Biostatistics POPH90013 - 2021
Assignment 3 – Special Consideration
Due: Tue 5th Dec, 9:00 am.
The maximum mark for this assignment is 60. It forms 30% of the final grade for this subject. Your
assignment should be emailed to your subject coordinator (nadia.kaunein@unimelb.edu.au) as a
PDF document.
Please put your student ID number in the header of the document.
Unless you are asked to do so, please do not include any Stata output in your assignment
document. Instead, format any results you want to show in a way that would be suitable for
inclusion in a report or journal article.
For questions where you are asked to calculate the answers by hand, please show your workings.
For this assessment, you will need to download and open the file “Assignment3_wound.dta”.
Also, we recommend that you perform all Stata tasks via a do-file (you can use the do-files from
the Stata practicals located on Canvas, as a guide).
2
Wound Healing Dataset
The Wound Healing Society defines a chronic wound as one that has failed to proceed through
an orderly and timely reparative process to produce anatomic and functional integrity within an
expected period. Chronic wounds represent a significant annual burden on the Australian health
care system, with direct health care costs reaching US$2.85 billion. Several factors can interfere
with one or more phases of the wound healing process, thus causing improper or impaired
wound healing. Such factors include infection, age, stress, diabetes, obesity, medications,
alcoholism, smoking, and nutrition. A better understanding of the influence of these factors on
repair may lead to therapeutics that improve wound healing and resolve impaired wounds.
For this assignment you will be using the dataset “Assignment3_wound.dta”, a new hypothetical
study with 839 participants investigating the association between wound healing and alcoholism.
As part of the study, wound patients were sampled from a randomly selected hospital and given
uniform treatment over 12 weeks.
Table 1: Description of the variables in the Assignment3_wound.dta dataset
Variable name Description
id Study participant identification number
age Age (years)
sex_male Sex (0 – Female, 1 – Male)
bmi Body mass index (kg/m2)
smoke Smoking status (0 – Non-smoker, 1 – Smoker)
alc Alcohol consumption per week (ml/week)
stress Stress score (units, Range: 0 - No stress, 10 - Maximum stress)
diab Type II diabetes (0 – No, 1 – Yes)
infect Was the wound infected at any time in twelve weeks? (0 – No, 1 – Yes)
3
Question 1 [14 marks]
Wound infections are common among smokers. In this question we will explore the association
between smoking (smoke) and wound infection (infect).
a) Calculate by hand, the odds of wound infection separately for smokers and non-smokers. [4
marks]
b) Calculate by hand, the odds ratio for the association between smoking and wound infection. [2
marks]
c) Calculate by hand, the 95% confidence interval for the population odds ratio for the association
between smoking and wound infection. [Hint: Use Stata to obtain the number of participants in
each group, for example, number of smokers with wound infection etc. required for this
calculation.] [5 marks]
d) Interpret the estimated odds ratio for the association between smoking and wound infection and
the corresponding 95% confidence interval for the population odds ratio calculated above, and
comment on the association between smoking and wound infection. [3 marks]
4
Question 2 [13 marks]
One of the key research questions of this study was to explore if participants with high alcohol
consumption were more susceptible to wound infections.
Participants who drink at least the average amount of alcohol per week (i.e., estimated to be 186
ml/week) are considered to have a high alcohol consumption. Generate a binary variable for high
alcohol consumption named high_alc which categorises alc into two groups; participants
with an alcohol consumption of at least 186 ml/week [coded as 1, “High”] and participants with
an alcohol consumption of less than 186 ml/week [coded as 0, “Low”]. Use this new binary
variable high_alc for alcohol consumption in Question 2.
a) Calculate using Stata, the frequency and proportion of participants with wound infection
separately for those with a high alcohol consumption and a low alcohol consumption in this
study. Write down the Stata command you used to obtain these proportions. [5 marks]
b) Using Stata, obtain an estimate for the population risk difference in wound infection between
those with high alcohol consumption and those with low alcohol consumption, the 95%
confidence interval for the population risk difference and the two-sided p-value for the null
hypothesis of no difference in the population risk of wound infection between those with high
alcohol consumption and those with low alcohol consumption. Write down the Stata command
you used to obtain these results. [4 marks]
c) Interpret the estimated risk difference in wound infection between those with high alcohol
consumption and those with low alcohol consumption, the corresponding 95% confidence
interval for the population risk difference and the p-value you obtained from Stata, and comment
on the association between alcohol consumption and wound infection. [4 marks]
5
Question 3 [8 marks]
The study investigators were interested in exploring whether participants with type II diabetes
(diab) had increased stress levels (stress).
a) Conduct an unpaired t-test in Stata and obtain the difference in the mean stress score between
participants with type II diabetes and participants without type II diabetes, the corresponding
95% confidence interval for the population mean difference and the p-value for the null
hypothesis of no difference in the population mean stress score between participants with type
II diabetes and participants without type II diabetes. Write down the Stata command you used
to obtain these results. [4 marks]
b) Interpret the estimated mean difference in the stress score between patients with type II
diabetes and patients without type II diabetes, the corresponding 95% confidence interval for
the population mean difference and the p-value you obtained from the unpaired t-test above,
and comment on the association between type II diabetes and stress levels. [4 marks]
6
Question 4 [20 marks]
Type II diabetes is a known risk factor of wound infections. In this question we will explore the
association between type II diabetes (diab) and wound infections (infect).
a) Visualise the association between type II diabetes and wound infections by completing the 2×2
table below. [2 marks]
Type II diabetes
Wound infection
Total
Yes No
Yes (Group 1)
No (Group 0)
Total
b) Calculate by hand, the risk of wound infection (i.e., the proportion of participants with wound
infection) for those with and without type II diabetes. [4 marks]
c) Calculate by hand, the difference in the risk of wound infection between those with type II
diabetes and those without type II diabetes in this study. [3 marks]
d) Calculate by hand, the standard error for the sample risk difference in wound infection between
those with type II diabetes and those without type II diabetes in this study. [4 marks]
e) Calculate by hand, the 95% confidence interval for the population risk difference in wound
infection between those with type II diabetes and those without type II diabetes. [4 marks]
f) Interpret the estimated risk difference in wound infection between those with type II diabetes
and those without type II diabetes and the corresponding 95% confidence interval for the
population risk difference calculated above, and comment on the association between type II
diabetes and wound infection. [3 marks]
7
Question 5 [5 marks]
Smoking is a known risk factor of type II diabetes and smoking further complicates managing type
II diabetes and regulating insulin levels. After analysing the association between smoking
(smoke) and type II diabetes (diab) in this study the investigators have claimed that smokers
are more likely to develop type II diabetes than non-smokers.
Investigate the validity of this claim by calculating the odds ratio for the association between
smoking and type II diabetes, the 95% confidence interval for the population odds ratio and a
two-sided p-value for the null hypothesis of no difference in the population odds of type II
diabetes between smokers and non-smokers using Stata. Interpret your results and comment on
whether you agree or not with the claim made by the investigators.