In: Statistics and Probability
As a medical social worker in a local hospital, you are asked to evaluate the success of a group instruction diabetic control program. You randomly assign twelve diabetic patients to the group program and twelve to the more traditional personal instruction program. Over a twelve-month period you collect data on the number of hospital admissions and emergency room visits for uncontrolled blood sugar for individuals in each group. These data are presented below. You are to analyze these data using an independent-samples test and then make a recommendation to the medical director as to whether to continue the program (Set α=.05).
Number of admissions and emergency room visits
Group instruction Personal Instruction
n1=12 n2=12
1=1.4 2=2.3
S1=1.2 S2=1.2
Ho : µ1 - µ2 = 0
Ha : µ1-µ2 < 0
Level of Significance , α =
0.05
Sample #1 ----> 1
mean of sample 1, x̅1= 1.400
standard deviation of sample 1, s1 =
1.2000
size of sample 1, n1= 12
Sample #2 ----> 2
mean of sample 2, x̅2= 2.300
standard deviation of sample 2, s2 =
1.2000
size of sample 2, n2= 12
difference in sample means = x̅1-x̅2 =
1.4000 - 2.3 =
-0.90
pooled std dev , Sp= √([(n1 - 1)s1² + (n2 -
1)s2²]/(n1+n2-2)) = 1.2000
std error , SE = Sp*√(1/n1+1/n2) =
0.4899
t-statistic = ((x̅1-x̅2)-µd)/SE = ( -0.9000
- 0 ) / 0.49
= -1.837
Degree of freedom, DF= n1+n2-2 =
22
p-value =
0.0399 [ excel function: =T.DIST(t stat,df) ]
Conclusion: p-value <α , Reject null
hypothesis
We conclude that the null hypothesis is rejected
hence there is evidence that mean for group instruction is less.
we should continue the program