Business Statistics Assignment 3

1) Texas is home to more than one million undocumented immigrants,

and most of them are stuck in low-paying jobs. Meanwhile, the state also
suffers from a lack of skilled workers. The Texas Workforce
Commission estimates that 133,000 jobs are currently unfilled, many
because employers cannot find qualified applicants (The Boston Globe,
September 29, 2011). Texas was the first state to pass a law that allows
children of undocumented immigrants to pay in-state college tuition
rates if they have lived in Texas for three years and plan to become
permanent residents. The law passed easily back in 2001 because most
legislators believed that producing college graduates and keeping them
in Texas benefits the business community. In addition, since college
graduates earn more money, they also provide the state with more
revenue. Carol Capaldo wishes to estimate the mean hourly wages of
workers with various levels of education. She collects a sample of the
hourly wages (in $) of 30 workers with a bachelor’s degree or higher, 30
workers with only a high school diploma, and 30 workers who did not
finish high school. (data is in excel file named Assignment3_data, sheet
name: Texas_Wages)
In a report, use the information to
a)Calculate descriptive statistics to compare the hourly wages for the
three education levels.
b)Construct and interpret 95% confidence intervals for the mean
hourly wages at each education level.
Bachelor's Degree High School Diploma No High School Diploma

22.50 12.68 11.21

19.57 11.23 8.54

24.13 19.53 12.52

27.23 9.85 9.06

27.00 15.76 14.21

28.60 12.31 13.40

16.85 12.27 11.46

22.70 8.57 11.22

26.69 11.06 9.56

20.14 11.47 9.43

21.33 13.38 10.98

18.33 9.85 10.41

17.86 12.35 11.73

20.47 10.68 8.28

21.08 10.70 8.59

17.05 11.54 13.30

21.70 13.55 7.91

22.19 17.80 12.28

23.80 15.70 10.72

22.30 17.50 15.97

22.42 6.50 10.58

22.29 8.98 9.59

27.43 12.14 10.92

23.14 8.83 9.70

22.84 13.02 7.64

21.86 8.90 10.39

29.32 13.80 4.62

26.00 21.67 13.04

30.53 8.74 6.29

21.44 7.47 10.27

A. Given n=30,

For bachelor’s degree or higher

Mean( X̄ )= 22.96
Standard deviation (σ )= 3.562.
For high school diploma
Mean (X̄) = 12.26
Standard deviation(σ) = 3.5517.
For no high school
Mean (X̄) = 10.46
Standard deviation (σ) = 2.369.

B) given confidence interval =95%, α = 0.05, df= n-1 = 29

Calculating using normal distribution, Zα/2 = Z0.025 = 1.96 (using z
distribution table)
For bachelor’s degree or higher
X̄ ± Zα/2 σ/√n = 22.96 ± 1.96(3.562/√30)
= (21.65, 24.234)
Hence the lower confidence interval is 21.65 and the higher confidence
level is 24.234 for mean hourly wages with bachelor’s degree or higher.
For high school diploma,
X̄ ± Zα/2 σ/√n = 12.26 ± 1.96(3.552/√30)
= (10.98, 13.53)
Hence the lower confidence interval is 10.98 and the higher confidence
level is 13.53 for mean hourly wages with only high school diploma.
For no high school,
Confidence intervals of mean hourly wages is given by
X̄ ± Zα/2 σ/√n = 10.46 ± 1.96(2.369/√30)
= (9.61, 11.307)
Hence the lower confidence interval is 9.61 and the higher confidence
level is 11.307 for mean hourly wages with no high school.

2) The information gathered from opinion polls and political surveys is

becoming so increasingly important for candidates on the campaign trail
that it is hard to imagine an election that lacks extensive polling. An
NBC News / Wall Street Journal survey (August 5-9, 2010) of 1,000
adults asked people’s preferences on candidates and issues prior to the
midterm 2010 elections. Some of the responses to the survey are shown
below, as well as responses from prior surveys. (Copyright © 2010 Dow
Jones & Co., Inc.)

Question: In general, do you approve or disapprove of the way Barack

Obama is handling the aftermath of the Gulf Coast oil spill in August
2010 (and George W. Bush’s handling of Katrina in March 2006)?

August 2010 (%) March 2006 (%)

Approve 50 36
Disapprove 38 53
Not sure 12 11

Question: Which are more important to you in your vote for Congress
this November: domestic issues such as the economy, health care, and
immigration; or international issues such as Afghanistan, Iran, and
terrorism?

August 2010 (%) September 2006 (%)

Domestic issues 73 43
International issues 12 28
Both equally important 15 28

In a report, construct 95% confidence intervals for the relevant

population proportions to
a)Compare the approval rates of President Obama’s handling of the
Gulf Coast oil spill and President George W. Bush’s handling of the
Hurricane Katrina crisis.
 b)Compare the importance of domestic issues in August 2010 and
in September 2006

A)
given, confidence interval = 95% and n=1000. Hence α = 0.05
Zα/2 = Z0.025 = 1.96 (using z distribution table)
Population proportion for 95% confidence interval is given by,
p̄ ± 1.96(√ (p̄ (1- p̄)/n)
Gulf coast oil spill handled by Obama in August 2010, approved by 50%
people,
p̄ = 0.50 , n=1000
= 0.50 ± 1.96(√(0.50(1-0.50)/1000)
=(0.4695, 0.5305)
Gulf coast oil spill handled by Bush in March 2006, approved by 36%
people,
p̄ = 0.36, n=1000
= 0.36 ± 1.96(√ (0.36(1-0.36)/1000)
= (0.3302, 0.3897)
Hence, we can be 95% confident that the approval rates for handling
Hurricane by Obama lies in the range (0.47,0.53) and by Bush lies in the
range (0.33,0.39). That is approval rates is more for Obama.

B)
Importance of domestic issues in August 2010, voted by 73% people,
p̄ = 0.73, n=1000
= 0.73 ± 1.96(√ (0.73(1-0.73)/1000)
= (0.7024, 0.7575)
 Importance of domestic issues in September 2006, voted by 43%
people,
p̄ = 0.43, n=1000
= 0.43 ± 1.96(√ (0.43(1-0.43)/1000)
= (0.3993, 0.4606)
Hence, we can be 95% confident that the importance of domestic issues
in August 2010 lies in the range (0.7,0.75) and in September 2006 lies in
the range (0.4,0.46). That is the importance given increased from 2006
to 2010.

3) The effort to reward city students for passing Advanced Placement

tests is part of a growing trend nationally and internationally. Financial
incentives are offered to lift attendance and achievement rates. One such
program in Dallas, Texas, offers $100 for every Advanced Placement
test on which a student gets a score of 3 or higher (Reuters, September
20, 2010). A wealthy entrepreneur decides to experiment with the same
idea of rewarding students to enhance performance, but in Chicago. He
offers monetary incentives to students at an inner-city high school. Due
to this incentive, 122 students take the Advancement Placement tests.
Twelve students get a 5, the highest possible score. There are 49 students
with scores of 3 and 4, and 61 students with failing scores of 1 and 2.
Historically, about 100 of these tests are taken at this school each year,
where 8% of students score 5, 38% score 3 and4, and remaining get
failing scores of 1 and 2.

In a report, use the sample information to

a) Provide a descriptive analysis of student achievement on Advanced
Placement before and after the monetary incentive is offered.
b) Conduct a hypothesis test that determines, at the 5% significance
level, whether the monetary incentive has resulted in a higher proportion
of scores of 5, the highest possible score.
c) Conduct a hypothesis test that determines, at the 5% significance
level, whether the monetary incentive has decreased the proportion of
failing scores of 1 and 2.
d) Assess the effectiveness of monetary incentives in improving student
achievement.

A) Given that 122 students taken part in advancement test due to

incentive,
The descriptive analysis can be given as,
Proportion of score 5,
Before incentive, 8%
pₒ = 0.08
After incentive, 12/122
p̄ = 0.0983
Proportion of scores 3 & 4,
Before incentive, 38%
pₒ = 0.38
After incentive, 49/122
p̄ = 0.4016
Proportion of failing scores 1 & 2,
Before incentive, 54%
pₒ = 0.54
After incentive, 61/122
p̄ = 0.50
B) n=122, significance level is 5% hence, α = 0.05
Using Right-tail Hypotheses test for score 5,
Hₒ: pₒ≤0.08 vs HA: pₒ>0.08 and p̄ = 0.0983
Z = (p̄-pₒ)/(√(pₒ(1-pₒ))/n) (using central limit theorem for sample
proportion)
= (0.0983-0.08)/ (√ (0.08(1-0.08)/122))
=0.745
p-value = P(Z≥0.745) = 1- P(Z≤0.745)
= 1- 0.7734 = 0.2266
Here, p-value > α. therefore, by p-value approach, we accept the null
hypotheses i.e.; cannot reject Hₒ.
Hence, at 5% significance level, we conclude that less than 8% students
score 5.

C)
Using Left-tail Hypotheses test for score 1 & 2,
Hₒ: pₒ≥0.54 vs HA: pₒ<0.54 and p̄ = 0.5
Z = (p̄-pₒ)/(√(pₒ(1-pₒ))/n) (using central limit theorem for sample
proportion)
= (0.5-0.54)/ (√ (0.54(1-0.54)/122))
= -0.886

p-value = P(Z<-0.886)
= 0.1867
Here, p-value > α. therefore, by p-value approach, we accept the null
hypotheses
i.e.; cannot reject Hₒ.
Hence, at 5% significance level, we conclude that more than 54%
students score 1 or 2.
D)
From above, I can summarize that monetary incentives have neither
resulted in decreasing the proportion of failing scores of 1 & 2 nor
resulted in increasing the higher proportion of score 5. Hence, we can
say that the monetary incentives in improving student achievement have
no or very less effectiveness.