HOMEWORK

I. Multiple Choices Questions

1. Because 25 percent of the students in my morning statistics class watch
eight or more hours of television a week, I conclude that 25 percent of all
students at the university watch eight or more hours of television a week.
The most important logical weakness of this conclusion would be
A) Relying on a sample instead of surveying every student.
B) Using a sample that may not be representative of all students.
C) Failing to correct for unconscious interviewer bias.
D) assuming cause and effect where none exists.
2. Which two levels of measurement do quantitative variables use?
A) Ordinal and ratio
B) Interval and ordinal
C) Nominal and ordinal
D) Interval and ratio
3. From its 32 regions, the FAA selects 6 regions, and then randomly audits 25
departing commercial flights in each region for compliance with legal fuel
and weight requirements. This is an example of
A) Simple Random Sampling
B) Stratified Random Sampling
C) Cluster Sampling
D) Judgment Sampling
4. The Centers for Disease Control and Prevention (CDC) wants to estimate the
average extra hospital stay that occurs when heart surgery patients
experience postoperative atrial fibrillation. They divide the United States
into nine regions. In each region, hospitals are selected at random within
each hospital size group (small, medium, large). In each hospital, heart
surgery patients are sampled according to known percentages by age group
(under 50, 50 to 64, 65 and over) and gender (male, female). This
procedure combines which sampling methods?
A) Systematic, simple random, and convenience
B) Convenience, systematic, and judgment
C) Cluster, stratified, and simple random
D) Judgment, systematic, and simple random
II. Essay Questions:
Question 1. Sleep plays a crucial role in both physical and mental development,
particularly during adolescence. According to research conducted by the Central
Health Bureau, the optimal time for sleep falls between 10:00 and 11:00 PM. This
recommendation is based on the body's natural circadian rhythm, during which
essential hormones such as melatonin and growth hormone are most actively
secreted. These hormones facilitate cellular repair, cognitive restoration, and
overall physiological recovery, ensuring optimal health and function (National
Sleep Foundation, 2022).
A study led by Dr. David Walker and colleagues further underscores the
importance of early sleep onset for adolescents, recommending they go to bed
before 11:00 PM to maximize cognitive and neurological benefits. The study,
conducted on a sample of 3,000 adolescents aged 11 to 18 living in the U.S.,
focused on this specific age group due to its critical phase of physiological
development. During this age period, teenagers undergo significant hormonal
changes and face increasing academic pressures, both of which contribute to a
high risk of sleep deprivation (According to a previous study by Walker, 2017).
Findings from the study revealed that 68% of participants habitually slept past
11:00 PM. Those in this late-sleep group frequently reported symptoms such as
migraines, difficulty concentrating, memory decline, and heightened irritability.
Furthermore, when subjected to comprehensive mental health evaluations—
including assessments of attention span and cognitive performance—their
average scores were a mere 6 out of 10, highlighting the detrimental effects of
late-night sleep patterns on mental and cognitive well-being (Carskadon, 2011).
To further examine the impact of improved sleep habits, researchers conducted a
one-month intervention requiring late sleepers to adjust their bedtime to before
11:00 PM while minimizing exposure to blue light from electronic devices before
sleep. The results were striking: participants demonstrated notable improvements
in cognitive function and overall well-being. Their average scores on cognitive and
attentional assessments increased to 8 out of 10, and many reported feeling more
alert, experiencing fewer headaches, and maintaining greater focus in their
studies.
These findings reaffirm the critical role of nighttime sleep in adolescent health,
highlighting its profound impact on cognitive function, psychological stability, and
long-term physical well-being. Ensuring sufficient and timely sleep is not merely a
matter of habit but a fundamental necessity for overall development. As such,
parents, educators, and adolescents themselves must recognize the significance
of healthy sleep practices and foster routines that support optimal rest, thereby
promoting a balanced and productive lifestyle.
(a) What is the sample and the population of the research conducted by
Dr. David Walker?
 Sample: 3,000 adolescents aged 11 to 18 living in the U.S.
 Population: All adolescents aged 11 to 18 living in the U.S.
(b) What is (are) the sampling method(s) used in this study?
 Judgment Sample, Stratified Sample
(c) What is (are) the level of measurement(s) employed in this survey?
 Nominal Measurement – Qualitative (Findings from the study revealed that
68% of participants habitually slept past 11:00 PM: Phân loại theo nhóm
ngủ muộn và ngủ sớm)
 Interval Measurement – Quantitative
(d) Why should use the sampling method(s) that you find above in this
study?
Use Judgment Sampling to increase the reliability of a sample dataset because
selecting samples based on expert advice enhances data credibility. Use Stratified
Sampling to ensure that the sample's bias is minimized as much as possible.
(e) Based on the study's results, the researchers concluded that late-
night sleep negatively affects cognitive performance. What type of
statistical inference technique would be appropriate to validate this
conclusion? Justify your answer.
Hypothesis Testing: Hypothesis testing is a statistical method used to make
decisions or inferences about a population parameter based on sample data. It
involves testing an assumption (hypothesis) by comparing sample data to what is
expected under that assumption.
H0: Late-night sleep negatively affects
H1: Late-night sleep positively affects  Sampling  Consider whether the
statistic contradict with the claim (H 0)  Consider whether evidence is persuative.

H0: Null (Claim/Statament of someone, organization, or an article about 1

parameter)
H1: Alternative GPA <3.5  Sampling  GPA of sample = 3.3

Null Hypothesis (H₀) – A statement of no effect or no difference. It assumes the

status quo.
Alternative Hypothesis (H₁ or Ha) – A statement that contradicts the null
hypothesis, suggesting an effect or difference.
Significance Level (α) – The probability of rejecting H₀ when it is actually true
(Type I error). Common values: 0.05 or 0.01.
Test Statistic – A value computed from the sample data used to decide whether to
reject H₀ (e.g., Z, t, χ²).
Decision Rule – A criterion based on α and the test statistic that determines
whether to reject H₀.

Conclusion – Based on the decision, either reject or fail to reject H₀ and interpret
the results.
Question 2. Interest rates are among the most critical economic factors
influencing borrowing and lending behaviors in financial markets. When interest
rates fluctuate, they not only affect consumer borrowing decisions but also shape
lending policies implemented by commercial banks. However, the extent to which
interest rates impact different types of loans and demographic groups varies
significantly, introducing complexities in analyzing their true economic effects.
A study conducted by Dr. Dallas James and colleagues aimed to examine the
impact of interest rates on consumer borrowing behavior and repayment capacity
in the U.S. financial market. The research utilized a dataset comprising 7,500
borrowers from financial institutions between 2021 and 2023, covering various
loan categories, including mortgages, auto loans, personal loans, and credit card
debt.
To gather data, the research team employed multiple methods, including online
surveys (CONVENIENCE), in-person interviews, and an analysis of credit records
(JUDGMENT) from major banks. Specifically, 3,200 participants responded to
online surveys, 2,500 were selected from the credit records of three large banks
(STRATIFIED) and the remaining participants were interviewed directly. Notably,
a portion of the online survey data contained incomplete or inaccurate responses
due to participant misunderstanding or dishonesty.
Preliminary findings indicated that when interest rates increased from 3% to 6%
(INTERVAL), the volume of mortgage applications declined by 28%, while auto
loan applications fell by 15%. Surprisingly, personal loan applications increased by
9% during the same period. Moreover, individuals with credit scores below 650
(based on the FICO credit rating system) experienced a 12% rise in delinquency
rates under high-interest conditions, whereas borrowers with credit scores above
750 exhibited minimal impact.
Age-based analysis yielded unexpected results: borrowing activity among
individuals aged 25–34 dropped significantly (by 32%), whereas individuals over
50 demonstrated little to no change in their borrowing behavior. This discrepancy
could reflect differences in interest rate sensitivity across income groups, or it
may be influenced by unexamined factors not accounted for in the study.
However, some financial experts argue that merely observing correlations
between interest rates and borrowing behavior is insufficient to establish
causality. Other factors, such as inflation, tax policies, household income, and
consumer sentiment, could play crucial roles in shaping financial decisions. To
address potential confounding variables, the research team proposed a
multivariate analysis model to control for external influences, though the
complete findings have yet to be released.
(a) Identify the sample and the population in this study.
Sample: 7,500 borrowers from financial institutions between 2021 and 2023
Population: All borrowers from financial institutions between 2021 and 2023
(b) What sampling method(s) was (were) used in this study?
Convenience Sample, Judgment Sample, Stratified Sample
(c) What levels of measurement were applied to the variables in
this study (Nominal, Ordinal, Interval, Ratio)?
Nominal Measurement, Ordinal Measurement, Interval Measurement
III. Text Book Question
Questions: 2.29 to 2.41, 2.43, 2.44, 2.52, 2.61
 KEY VERSION
I. Multiple Choices Questions
1. Because 25 percent of the students in my morning statistics class watch
eight or more hours of television a week, I conclude that 25 percent of all
students at the university watch eight or more hours of television a week.
The most important logical weakness of this conclusion would be A) relying
on a sample instead of surveying every student. B) using a sample that
may not be representative of all students. C) failing to correct for
unconscious interviewer bias. D) assuming cause and effect where none
exists.
2. Which two levels of measurement do quantitative variables use? A) Ordinal
and ratio B) Interval and ordinal C) Nominal and ordinal D) Interval and
ratio
3. From its 32 regions, the FAA selects 6 regions, and then randomly audits 25
departing commercial flights in each region for compliance with legal fuel
and weight requirements. This is an example of A) simple random sampling.
B) stratified random sampling. C) cluster sampling. D) judgment
sampling. entity
4. The Centers for Disease Control and Prevention (CDC) wants to estimate the
average extra hospital stay that occurs when heart surgery patients
experience postoperative atrial fibrillation. They divide the United States
into nine regions. In each region, hospitals are selected at random within
each hospital size group (small, medium, large). In each hospital, heart
surgery patients are sampled according to known percentages by age group
(under 50, 50 to 64, 65 and over) and gender (male, female). This
procedure combines which sampling methods? A) Systematic, simple
random, and convenience B) Convenience, systematic, and judgment C)
Cluster, stratified, and simple random D) Judgment, systematic, and
simple random
II. Essay Questions:
Question 1. Sleep plays a crucial role in both physical and mental development,
particularly during adolescence. According to research conducted by the Central
Health Bureau, the optimal time for sleep falls between 10:00 and 11:00 PM. This
recommendation is based on the body's natural circadian rhythm, during which
essential hormones such as melatonin and growth hormone are most actively
secreted. These hormones facilitate cellular repair, cognitive restoration, and
overall physiological recovery, ensuring optimal health and function (National
Sleep Foundation, 2022).
A study led by Dr. David Walker and colleagues further underscores the
importance of early sleep onset for adolescents, recommending they go to bed
before 11:00 PM to maximize cognitive and neurological benefits. The study,
conducted on a sample of 3,000 adolescents aged 11 to 18 living in the U.S.,
focused on this specific age group due to its critical phase of physiological
development. During this age period, teenagers undergo significant hormonal
changes and face increasing academic pressures, both of which contribute to a
high risk of sleep deprivation (According to a previous study by Walker,
2017).
Findings from the study revealed that 68% of participants habitually slept past
11:00 PM. Those in this late-sleep group frequently reported symptoms such as
migraines, difficulty concentrating, memory decline, and heightened irritability.
Furthermore, when subjected to comprehensive mental health evaluations—
including assessments of attention span and cognitive performance—their
average scores were a mere 6 out of 10, highlighting the detrimental effects of
late-night sleep patterns on mental and cognitive well-being (Carskadon, 2011).
To further examine the impact of improved sleep habits, researchers conducted a
one-month intervention requiring late sleepers to adjust their bedtime to before
11:00 PM while minimizing exposure to blue light from electronic devices before
sleep. The results were striking participants demonstrated notable improvements
in cognitive function and overall well-being. Their average scores on cognitive and
attentional assessments increased to 8 out of 10, and many reported feelings
more alert, experiencing fewer headaches, and maintaining greater focus in their
studies.
These findings reaffirm the critical role of nighttime sleep in adolescent health,
highlighting its profound impact on cognitive function, psychological stability, and
long-term physical well-being. Ensuring sufficient and timely sleep is not merely a
matter of habit but a fundamental necessity for overall development. As such,
parents, educators, and adolescents themselves must recognize the significance
of healthy sleep practices and foster routines that support optimal rest, thereby
promoting a balanced and productive lifestyle.
(a) What is the sample and the population of the research conducted by Dr. David
Walker?
Sample: 3,000 adolescents aged 11 to 18 living in the U.S
Population: All adolescents aged 11 to 18 living in the U.S
(b) What is (are) the sampling method(s) used in this study?
Judgment sample, Stratified sample
(c) What is(are) the level of measurement(s) employed in this survey?
Nominal, Interval
(d) Why should you use the sampling method(s) that you find above in this study?
(e) Based on the study's results, the researchers concluded that late-night sleep
negatively affects cognitive performance. What type of statistical inference
technique would be appropriate to validate this conclusion? Justify your answer.
Hypothesis Testing
H0: Null (claim/statement của ai đó/ tổ chức/ tờ báo) GPA >=3.5
H1: Alternative GPA <3.5 -> sampling -> GPA of sample = 3.3
Hypothesis testing
Question 2. Interest rates are among the most critical economic factors
influencing borrowing and lending behaviors in financial markets. When interest
rates fluctuate, they not only affect consumer borrowing decisions but also shape
lending policies implemented by commercial banks. However, the extent to which
interest rates impact different types of loans and demographic groups varies
significantly, introducing complexities in analyzing their true economic effects.
A study conducted by Dr. Dallas James and colleagues aimed to examine the
impact of interest rates on consumer borrowing behavior and repayment capacity
in the U.S. financial market. The research utilized a dataset comprising 7,700
borrowers from financial institutions between 2021 and 2023, covering various
loan categories, including mortgages, auto loans, personal loans, and credit
card debt.
To gather data, the research team employed multiple methods, including
online surveys (Convenience), in-person interviews, and an analysis of credit
records (judgment) from major banks. Specifically, 3,200 participants
responded to online surveys, 2,500 were selected from the credit records of
three large banks and the remaining participants were interviewed directly.
Notably, a portion of the online survey data contained incomplete or inaccurate
responses due to participant misunderstanding or dishonesty.
Vay cực nhiều =
Vay nhiều =
Vay ít
Vay cực ít
Preliminary findings indicated that when interest rates increased from 3% to 6%
(interval), the volume of mortgage applications declined by 28%, while auto loan
applications fell by 15%. Surprisingly, personal loan applications increased by 9%
during the same period. Moreover, individuals with credit scores below 650 (based
on the FICO credit rating system) experienced a 12% rise in delinquency rates
under high-interest conditions, whereas borrowers with credit scores above 750
exhibited minimal impact.
Age-based analysis yielded unexpected results: borrowing activity among
individuals aged 25–34 dropped significantly (by 32%), whereas individuals over
50 demonstrated little to no change in their borrowing behavior. This discrepancy
could reflect differences in interest rate sensitivity across income groups, or it
may be influenced by unexamined factors not accounted for in the study.
However, some financial experts argue that merely observing correlations
between interest rates and borrowing behavior is insufficient to establish
causality. Other factors, such as inflation, tax policies, household income, and
consumer sentiment, could play crucial roles in shaping financial decisions. To
address potential confounding variables, the research team proposed a
multivariate analysis model to control for external influences, though the
complete findings have yet to be released.
(a) Identify the sample and the population in this study.
Sample: 7,700 borrowers from financial institutions between 2021 and
2023
Population: All borrowers from financial institutions between 2021 and
2023
(b) What sampling method(s) was (were) used in this study?
Convenience sample, Judgment Sampling, Stratified Random Sampling
(c) What levels of measurement were applied to the variables in this study
(nominal, ordinal, interval, ratio)?
Ratio, Interval, Nominal
III. Text Book Question
Questions: 2.29 to 2.41, 2.43, 2.44, 2.52, 2.61
Income=β 1∗Education+ β 2∗Age+ β 3∗exp+ β 4∗Gender + β 0 + μi ,t → ¿ Effect Model ( FEM )

OLS = crossectional (EXCEL)

REM (Random Effect Model )= time series
FEM = Panel data
STATA
SEM  Structural Equation Modeling (BRM)
Intercept or Y-Intercept
Khi Education = 0 (không đi học) thì Income = β 0
β 1=Slope→ Khi education tăng hoặc giảm , sẽ gây ra sự thay đổitỉ lệ với Income

μi ,t =unobserved factors +timeinvariant factors