Professional Documents
Culture Documents
Math 1040 Project
Math 1040 Project
Math – 1040
Part 1: TB Data Project
A. In a random sample of the 194 members of the World Health Organization, I will be
using the following 10 countries: Austria, Estonia, Guinea, Haiti, Kyrgyzstan, United
method to select a random 10 members or countries of the 194 of the World Health
Organization (WHO); I googled random sampler generator, and the first thing to come up
was a random number generator. I continued to enter in “1” for my minimum as well as
“194” for my maximum. Corresponding to the 194 members of the WHO. Then
proceeded to generate 10 different numbers through the same method for the random 10
B.
Tanzania
C. Denmark:
1. For females, the age group from 45-54 had the most notified cases.
2. For males, the age group from 0-4 had the least notified cases.
3. If there were 5000 total cases notified Female 45-54 = 26.9% and Male 0-4 =0.9%
Relative frequency 0.269*5000 = 1345 females aged 45-54
Relative frequency 0.009*5000 = 45 males aged 0-4
D.
We resulted in zero samples for Austria with the success rate at 0.70.
Since the P value is equal to 0 and the alpha is equal to 0.05, our P value is greater. Leading us to
believe that we do have statistically significant evidence that the success rate for Austria is not
the same as the rest of the world and we can furthermore reject the null hypothesis.
To retrieve these countries, they were chosen from the random sample of 10 countries from Part
I of this project.
For Denmark, the cohort size will be our sample size and the success rate of treatment will be
our sample proportion. The sample size is 206 and the sample proportion is 0.34. When checking
for the conditions of computing a 95% confidence interval, we first looked at if it was a random
sample, which it was. Each country was chosen randomly during part one of this project. Second,
we checked to see if the sample size was less than 5% of the population proportion. With the
sample size being 206, it is more than likely that 206 is less than 5% of the world’s population.
Lastly, we check to see if the successes and failures are greater than 10. So, we took 0.34*206,
which was 70.04 successes. Then we took 206(1-0.34), which came out to be 135.96 failures.
Both 70.04 as well as 135.96 are greater than 10. For Denmark, all conditions were met for
Secondly, for Togo, the sample size is 2312 and the sample proportion is 0.85. When checking
for the conditions of computing a 95% confidence interval, we first looked at if it was a random
sample, which it was. Again, each country was chosen randomly during part one of this project.
Secondly, we checked to see if the sample size was less than 5% of the population proportion.
With the sample size being 2312, it is more than likely that 2312 is less than 5% of the world’s
population. Lastly, we check to see if the successes and failures are greater than 10. So, we took
calculated as 346.8 failures. Once again, both 1965.2 as well as 346.8 are both greater than 10.
For Togo, all conditions were met for computing a 95% confidence interval.
B. The image containing an image of the 95% confidence interval being interpreted for
95% confidence interval, we entered in both the sample size (N) and number of successes
into GeoGebra. Once computing the numbers in the system is done you then take the
interval and both subtract as well as add the margin of error to achieve the interval. Or for
a quicker result, just take both the lower and upper limit numbers given.
Below, the second country, Togo’s interpretation and results are given.
The confidence interval achieved in the same manner as the country before for Togo is
(0.8354,0.8646).
C. In Part I of this project, PLOS One report stated that the global threshold for successful
treatment was 85%. After computing the confidence interval for Demark, which, as a
reminder was (0.2753,0.4047) We can look and see that the confidence interval is making
the successful treatment of 85% not very likely. We can also see after computing the
confidence interval for Togo, which again was (0.8354,0.8646), looking at this
confidence interval we can see that making the successful treatment of 85% is actually
very likely. Concluding that Denmark is not very likely because 0.85 does not fall into
the confidence interval; however, for Togo 0.85 falls directing into that confidence
interval.
D. We will now further this study by looking at the country the was used in part I of this
project, Austria. We are going to be checking the conditions to carry out a two-sided test
of whether p=0.85. We must once again begin by checking the requirements are met.
Firstly, we need to confirm that this was a random sample; which has been stated
multiple times now that this country was randomly selected during Part I of this project.
With the sample size being 380, it is more than likely that 380 is less than 5% of the
world’s population. Lastly, we check to see if the successes and failures are greater than
10. So, we took 0.70*380, which was 266 successes. Then we took 380(1-0.70), which
came out to be 114 failures. Both 266 as well as 114 are greater than 10. For Austria, all
The following information is the put into GeoGebra; null hypothesis p=0.85, successes =
We can conclude that the test statistic given is -8.19. With a significance level of 0.05 and the p-
value being 0, we can see that the p-value is less than the 0.05. We reject the null hypothesis.
There is sufficient evidence to conclude that 85% is not the global threshold for successful
tuberculosis treatments.
F. Using the image below, we can compare the results from Part I section D to the results
found above. From this we can see that both of our p-values equal 0. We can see from
Part I that the success rate of Austria is 0.70 which is a rare rate compared to the rest of
the world. We can see that similarly; Austria also rejected the null hypothesis in part I
just like in Part II. However, in my opinion I believe that the results from Part II would be
more valid than those found in Part I, because the sample size in Part II is much larger
than the one used in Part I leading us to believe that the information gathered from Part II
A.
Austria 5
Estonia 9.3
Guinea 175
Haiti 159
Kyrgyzstan 130
Samoa 6.8
Romania 45
Denmark 3.8
quency
B. This box plot is right skewed. The center is 39 and the spread of distribution is 152.2.
lower fence is -221.5 and the upper fence is 387.3 Since there are not numbers outside of
D. When checking the three conditions we can confirm that this is a randomized sample. As
mentioned, numerous times, these countries were randomly selected. The sample size is
124,443. We can confirm that our sample size is less than 5% of the world’s population.
And lastly, it is a normal distribution because our sample size is greater than 30.
E.
We are 95% confident that the interval 19.41 to 135.56 contains the true mean of the total
number of TB incidences.
F. We wanted to find out if the global incident rate of TB is different than the reported value
of 132. From the table below we can see that our test statistic is -2.12 and our p-value is
0.0627. Our alpha = 0.05. We can see that 0.06274 > 0.05.
Therefore, since the p-value is greater than alpha, we fail to reject the null hypothesis. We
do not have sufficient evidence that the global incidence rate of TB in the world is
Kyrgyzstan 82 18 100
United Republic of 96 4 100
Tanzania
Togo 86 14 100
Samoa 85 15 100
Romania 82 18 100
Denmark 34 66 100
Total 783 217 1000
B.
1. The probability that a randomly selected case is from Kyrgyzstan, or the United
Republic of Tanzania is:
100 100 0
+ − =0.2
1000 1000 1000
2. The probability that a randomly selected case is from Kyrgyzstan or is a failure is:
100 217 18
+ − =0.299
1000 1000 1000
3. The probability that a randomly selected case is from Kyrgyzstan AND is a failure is:
18
=0.018
1000
4. The probability that a randomly selected case is from the United Republic of
Tanzania GIVEN it is a failure:
4
=0.018
217
5. The probability that three randomly selected case are all successes from Samoa is:
100 99 98
x x =0.00097
1000 999 998
C. Below is the GeoGebra output and interpretation for a 95% confident interval for the
difference between proportions of successes of Kyrgyzstan and the United Republic of
Tanzania.
We are 95% confident that the interval -0.2245 to -0.0555 contains the true difference of
proportions of successes of Kyrgyzstan and the United Republic of Tanzania.
D. Below is the hypothesis test, p-value, and test-statistic for where there is a difference in
proportions of successful treatment for Kyrgyzstan and the United Republic of Tanzania.
With alpha being 0.05
Since the p-value is less than alpha, we reject the null hypothesis. There is sufficient
evidence to show that there is a difference of proportions for successful treatments from
Kyrgyzstan and the United Republic of Tanzania.