In: Statistics and Probability
Two catalysts are being analyzed to determine how they affect the mean yield of a chemical process. Specifically, catalyst 1 is currently used. Because catalyst 2 is cheaper, it should be adopted, if it does not change the process yield. A test is run in the pilot plant and results in the data shown in the Table below. Both populations are assumed normal.
Observation # |
Catalyst 1 |
Catalyst 1 |
1 |
91.5 |
89.19 |
2 |
94.18 |
90.95 |
3 |
92.18 |
90.46 |
4 |
95.39 |
93.21 |
5 |
91.79 |
97.19 |
6 |
89.07 |
97.04 |
7 |
94.72 |
91.07 |
8 |
89.21 |
92.75 |
a) Assuming equal variances, using a hypothesis test at 5% alpha level, show if there is any difference in the mean yields.
b) Assuming unequal variances, using a hypothesis test at 5% alpha level, show if catalyst 2 yields greater mean than catalyst 1.
c) Find a 95% confidence interval for the mean of catalyst 1 minus that of catalyst 2 assuming equal variances.
a)
Ho : µ1 - µ2 = 0
Ha : µ1-µ2 ╪ 0
Level of Significance , α =
0.05
Sample #1 ----> Catalyst 1
mean of sample 1, x̅1= 92.26
standard deviation of sample 1, s1 =
2.39
size of sample 1, n1= 8
Sample #2 ----> Catalyst 2
mean of sample 2, x̅2= 92.73
standard deviation of sample 2, s2 =
2.98
size of sample 2, n2= 8
difference in sample means = x̅1-x̅2 =
92.2550 - 92.7 =
-0.48
pooled std dev , Sp= √([(n1 - 1)s1² + (n2 -
1)s2²]/(n1+n2-2)) = 2.70
std error , SE = Sp*√(1/n1+1/n2) =
1.3504
t-statistic = ((x̅1-x̅2)-µd)/SE = ( -0.4775
- 0 ) / 1.35
= -0.354
Degree of freedom, DF= n1+n2-2 =
14
p-value = 0.7289
(excel function: =T.DIST.2T(t stat,df) )
Conclusion: p-value>α , Do not reject null
hypothesis
There is not enough evidence to conclude that there is any
difference in the mean yields
b)
Ho : µ1 - µ2 = 0
Ha : µ1-µ2 < 0
Level of Significance , α =
0.05
Sample #1 ----> Catalyst 1
mean of sample 1, x̅1= 92.26
standard deviation of sample 1, s1 =
2.385018718
size of sample 1, n1= 8
Sample #2 ----> Catalyst 2
mean of sample 2, x̅2= 92.733
standard deviation of sample 2, s2 =
2.98
size of sample 2, n2= 8
difference in sample means = x̅1-x̅2 =
92.255 - 92.7325 =
-0.4775
std error , SE = √(s1²/n1+s2²/n2) =
1.3504
t-statistic = ((x̅1-x̅2)-µd)/SE = ( -0.4775
/ 1.3504 ) = -0.3536
p-value = 0.3647 [
excel function: =T.DIST(t stat,df) ]
Conclusion: p-value>α , Do not reject null
hypothesis
There is not enough evidence to conclude that catalyst 2
yields greater mean than catalyst 1.
c)
Degree of freedom, DF= n1+n2-2 =
14
t-critical value = t α/2 =
2.1448 (excel formula =t.inv(α/2,df)
pooled std dev , Sp= √([(n1 - 1)s1² + (n2 -
1)s2²]/(n1+n2-2)) = 2.7009
std error , SE = Sp*√(1/n1+1/n2) =
1.3504
margin of error, E = t*SE = 2.1448
* 1.3504 =
2.8964
difference of means = x̅1-x̅2 =
92.2550 - 92.733 =
-0.4775
confidence interval is
Interval Lower Limit= (x̅1-x̅2) - E =
-0.4775 - 2.8964 =
-3.374
Interval Upper Limit= (x̅1-x̅2) + E =
-0.4775 + 2.8964 =
2.419