that the data provides sufficient evidence to support the claim that the drug increases test scores.
We were unable to transcribe this image
Test Statistics t-statistic is computed as follows: X - X2 In, -1);{ +(12-1)3 (1+1) 71-19-2 15-9 = = 18.429 (900-142+(1000-191 (900 + 1000) 1 ) 900-1000-2