POPH90013 Biostatistics - Short Answer Questions - Assignment Help

The maximum mark for this assignment is 80. It forms 40% of the final grade for this subject. Your assignment should be submitted via Gradescope 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.

This Assignment has 6 short answer questions. You should attempt all questions.

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 files “Assignment4_wound.dta” and “Assignment4_frailty.dta” from Canvas. 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).

Section A - 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 $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 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 section of the assignment you will be using the dataset “Assignment4_wound.dta”, a prospective cohort study of 750 wound patients investigating the risk factors for wound infection, where the patients were given uniform treatment over 12 weeks.

Table 1: Description of the variables in the Assignment4_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)

*All other variables except wound infection (infect) were measured at hospital admission.

Question 1 [18 marks]

Some common risk factors for wound infection are age, sex, stress, diabetes, obesity, high alcohol consumption and smoking.

1. Provide a table (in a format that would be acceptable for a report or journal article) that summarises the distribution of the outcome of interest wound infection and the potential risk factors, age (years), sex, stress (units), diabetes, body mass index (BMI, kg/m²), alcohol consumption (ml/week) and smoking. Describe the study population using this table. [3 marks]

One of the research questions of this study was to explore if smokers were more susceptible to wound infection. From related literature the study investigators were able to further identify that a patient’s sex may confound the association between smoking and wound infection. The directed acyclic diagram (DAG) is shown below.

1. Calculate using Stata and interpret, the unadjusted odds ratio for the association between smoking (smoke) and wound infection (infect). Write down the Stata command you used to obtain this odds ratio as [2 marks]

1. Calculate using Stata, and interpret the adjusted odds ratio, corresponding 95% confidence interval for the population odds ratio and the two-sided p-value for the association between smoking (smoke) and wound infection (infect), adjusted for sex (sex_male). Write down the Stata command you used to obtain these results as [4 marks]

1. After analysing the association between wound infection, smoking and sex, the study investigators have claimed that sex does not confound the association between smoking and wound infection in this study. Do you agree with this claim? Investigate the validity of this claim by comparing the unadjusted and adjusted odds ratios calculated in Questions 1b and And explore the associations between the exposure and confounder, and outcome and confounder to explain your observations. [5 marks]
2. A group of investigators want to design a randomised controlled trial to explore the effect of a smoking cessation intervention on wound Wound patients who smoke at least 10

cigarettes per day will be randomly assigned in a 1:1 ratio to either abstain from smoking (i.e., the intervention group) or continue their usual smoking patterns (i.e., the control group). The investigators have estimated the proportion of wound infections among participants continuing their usual smoking patterns to be similar to the proportion of wound infections among smokers in the current study population. They are interested in detecting an absolute reduction of 15% in the proportion of wound infections among participants abstaining from smoking. Using Stata, calculate the sample size required for this new study assuming a significance level of 5% and a power of 90%. Write down the Stata command you used to calculate this sample size as well. [4 marks]

Question 2 [14 marks]

The study investigators were interested in analysing the cross-sectional hospital admission data on type II diabetes (diab) and stress scores (stress), and exploring whether patients with type II diabetes had increased stress levels. From related literature the study investigators were able to further identify that a patient’s body mass index (BMI) may confound the association between type II diabetes and stress. The directed acyclic diagram (DAG) is shown below.

1. Provide a graph visualising the association between stress and type II diabetes, and comment on the association. [3 marks]

1. Using Stata, fit a linear regression model to obtain an estimate for the unadjusted association between stress and type II diabetes, and provide an interpretation for this [2 marks]

Participants with a BMI of at least 25 kg/m² are considered to be overweight/obese. Using the bmi variable, generate a new binary variable named bmi_bin as; participants with a BMI less than 25 kg/m² [coded as 0, “Normal”] and participants with a BMI of at least 25 kg/m² [coded as 1, “Overweight/Obese”]. Use this new binary variable bmi_bin for BMI in Questions 2c, 2d and 2e.

1. Using Stata, obtain the frequency and proportion of patients who are overweight/obese in this study. Write down the Stata command you used to obtain this proportion as well. [3 marks]

1. Using Stata, fit a linear regression model to obtain the adjusted association between the outcome stress score, exposure type II diabetes and confounder BMI. Interpret the adjusted association for stress and type II diabetes using the estimate, corresponding 95% confidence interval and p-value. Write down the Stata command you used to obtain these results as [3 marks]
2. Comment on whether the association between stress and type II diabetes is confounded by BMI in this study, by comparing the unadjusted and the adjusted estimates calculated in Questions 2b and Use the additional information provided below on the associations

between the outcome and confounder, and exposure and confounder to explain your observations. [3 marks]

• The estimated mean difference in the stress score between patients with overweight/obesity compared to patients with a normal BMI is -0.08 units (95% CI: - 45, 0.28 units, p-value=0.649).
• The proportion of patients with type II diabetes among those with a normal BMI is 122 (20.57%) and those with overweight/obesity is 30 (21.58%).

Section B - Frailty Dataset

Frailty is a state of vulnerability resulting from a decline in physical and cognitive capabilities. Particularly in surgical and intensive care unit (ICU) patients, frailty predisposes to poor outcomes. Frailty is more prevalent among older patients and is associated with increased mortality, length of stay in hospital and post-operative complications.

For this section of the assignment you will be using the dataset “Assignment4_frailty.dta”, a random sample of 150 patients from an observational cohort study conducted in Melbourne. The aim of this study was to explore the risk factors for frailty and the association between frailty and other health outcomes.

Table 2. Description of the variables in the Assignment4_frailty.dta dataset.

Variable name	Description
id	Study participant identification number
sex_female	Sex (0 – Male, 1 – Female)
age	Age (years)
weight	Body weight (kg)
height	Height (cm)
adm_source_cat	Admission source (0 – Home, 1 – Other hospital, 2 – Assisted living)
adm_source_bin	Admission source (0 – Home, 1 – Other hospital/Assisted living)
frailtyindex	Frailty indexa
frailtyindex_bin	Frailty (0 – Non-frail, 1 – Frail)
diabetes	Diabetes with end organ damage (0 – No, 1 – Yes)
renal	Acute renal impairment (0 – No, 1 – Yes)
icuadm	Unplanned admission to ICU, CCU or HDU (0 – No, 1 – Yes)
woundinfection	Wound infection (0 – No, 1 – Yes)

CCU = Critical care unit; HDU - High dependency unit; ICU = Intensive care unit

^aThe frailty index is a score between 0 and 1, with 1 indicating a higher rate of physical and cognitive decline.

Question 3 [19 marks]

The primary aim of this study was to identify risk factors for frailty. Some common risk factors for frailty are sex, age, obesity and admission source.

1. Generate a new variable for body mass index (BMI, kg/m²), named bmi, using weight and height. Write down the Stata command you used to create this new variable bmi. What is the average BMI in this study population? [2 marks]

1. Provide graphs visualising the associations between the outcome of interest frailty (frailtyindex) and the potential risk factors, sex (sex_female), age (age), BMI (bmi), and admission source (adm_source_cat), and briefly comment on these associations. [5 marks]

The study investigators wanted to explore how a patient’s frailty (frailtyindex, units) varied with their BMI (bmi, kg/m²). From related literature the investigators were able to identify that admission source (adm_source_bin) may confound the association between BMI and frailty. The directed acyclic diagram (DAG) is shown below.

1. Using Stata, fit a linear regression model to obtain an estimate for the unadjusted association between frailty and BMI, and provide an interpretation for this estimate. Write down the Stata command you used to fit this regression model as [2 marks]
2. Using Stata, fit a linear regression model to obtain an estimate for the adjusted association between the outcome frailty, exposure BMI and confounder admission source, and provide an interpretation for this estimate. Write down the Stata command you used to fit this regression model as [2 marks]
3. Comment on whether the association between frailty and BMI is confounded by admission source in this study, by comparing the unadjusted and the adjusted estimates calculated in Questions 3c and 3d. Explore the associations between the exposure and confounder, and outcome and confounder to explain your [4 marks]
4. Write a statistical methods section similar to what is presented in research papers explaining the methods you have used for the statistical analyses in Questions 3a to 3e (max. 150 words). [4 marks]

Question 4 [16 marks]

One of the research questions of this study was to explore if patients with frailty were more susceptible to diabetes with end organ damage. From related literature the study investigators were able to further identify that a patient’s age may confound the association between frailty and diabetes with end organ damage. The directed acyclic diagram (DAG) is shown below.

Using the age variable, generate a new binary variable named age_bin as; patients aged less than 75 years [coded as 0, “< 75 years”] and patients aged at least 75 years [coded as 1, “≥ 75 years”]. Use this new binary variable age_bin for age in Question 4.

1. Visualise the unadjusted association between frailty (frailtyindex_bin) and diabetes with end organ damage (diabetes) by completing the 2×2 table [2 marks]

Frailty	Diabetes with end organ damage		Total
	Yes	No
Frail (Group 1)
Non-frail (Group 0)
Total

 

1. Calculate by hand and interpret, the unadjusted odds ratio for the association between frailty and diabetes with end organ damage. [3 marks]

1. Visualise the association between frailty and diabetes with end organ damage, stratified by age by completing the table below. [2 marks]

Frailty	Age < 75 years		Age ≥ 75 years
	Diabetes with end organ damage		Diabetes with end organ damage
	Yes	No	Yes	No
Frail (Group 1)
Non-frail (Group 0)

Total

 

1. Calculate by hand and interpret, the odds ratio for the association between frailty and diabetes with end organ damage separately for patients aged < 75 years and patients aged ≥

75 years. How do the stratum-specific odds ratios compare with each other and the unadjusted odds ratio calculated in Question 4b? [3 marks]

1. Calculate by hand and interpret, the Mantel-Haenszel estimate of the pooled odds ratio for the association between frailty and diabetes with end organ damage, adjusted for age. [4 marks]
2. Comment on whether the association between frailty and diabetes with end organ damage is confounded by age in this study, by comparing the unadjusted and the adjusted odds ratios calculated in Questions 4b and [2 marks]

Question 5 [10 marks]

One of the research questions of this study was to explore if patients living at home were more susceptible to unplanned admissions to the ICU, CCU or HDU.

1. Using Stata, obtain the frequency and proportion of patients with unplanned admissions (icuadm) to the ICU, CCU or HDU, separately for patients living (adm_source_bin) at home and patients living in other hospitals or assisted living facilities at admission in this Write down the Stata command you used to obtain these proportions as well. [2 marks]

1. Calculate using Stata, and interpret the odds ratio, corresponding 95% confidence interval for the population odds ratio and the two-sided p-value for the unadjusted association between admission source (adm_source_bin) and unplanned admissions to the ICU, CCU or HDU (icuadm). Write down the Stata command you used to obtain these results as [4 marks]

1. Based on the results of this study, a group of investigators in Australia want to conduct a cross-sectional study to determine the population proportion of unplanned admissions to the ICU, CCU or HDU for patients living in hospitals or assisted living facilities. Calculate by hand, the sample size required to obtain an estimate of the population proportion of unplanned admissions to the ICU, CCU or HDU with a precision of ±5%. [4 marks]

Question 6 [3 marks]

Please provide a copy of your Stata do-file for performing the statistical analyses for this Assignment, both sections A and B. Do not upload a second file when submitting your assignment, instead copy and paste the Stata do-file commands to your assignment word document prior to converting to PDF.