Please take a look at the attached documents as they contain crucial information to enable you to complete this task satisfactorily.
The main task:
(see attached: Summative Assessment Template)
(Tasks 1, 2 and 3 [Option A or B])
Due date: 2 May 2023
Please refer to the Assessment
Guides for each Task for further detail if needed. Some instructions to
help you are added throughout this template. Please delete once you have added
in your work. The final submission should be submitted as document, in PDF or
Word.)
TASK 1:
1.
Present all four selected papers: quantitative,
peer-reviewed, primary research journal articles that are relevant to
statistical analysis in Public Health relating to any Public Health topic of
your choice. These must be either Randomised Control Trials, Cohort Studies,
Cross-Sectional Studies or Case-Control Studies.
2.
First give the reference for the paper, then outline
the aim of the study, the research design, and critique the analysis used and
the findings from each study. The following questions can be used as a guide
for what information to include:
What is the aim of the study?
The study type (cross-sectional, randomised control trial)?
Briefly explain the type of quantitative study being reviewed (Reference)
Is this study type appropriate (Reference)?
Any significance or limitation of the study type? (reference)
Population of the participants in the study?
What was the sampling type used?
Sample size calculation and how recruitment was done, is it appropriate?
Strength and limitation of such sampling and recruitment approach used
(reference needed)
What analysis used? Is it appropriate?
What is the result reported?
Do you have explanation for why the result is what it is?
Is there any similar study that
can be used to explain the result from this study?
Why are they different?
Your brief conclusion.
(Word count: Approximately 250)
References (give any further references that you
draw from to support the summary for each paper before going on to summarise
the next paper):
1
2
(Repeat
for all 4 Papers)
TASK 2:
3.
Select and explain four of the key terms from
Task 2 (see Task 2 folder).
Key term 1:
What is the definition of the key term? Is there
another way to define the key term? (reference needed). Explain what is the
use/strength/function of the key term in quantitative research? (Reference
needed). Explain disadvantage or limitation of key terms (if available).
Present your understanding of the key term. How can studies incorporate the key
terms in quantitative research (if possible)?
(Word count: Approximately 200)
References: (add supporting references after each definition)
1
2
3
TASK 3:
(For
Task 3 choose Option A or B. You do not need to do both. Please delete the
Option that you didn’t choose.)
Task 3, Option
A
Statistical
Analysis Exercise Observational study
The data
presented below is one of the 3 tasks to be completed for the assessment for
this module. This will focus on task 3a in your assessment guide.
Task 3 (Option
A) Data analysis
You have been
asked to analyse the data presented, make clear justification for the
statistical test and summarise your analysis (800 words).
Label this task
as Task 3 in your assessment submission. All answers should be clearly labelled
and show workings carried out as needed.
1. A
cruise ship from Canada to the UK carrying 900 people was quarantined for
possible infection with a deadly virus. All passengers on board were tested for
the virus, 200 of these people tested positive for the virus.
I.
Estimate the prevalence of the virus in the
people on the cruise ship and provide 95% confidence level for the estimate.
2.
40% of the people on the
cruise ship wore protective face mask
throughout their time on
the ship, 15% of these people tested positive to the virus.
I.
Construct a well labelled two-way
table for the data derived from the 900 people on the cruise ship.
II.
Estimate the odd ratio, risk ratio, risk difference for those who did not wear face mask on the ship compared
to those that wore the face mask.
III.
A statistician performs
a 𝑡− 𝑡est analysis and
obtained a p-value
of 0.005 between the group that wore and those
that did not wear the face mask, what does this mean?
3. Face
mask is now a very scarce commodity in Singapore, it was suggested that
families with higher socio-economic status are more likely to have access to
face mask and are more likely to get immediate treatment. Families were grouped
into three socioeconomic (high, medium and low) categories.
I.
Suggest appropriate test to check for
differences between the three high, medium
and the low socioeconomic groups.
II.
State hypotheses for testing differences between
these groups
III.
Explain how to test for differences between
groups and using the sample of test
suggested in 1, what will be the interpretation of the findings if
IV.
Significant result was obtained
V.
insignificant result was obtained
1b A statistician wants to perform a
research to investigate if there is a difference between Male and female
participants in a study using coffee. A researcher collected sample of test
scores from male and female university students. The research aimed to
determine if there is a difference
between male and female test scores using SPSS analysis software (400 words).
I.
What are the considerations required to choose
an appropriate statistical tests in
SPSS.
II.
What statistical test will you recommend for the
researcher to determine differences between male and female test score in SPSS
III.
State the Null and alternative hypothesis for
the suggested test in II.
IV.
If the researcher performs the suggested test in
(II) using SPSS and the software flagged a p-value of 0.001, what does this
mean in regards to the hypothesis for the
test.
V.
The researcher wrongly
rejected null hypothesis when null hypothesis was true, what type
of error has the researcher made. Explain your
answer.
Task 3, Option
B
Data Analysis Exercise using SPSS
Following the instruction on your assessment page, a
data analysis is expected following the instructions below.
Data Set
A data set is
posted on Moodle which presents information on
sample collected from subjects in relation to the influence of coffee intake on
test score among University students. This data has been presented in Excel
format; you are encouraged to export this into SPSS where you will carry out
the analysis recommended in this task. Gender Category: 1 = Male, 2 = Female
(800 words excluding tables and graphs).
Research question
Is there any
difference between score_before and score_after? Is there any association
between age and test score (after)?
Here are some considerations for this task
·
Consider the research questions presented above carefully.
·
Think about the presented data carefully
·
Check if the data need to be subdivided further
Perform the following analysis
Calculate statistical analysis you
think is appropriate for this data set
·
Check for normalcy in the data set
·
What is your null hypothesis based on each
research question?
·
What is the alternate hypothesis based on these
research questions?
·
Identify any outliers (by scanning and/or using
boxplots) for test score_after and age. Replace any outliers with 65 (test
score) and 25 (age). Use relevant literature to explain what is an
outlier and how to manage them.
·
Using your findings from the normalcy check,
decide on whether to use a parametric or non- parametric test.
·
Explain why you have chosen this test.
·
What is the parametric version or the
non-parametric version of the test you have
chosen?
·
Run the statistical analysis for your chosen
tests in SPSS.
· Explain and summarise your findings in relation to the research
questions, make use of
appropriate graphs and tables generated in the analysis for your explanation
3b Use the 2×2
table to answer the questions below (400 words)
With Virus X (Cases)
Without Virus X (Controls)
Total
Exposed
89
Non-Exposed
37
205
Total
600
I.
Complete the given table as required.
II.
Using the 2 x 2 table,
calculate the following for this infection: Risk Ratio, Risk Difference and Odds Ratio
Explain your
findings appropriately.
Use the following as a source for the work (Harvard Reference style and in-text citation).
Walker, J., & Almond, P. (2010). Interpreting
statistical findings: a guide for health professionals and students.
McGraw-Hill Education (UK).
Marston, L. (2009). Introductory statistics for health and
nursing using SPSS. Sage (UK).
Martin, W.E. and Bridgmon, K.D., 2012. Quantitative and
statistical research methods: From hypothesis to results (Vol. 42). John Wiley
& Sons.
Dancey, C. P., & Reidy, J. (2014). Statistics without
maths for psychology. Harlow, England. (Available as an Ebook)
Gordon, R. A. (2012). Applied statistics for the social and
health sciences. Routledge.
Horton, L. A. (2012). Calculating and reporting healthcare
statistics. Ahima Press.
Pallant, J. (2016). SPSS survival manual. McGraw-Hill
Education, UK. (Available as an Ebook)
Martin, E & Bridgmon, K.
(2012) Quantitative and Statistical Research Methods from Hypothesis to
Results. Chichester : Wiley 2012 (Available as an Ebook)
E-BOOK
Interpreting Statistical Findings: a Guide for Health
Professionals and Students
Walker, Jan; Almond, Palo • 2010
Foster, L., Diamond, I., and Jefferies., J. 2015.
Beginning Statistics. An
Introduction for Social Scientists.
Second Edition. London: Sage
Publications.
Marston, L.
2010. Introductory Statistics for
Health and Nursing Using SPSS. London:
Sage Publications.
Balnaves M. Caputi P. 2001 Introduction to Quantitative
Research Methods London: Sage.
