In: Statistics and Probability
1.) Now use Minitab and attach "Output" for the problem below?
A random sample of 59 students was selected from the PSU student data base. Each student was asked their Sex and Height (in inches). Below are the summary results:
Sex |
N |
Mean |
SD |
Female |
42 |
66.10 |
2.58 |
Male |
17 |
70.12 |
3.66 |
a.) Using the summary information, estimate with 99% confidence the difference in heights between the sexes and interpret these results. What are the exact degrees of freedom used in the calculation of the t-statistic?
b.) Is there enough evidence at a 1% level of significance to
conclude that males, on average, are taller than females? Include
hypotheses, p-value, decision, and conclusion.
c.) What assumptions would need to be satisfied in order to safely
use and interpret the results?
Solution:
Given data:
Female | Male |
66.1 | 70.12 |
2.58 | 3.66 |
42 | 17 |
a) We have to find 99% confidence interval for the difference between height of female and height of male.
Following is the output:
Female | Male | ||||
66.1 | 70.12 | mean | |||
2.58 | 3.66 | std. dev. | |||
42 | 17 | n | |||
57 | df | ||||
-4.0200 |
difference (Female - Male) |
-4.78 t |
-6.2597 | confidence interval 99.% lower | |||
-1.7803 | confidence interval 99.% upper | ||||
2.2397 | margin of error |
Hence, 99% confidence interval is,(-6.2597 , -1.7803)
b)
The null and alternative hypotheses:
The output is,
Decision: P-value is close to 0. Therefore, P-value <0.01 then reject H0.
Conclusion: There is enough evidence to conclude that males, on average, are taller than females at 0.01 level of significance.
c)
Here the given data is sample data which is in the form of summary. Therefore, we assume that this data is approximately normally distributed. In this scenario, population standard deviation is uknown and thus the t test for two mean is used. Also there is not given about equality of standard deviation, so we asumed it and followed pooled t-test.
Done