Problem Set 3 BUS 310

WF 10:30-11:45

Ashley Plemmons

Chapter 8:
This problem is based on the file Absent PS3 F17 on Laulima. (1.5 points)
The data represents a sample of 100 organizations and gives the Wages for each organization. Unstack
Wage by Union. Use the data in the Unstacked sheet.
Construct 95% Confidence intervals for the population mean for Wages for each of these 3 union levels
and write a one sentence interpretation for each of the 3 confidence intervals you obtained. Also for each
interval assess whether the assumption that the data comes from a Normal shaped population is
acceptable for each of the 3 sets of data. Then comment on whether the 3 confidence intervals should be
valid or not using the fact that they should be valid whenever the data is normal or the sample size is
large (n > 30).

● We can be 95% confident that the population mean of wages for Low union companies
falls between $33,192.47 and $40981.59.
● We can be 95% confident that the population mean of wages for Medium union companies
falls between $31,696.11 and $36,462.47.
● We can be 95% confident that the population mean of wages for High union companies
falls between $29,656.59 and $44,648.48
● The confidence interval for low, medium, and high is valid because the data is normal
since skewness and kurtosis for all 3 of these is between -1 and 1
2. Scott Gerber of Young Entrepreneur Council teamed up with Buzz Marketing Group (and sponsor
LegalZoom.com) to put together a survey of 1,000+ college students and recent graduates.

They asked questions about entrepreneurship, the economy and business aspirations.
Here are the major findings:
● 36% are "sidepreneurs," i.e. they've started businesses in addition to getting their degrees
● 21% Started businesses because they are unemployed.
● 69% would like to work for an entrepreneur
● 89% feel entrepreneurship education is important given the new economy and job market
● 73% were not offered classes in entrepreneurship
● 70% who took entrepreneurship classes said they were not adequate
From the survey results, we can gather that the demand for entrepreneurship is high, and our education
system isn't adapting quickly enough.

The survey was based on 1635 respondents.

Answer the following questions based only on the first finding (36% figure) above (2.0 points).
1. Write a one sentence interpretation of your 95% confidence interval.
It is 95% confident that the population proportion of sidepreneurs falls between 0.3370 and
0.3835.

2. Calculate both a 95% confidence interval and a 90% confidence interval. See directly
below for how to do this. The 90% CI is the same except to change the 95 to 90. What is
the difference in the width (upper – lower limits) of the 2 confidence intervals? Which
confidence interval gives you a more precise estimate (smaller width)?

The width difference of the 95% confidence interval is 0.0465. The width difference of the 90%
confidence interval is 0.0391. The smaller interval means that it is a higher precision. Which
means the 90% confidence interval is more accurate because the difference between the upper
and lower limit is much smaller.

3. Problem 8.50 on P.283 (.5 point)

Why can you never really have 100% confidence of correctly estimating the population
characteristic of interest?

A confidence uses a normal distribution. Negative infinity to infinity is the only interval for
a normal distribution that you can be 100% confident in. An estimate can never be 100%
confident or else it wouldn’t be an estimate.

4. Problem 8.52 on P.283 (.5 point)

Why is it true that for a given sample size, n, an increase in confidence is achieved by
widening (and making less precise) the confidence interval?

When widening the confidence interval, it will be increasing the possible values that can
be possible. There is only one exact value for the population characteristic which is
widening our range of possible values only makes this estimate of the exact value less
precise.

5. Problem 8.53 on P.283 (.5 point)

 Why is the sample size needed to determine the proportion smaller when the population
proportion is 0.20 than when the population proportion is 0.50?

The formula for calculating the sample size needed for estimating a population proportion
contains:

the proportion multiplied by (1-proportion) in the numerator.

20%*(1-20%)=(0.2)(0.8)=0.16 whereas 50%*(1-50%)=(0.5)(0.5)=0.25 which is
larger than 0.16

Chapter 9:
Note: For all problems except 1, to get full credit you need to state the
hypotheses and write a conclusion that includes how confident you are in the
alternative. See the Chapter 9 HT Confidence Approach handout and Lecture
notes 14, and 15 for details, especially for suggestions (RoTs) on writing up
conclusions clearly.

1. Problems 9.73 (a,b); (1 pt)

Remember that the null hypothesis always contains the = sign and that the alternative hypothesis never
does. Read the problem, determine whether it is a problem concerning a pop mean (μ) or a pop
proportion (π), and then find the specific question to be answered.
Both parts (a) and (b) should have an H0and an H1.

a) H0 : μ >= $100, This means that the population mean reimbursements will be more than
$100
H1 : μ < $100, The population means reimbursements will be less than $100
b) H0 : π <= .10, At least 10% of the reimbursements will be wrong
H1 : π > .10, the amount of wrong reimbursements will be more than 10%

2. Problem 9.33(2 points)

Be sure to set up your hypotheses first. H0always contains the equal sign and the alternative
never does. Data is in the Steel_S13file in your Problem Set folder.
Use PHSTAT – One sample test – for a mean (Need to fill in the hypothesized mean in the top window,
then level of significance (.05), then highlight the data, and last pick 2 tailed, upper or lower depending
upon what you have in your H1 .
Hypothesis
H0: μ = 0.0
H1: μ ≠ 0.0

a) At the 0.05 level of significance, there isn’t sufficient evidence that supports the mean
difference is different from 0.0 inches. The p-Value came out to be 0.41 which is higher
than the level of significance 0.05 which means you do not reject the null hypothesis H 0:
μ=0.0. The sample mean is 0.0 which also supports the null hypothesis. Since the
p-value is 0.41, the actual confidence is 59%, this is less than the required 95%
confidence. This means the overall null hypothesis is equal to H0: μ = 0.0
b) The Interval Lower Limit is equal to -0.00023, and the upper limit 0.0056. We can
be 95% confident that the population mean for steel part length is between
-0.00023 and 0.00056. This is within the accepted length of +/- 0.005 so we don’t
have to reject the null hypothesis.
c) Both intervals contains the hypothesized mean of 0.0, therefore we can conclude
that μ=0.0 and we should use the null hypothesis of H0: μ=0.0
d) Since the kurtosis is outside the range of -1 to 1, the sample size is 100; which is
larger than 30, it is assumed that the data is normally distributed based on the
central limit theorem we learned.
3. Problem 9.57: (1 point) Use 1 sample test – for a proportion. Make sure you state hypotheses and
write up a conclusion stating how confident you are in H1.

H0=0.55
H1≠0.55

We failed to reject the null hypothesis because the p-value is greater than the level of
significance. We are only 13.5% (1-0.8645) confident that there is a statistically
significant difference of the proportions of the females in the medical center to the
general work force. Therefore, there is no evidence that the proportion of females in the
position of the medical center is different from the general workforce.
4. Problem 9.29 (1.5 points)
H0:μ = 45 days
H1:μ ≠ 45 days

No, there is not enough evidence that the meaning processing time has changed from 45
days because we failed to reject the null hypothesis and we are only 18% confident in the
alternate hypothesis.

b. The assumption we need to make about the population distribution in order conduct t
test is that the population needs to be normally distributed or if it’s not normally
distributed, it should not be too skewed and the sample size is not too small.

Descriptive Summary
Time
Mean 43.88888889
Median 45
Mode 17
Minimum 16
Maximum 92
Range 76
Variance 639.2564
Standard Deviation 25.2835
Coe. of Variaon 57.61%
Skewness 0.5173
Kurtosis -0.9041
Count 27
Standard Error 4.8658

d. Yes, the t test is valid because the data is normally distributed.