In: Statistics and Probability
Does the use of sweetener xylitol reduce the incidence of ear
infections? Some children are randomly allocated t xylitol
treatment group and other children to the control group (who are
treated with placebo). Of 214 children on xylitol, 54 got ear
infection, while of 292 children on placebo, 73 got ear
infection.
Suppose p1 and p2 represent
population proportions with ear infections on xylitol and placebo,
respectively. Again [^(p)]1 and
[^(p)]2 represent sample proportions with ear
infections on xylitol and placebo, respectively.
1. What are the appropriate hypotheses one should test?
H0: p1 =
p2 against
Ha: p1
> p2.
H0: [^(p)]1 =
[^(p)]2 against
Ha:
[^(p)]1 ≠ [^(p)]2.
H0: p1 =
p2 against
Ha: p1
< p2.
H0: p1 =
p2 against
Ha: p1
≠ p2.
H0: [^(p)]1 =
[^(p)]2 against
Ha:
[^(p)]1 > [^(p)]2.
H0: [^(p)]1 =
[^(p)]2 against
Ha:
[^(p)]1 < [^(p)]2.
Tries 0/3 |
2. Rejection region: We reject H0 at 1%
level of significance if:
z < −2.326.
|z| > 2.326.
z > 2.326.
z < −2.576.
|z| > 2.576.
None of the above
Tries 0/3 |
3. The value of the test-statistic is: Answer to 2 decimal places.
Tries 0/5 |
4. If α = 0.01, what will be your conclusion?
Reject H0.
There is not enough information to conclude.
Do not reject H0.
Tries 0/3 |
5. The p-value of the test is: Answer to 4 decimal places.
Tries 0/5 |
6. We should reject H0 for all significance
level (α) which are
larger than p-value.
smaller than p-value.
not equal to p-value.
1)
H0: p1 = p2 against Ha: p1 < p2.
2)
z-critical value , Z* = -2.3263
[Excel function =NORMSINV(α)
We reject H0 at 1% level of significance if:
z < −2.326.
3)
sample #1 ----->
first sample size, n1=
214
number of successes, sample 1 = x1=
54
proportion success of sample 1 , p̂1=
x1/n1= 0.2523
sample #2 ----->
second sample size, n2 =
292
number of successes, sample 2 = x2 =
73
proportion success of sample 1 , p̂ 2= x2/n2 =
0.2500
difference in sample proportions, p̂1 - p̂2 =
0.2523 - 0.2500 =
0.0023
pooled proportion , p = (x1+x2)/(n1+n2)=
0.2510
std error ,SE = =SQRT(p*(1-p)*(1/n1+
1/n2)= 0.0390
Z-statistic = (p̂1 - p̂2)/SE = ( 0.002
/ 0.0390 ) =
0.06
4)
Do not reject H0.
5)
p-value = 0.5239
[Excel function =NORMSDIST(z)
6)
We should reject H0 for all significance
level (α) which are
smaller than p-value.