Essay Depression and Anxiety Disorders During Pregnancy – PICO Format – Research Writing – Statistics Assignment Help

Assignment Task

You will need to use Stata to answer Question 2 and Question 3 (Part c). Other questions can be answered using hand calculations, Microsoft Excel or Stata. Answer all questions and show working where relevant.

Question 1
Depression and anxiety disorders during pregnancy are common and can seriously affect women, their children and their partner. Identifying risk factors for perinatal (from 22 weeks pregnancy until 7 days post-birth) and postnatal (from birth to six weeks post-birth) depression can assist health providers (both general practitioners and obstetricians) to identify high risk women and help guide management choices. Australian researchers were interested in studying a range of risk factors including whether there was an association with family history of depression and anxiety disorders and the onset of depression both in pregnancy and during the postnatal period. Data from a large cross-sectional study found that 15% of pregnant women reported a family history of depression and anxiety. They decided that a prospective cohort study was the most suitable study design to answer the research question. They planned to recruit participants into the cohort through the family birthing centres of local public hospitals in New South Wales on their first appointment at 12 weeks with the centre and follow the participants until six weeks post-birth.
I: Study design and participants
a) Using PICO format, write the research question for this study.
b) What methods should the researchers use to minimise selection bias in the study?
Are there any concerns about selection bias in this study? Provide reasons for the methods you identify and your concerns.

II: Measurement issues
Researchers developed a modified version of the Edinburgh Postnatal Depression Scale (EPDS), a 10 item self-complete screening questionnaire. A score of 13 or more indicates poor wellbeing and is an indication for further testing for depression. Researchers planned to use this questionnaire in the cohort study and ask women to self-complete at 3 time points during pregnancy and 3 time points during the postnatal period and send results via text message to investigators. Before commencing the study, the research team conducted a pilot study to investigate the accuracy of the EPS in classifying patients as depressed against the “gold standard”. The results of the pilot study are shown in Table 1 (below).

III: Data analysis
A cohort study was conducted, 7500 pregnant women were enrolled in the study. A baseline questionnaire collected information on risk factors including a family history of depression and anxiety. Women were followed until 6 weeks post-birth. During the follow-up, 1,480 women reported depression at any time during the follow-up, including 570 in those with a family history of depression and anxiety. Of those without depression during the study period, 19% reported a family history of depression and anxiety.
f) Calculate the cumulative incidence of depression in those exposed to the study factor. Show your working, report and interpret the meaning of the measure you have
calculated.
g) Using the data provided, calculate the proportion of depression in pregnant women that is attributable to a family history of depression and anxiety. Show your working,
report and interpret the meaning of the measure you have calculated. 

Question 2 Part A
Fitbit monitors attach to a person’s wrist and track the number of steps walked per day, the number of stairs climbed and heart rate. A randomised controlled trial was undertaken to investigate whether the use of a Fitbit monitor along with web-based feedback on fitness progress would increase participants' activity levels. Participants were randomised to either use the Fitbit monitor with web-based feedback intervention (group=1) or a control group that used a pedometer measuring number of steps only (group = 0). The participants used the devices for one month. The primary trial outcome was the number of steps on the last day of the trial. The dataset FitbitData.dta has data on all 949 trial participants. Using your dataset:
a) Produce a box plot comparing the number of steps taken between the intervention and control groups. Are there any outliers that need to be dealt with? If so, deal with
them appropriately and describe what you have done as well as the reasons for the
decisions you have made.
b) Produce histograms of the number of steps taken for the intervention and control groups and comment on their shape.

c) Calculate and report relevant descriptive statistics (including the mean and 95% confidence interval) for the number of steps by each group. Interpret the 95% confidence intervals.
d) The primary research question is investigating whether there is a difference in the mean number of steps taken between the intervention and control groups. What is
the most appropriate test to use to investigate the primary research question? Why is this test appropriate?

Question 2 Part B 
Glycated haemoglobin, also called HbA1c, is used in the diagnosis of diabetes. It is used to determine average blood sugar levels over a period of weeks or months. HbA1c can either be expressed as a percentage or in mmol/mol. A health department conducts a study in 667 people who have not been previously diagnosed with diabetes. The dataset diabetes.dta contains two variables:
• id: a unique personal identifier
• hba1c: a person’s HbA1c level measured as a percentage
Normal HbA1c is below 6.0%; pre-diabetes HbA1c is 6.0% to < 6.5%; and diabetes HbA1c is 6.5 % and above.
a) Use an approp a) Write the research question of the study using the PICO format. 
b) What study type have the investigators used? What would be the ideal study type to answer this research question? Why?

c) i) Construct a 2×2 table to display the data on new endometrial cancer cases by BMI category for normal and obese participants. 
ii) Use Stata to calculate the relevant measure of effect (with its 95% confidence interval) to summarise the association between obesity and new endometrial cancer. Interpret the measure of effect and the 95% confidence interval.
d) The investigators analysed the data further to assess whether there was an association between BMI and endometrial cancer. They also wanted to know whether menopausal status was a confounder or effect modifier of the association between BMI and endometrial cancer. They calculated the following values:
i. Premenopausal participants – BMI and endometrial cancer: RR = 1.9
ii. Postmenopausal participants – BMI and endometrial cancer: RR = 3.5
Is menopausal status a confounder or effect modifier of the association between BMI and endometrial cancer? Give reasons for your answer.

Question 3 –

a) Write the research question of the study using the PICO format.
b) What study type have the investigators used? What would be the ideal study type to answer this research question? Why?
c) i) Construct a 2×2 table to display the data on new endometrial cancer cases by BMI category for normal and obese participants. 
ii) Use Stata to calculate the relevant measure of effect (with its 95% confidence interval) to summarise the association between obesity and new endometrial cancer. Interpret the measure of effect and the 95% confidence interval.
d) The investigators analysed the data further to assess whether there was an association between BMI and endometrial cancer. They also wanted to know whether menopausal status was a confounder or effect modifier of the association between BMI and endometrial cancer. They calculated the following values:
i. Premenopausal participants – BMI and endometrial cancer: RR = 1.9
ii. Postmenopausal participants – BMI and endometrial cancer: RR = 3.5