In: Statistics and Probability
Pitcher |
Strikes |
Balls |
Total |
Bumgarner |
76 |
32 |
108 |
Cueto |
76 |
41 |
117 |
Bumgarner Cueto
Sample Mean (pitches per inning) 12.0 13.0
Sample Variance (pitches per inning) 3.5 8
Sample Size (# of innings) 9 9
(an “inning” is one of the rounds in a game)
(5) a. At the 99% level, test the alternate hypothesis that Cueto throws more pitches per inning than Bumgarner for the entire season (population of pitches):
(5) b. Set up a 90% confidence interval for the true difference in the proportion of Balls thrown by each pitcher for the entire season:
(5) c. Perform a hypothesis test to see if the proportion of throwing strikes for Bumgarner and Cueto is not equal for the entire season. Set the Type I error equal to 10%.
A)
Ho : µ1 - µ2 = 0
Ha : µ1-µ2 < 0
Level of Significance , α =
0.01
Sample #1
----> BumgarneR
mean of sample 1, x̅1= 12.00
standard deviation of sample 1, s1 =
3.50
size of sample 1, n1= 9
Sample #2 ----> Cueto
mean of sample 2, x̅2= 13.00
standard deviation of sample 2, s2 =
8.00
size of sample 2, n2= 9
difference in sample means = x̅1-x̅2 =
12.0000 - 13.0 =
-1.00
pooled std dev , Sp= √([(n1 - 1)s1² + (n2 -
1)s2²]/(n1+n2-2)) = 6.1745
std error , SE = Sp*√(1/n1+1/n2) =
2.9107
t-statistic = ((x̅1-x̅2)-µd)/SE = (
-1.0000 - 0 ) /
2.91 = -0.344
Degree of freedom, DF= n1+n2-2 =
16
p-value =
0.367826 [ excel function: =T.DIST(t stat,df) ]
Conclusion: p-value>α , Do not reject
null hypothesis
.................
B)
sample #1 ----->
Bumgarner
first sample size, n1=
108
number of successes, sample 1 = x1=
32
proportion success of sample 1 , p̂1=
x1/n1= 0.2963
sample #2 -----> Cueto
second sample size, n2 =
117
number of successes, sample 2 = x2 =
41
proportion success of sample 1 , p̂ 2= x2/n2 =
0.350
difference in sample proportions, p̂1 - p̂2 =
0.2963 - 0.3504 =
-0.0541
level of significance, α = 0.10
Z critical value = Z α/2 =
1.645 [excel function: =normsinv(α/2)
Std error , SE = SQRT(p̂1 * (1 - p̂1)/n1 + p̂2 *
(1-p̂2)/n2) = 0.0623
margin of error , E = Z*SE = 1.645
* 0.0623 = 0.1024
confidence interval is
lower limit = (p̂1 - p̂2) - E = -0.054
- 0.1024 = -0.1565
upper limit = (p̂1 - p̂2) + E = -0.054
+ 0.1024 = 0.0483
so, confidence interval is (
-0.1565 < p1 - p2 <
0.0483 )
.............
C)
Ho: p1 - p2 = 0
Ha: p1 - p2 ╪ 0
sample #1 ----->
experimental
first sample size, n1=
108
number of successes, sample 1 = x1=
76
proportion success of sample 1 , p̂1=
x1/n1= 0.7037
sample #2 -----> standard
second sample size, n2 =
117
number of successes, sample 2 = x2 =
76
proportion success of sample 1 , p̂ 2= x2/n2 =
0.650
difference in sample proportions, p̂1 - p̂2 =
0.7037 - 0.6496 =
0.0541
pooled proportion , p = (x1+x2)/(n1+n2)=
0.6756
std error ,SE = =SQRT(p*(1-p)*(1/n1+
1/n2)= 0.0625
Z-statistic = (p̂1 - p̂2)/SE = (
0.054 / 0.0625 ) =
0.8665
p-value =
0.3862 [excel formula =2*NORMSDIST(z)]
decision : p-value>α,Don't reject null
hypothesis
Conclusion: There is not enough evidence
to the proportion of throwing strikes for Bumgarner and
Cueto is not equal for the entire season
.....................
thanks
revert back for doubt
please upvote