Statistics chapter 8 project- Siera and Tyler

1. SF & TL - Annual profits per employee for financial service companies, such as Wells
Fargo, First Bank System, and Key Banks (in thousands of dollars per employee)

42.9 43.8 48.2 60.6 54.9 55.1 52.9 54.9 42.5 33.0 33.6

36.9 27.0 47.1 33.8 28.1 28.5 29.1 36.5 36.1 26.9 27.8

28.8 29.3 31.5 31.7 31.1 38.0 32.0 31.7 32.9 23.1 54.9

43.8 36.9 31.9 25.5 23.2 29.8 22.3 26.5 26.7

1. Identify and/or calculate the following quantities and give descriptions and show work for how
you found them:
a. Sample size: 42
b. Sample mean: Is the average number of the data set which is 35.9952
c. Sample standard deviation: is how far the data is spread out from each other. 10.2379
d. Degrees of freedom: is the sample size minus 1. Our d.f. Is 41.
e. Critical values for 90%, 95%, and 99% confidence levels: The critical values show the
area of the standard normal curve. The critical values are 1.645, 1.96, and 2.58
f. Maximal margin of error for 90%, 95%, and 99% confidence levels: The maximal
margin of error is a small amount that is allowed past the μ. The Maximal
margin of error for 90% is E= tc x s/√n which means
E= 1.684 x 10.2379/√42=2.66.
For 95%, the margin of error is E= 2.021 x 10.2379/√42= 3.19.
The last margin of error for 99% is E= 2.704 x 10.2379/√42= 4.27
Determine 90%, 95%, and 99% confidence intervals for μ(the population mean):
The confidence intervals for μ shows us what range of the data set is in 90%, 95%, and
99%.
The formula for this equation is X −¿E¿ μ< X + E
For 90% of the data the range is 35.9952-2.66 < μ< 35.9952+2.66 Which is 33.3352 (33,300)
< μ< 38.6552. (38,700)
The range for 95% is 35.9952-3.19 < μ< 35.9952+3.19 which is 32.8052(32,800) < μ<
39.1852. (39,200)
The range for 99% is 35.9952-4.27 < μ< 35.9952+4.27 which is 31.7252(31,700) < μ<
40.2652. (40,300)
2. Annual profits per employee for financial service companies, such as Wells Fargo, First Bank
System, and Key Banks (in thousands of dollars per employee)
a. All of the above values and intervals
b. Work and/or descriptions for how each value was found
c. DETAILED description of what each of the 3 intervals you found represent in terms of
the original context of your data. Make sure to include units in your description - dollars,
 pounds, blood sugar level, etc. You must relate your results back to the data that was
collected! This is the whole point of doing a statistical analysis!
d. A brief comment about how you would have approached the above scenario differently
had you been given σ (the population standard deviation). What would have changed?

Chapter 8 Project Paper

For our chapter 8 Statistics Project we had a sample size of 42 from annual profits per
employee for financial service companies, such as Wells Fargo, First Bank System, and Key
Banks (in thousands of dollars per employee). Once we figured out the sample size of our data
we were able to calculate the sample mean, the average number of the data set. In our situation
the sample mean of our data is 35.9952, we got this by adding all of our data points together and
dividing by our sample size. Next we were able to figure out the sample standard deviation of
our data by putting the data into a graphing calculator and ending up with a result of 10.2379.
Furthermore we found the degrees of freedom, independent values in our data set. To get this we
had to subtract our sample size from one, leaving us with a degree of freedom of 41. Lastly we
were able to find the critical values of confidence levels, 90%, 95% and %99. These are the
percentages of all possible samples that can be expected. The critical values show the area of the
standard normal curve. The critical values we ended up with were 1.645, 1.96, 2.58. To find
these values we were able to look on table 4.
Once we found the critical values we could continue finding the maximal error in our
data, this is a small amount allowed past the μ. To find the maximal error for 90%,
95% and 99%, we had to use the equation E= tc x s/√n. T.c. was found on
our table using our degrees of freedom and percentage(90%) resulting
in 1.684. Then multiplied by our s which is 10.2379 and divided by the
square root of n, sample size, which in our case is 42. When put in a
graphing calculator we ended up with an answer of 2.66. After
repeating these steps with 95% and 99% we ended up with the answers
3.19 and 4.27. This means that only some employees will have an
annual profit outside of μ.
Our confidence intervals for μ show us what range of the data set is in 90%, 95%, and
99%. To figure out our confidence intervals we need to complete the equation, X −¿E¿ μ< X + E.
To complete this equation we took X , our sample mean, 35.9952 and subtracted it by the
maximal error using a 90% confidence level which was 2.66 and then added the same numbers
that were just subtracted to get the second interval. This gave us the intervals of 33.3352
(33,300) < μ< 38.6552. (38,700). These intervals let us know that we can be 90% confident that
the annual profits per employee for financial service companies, such as Wells Fargo, First Bank
System, and Key Banks are between the numbers of 33.3352($33,340) and 38.6552. ($38,700),
since the answers we found are in decimals we had to move them to the thousandths place
because the data we were given is in the thousandths . Once the equation is repeated again with
95% and 99% confidence intervals we are able to be 95% confident that the annual profits per
employee are between 32.8052($32,810) and 39.1852. ($39,200) and 99% confident that the
annual profits per employee are between 31.7252($31,730) and 40.2652. ($40,300).
If we were given the population standard deviation, σ instead of the sample standard
deviation we would have had to use a different equation to find the maximal error which would
give us another answer. This would give us new intervals but to find the confidence intervals the
same equation would’ve been used. We would have also had to decide whether or not the data
set was binomial.