PUBH7290/7630 Introduction to Biostatistics

Assignment 3 Instructions and Questions

Assignment 3 is a culmination of the information from Topics 1-9. The assignment is 

worth 40% of your overall mark. 

Notice: This assignment is an individual assignment and must be your own 

individual work.

Format of assignment

Use the document provided on Blackboard to create your assignment because 

it is already formatted correctly and has the cover sheet already in it.

• The assignment should be in Word (.doc or.docx) or .pdf format. If working from 

a Mac computer, it is recommended to submit in .pdf format. • Use 2.54cm margins all around and no smaller than 12 size font. 

• Use a common font such as Times New Roman, Arial or Calibri. 

• The first page of your assignment must be the cover sheet. i.e. the cover is 

part of your assignment and not a separate document. Make sure to fill it in with 

the relevant details.

• Your assignment answers must total 10 pages or less. The cover sheet should be 

included in the file as the first page, bringing the total pages to no more than 11 

pages. Follow the individual instructions on page/word limits.

Submission of the assignment

• Students are required to submit their assignments to the Blackboard site via the 

TurnItIn link.

• Name your file by YOURSURNAME_INITIAL_PUBH7630A3 so it would look like 

Darssan_D_PUBH7630A3.doc. If you are an MD student use PUBH7290 

instead of PUBH7630. This is so we can easily match up files to students. If you 

don't name your file correctly, you are making extra work for the marking team, 

which will not put smiles on your markers' faces. Not a good idea to do before the 

markers mark your assignment. 

• Make sure you complete each section of the cover sheet, with the correct course 

name and number, assignment number and title and the course coordinator's 

name. On the cover sheet (which is the first page of your file), you affirm that 

the work is your own, as per the University Academic Integrity and Plagiarism 

policy at http://ppl.app.uq.edu.au/content/3.60.04-student-integrity-and-

misconduct; entering your name on the signature line is an acceptable substitute 

for your signature.

• Please keep a copy of your assignment.

• Please keep a copy of your TurnItIn Digital Submission receipt that you will 

receive by email once you’ve submitted your assignment.

• Once marking starts, the assignment information will be hidden in My Grades 

until marking is complete.

Background 

The Health Information National Trends Survey (HINTS) is a national survey uniquely 

dedicated to learning how people find, use, and understand health information 

(http://hints.cancer.gov/Default.aspx). An information sheet about the study is 

available on the Blackboard site (HINTS_Fact_Sheet.pdf). We will use the data for some 

simple statistical analysis.

Data

You will be using the HINTS 4 (Cycle 2) data to answer the assignment questions. This 

data set and accompanying codebook were updated in 2017. A random sample of size 

1500 was taken in order to simplify data handling. The data are available on Blackboard 

in R binary .Rdata format (A3_2019sem2_hints4_cycle2_sample1500.RData). 

You will need to download and save the data file onto your computer and then LOAD it 

into Rcmdr (Data => Load dataset…)

The codebook for these data is available on the Blackboard site in the file 

HINTS_4_Cycle_2_Codebook_09062017.pdf.

Do NOT print the codebook.

Note that data have not been recoded nor changed in any way but simply read into R by 

first reading in the SPSS format data saved as a text (.csv) file. This will mean the R 

automatically made some variables factors if there was only a small number of values. 

The variable names match those in the codebook. You may find it easier to remove 

variables that you don’t need to make data handing and using the analysis menus more 

manageable.

Finally, you may see reference to analysis using sample weights. While this is common 

in complex surveys, statistical analyses should not be weighted for this assignment.

Assignment 3 Questions

The answers to questions 1-3 must include 

• what data you used (inclusion / exclusion)

• and selection of appropriate statistical measures and why,

• an appropriate presentation of the data in a graph and / or table, 

• statements about assumption testing, and 

• an appropriate conclusion based on a statistical test, with justification in 

text.

Report the p-value to 2 or 3 decimal places (p=0.02, p<0.001, p=0.008 for example) and 

other values to 1 or 2 decimal places or whole numbers if appropriate. There will be 

penalties for going over specified word and page limits.

Analysis questions using HINTS data

These analyses require using several variables from the HINTS4 Cycle 2 data set and 

assessing some relationships between these variables. In particular, you will be testing 

the relationships between BMI and variables measuring screen time and income ranges, 

both as continuous variables or as categorical variables. Since the variables of interest

are provided as either continuous or categorical then the other variable type will need to 

be constructed.

Variable names are in brackets and their details may be found in the codebook.

1. Consider body mass index BMI (BMI) as a continuous variable. Use hours of 

watching television or playing computer games (AverageDailyTVGames) in hours 

per day as a continuous variable to predict BMI. Comment on the similarity or 

otherwise of the relationship between men and women. Gender is (GenderC)

2. We Consider BMI (BMI) as a continuous variable. Is BMI related to annual 

income (IncomeRanges_IMP) when income is considered to be 4 

categories (“$0 to $34,999”, “$35,000 to $99,999”, “$100,000 to $199,999” and 

“$200,000 and above”)? Comment on the similarity or otherwise of the 

relationship between men and women.

3. For both men and women, underweight is BMI < 18.5; healthy weight is BMI >= 

18.5 to <25; overweight is BMI > = 25 to <30; obese is BMI > = 30. Construct a 

categorical variable with these categories from the continuous variable BMI 

(BMI). Analyse the relationship between the BMI categorical variable and Income 

variable with four categories used in Question 2. Interpret your findings.

Maximum 5 pages to answer Questions 1-3.

Questions 1-3 are worth 20% each.

Summary for Questions 1-3

4. Write 200 words describing your overall conclusions from the above analyses in 

Questions 1-3. Comment on the findings. 10%

Data analysis plan

5. Write an analysis plan to examine the relationships between several variables 

from the HINTS4 Cycle 2 participants’ with their reported age using the age 

variable is in 5 categories (AgeGrpB). Consider age group in relation to several 

other variables, namely, gender (GenderC), education (EducA), using the internet 

to look up cancer information (InternetCancerInfoSelf) and BMI category as 

defined in Question 3. Finally, include a brief analysis plan to relate one sleep 

pattern variable, which is the hours per working day (SleepWorkdayHr), with 

continuous BMI (BMI). Use the same PDF codebook as for Questions 1 to 4. This 

is available on Blackboard.

Do NOT do the analysis. 20%

Maximum 4 pages in an outline format for the data analysis plan.

The remaining 10% of marks will be given for stating significance level cut-offs, 

following instructions, using proper grammar and writing, having a clear, 

organised presentation, and referencing appropriately.

Assignment 3 is worth 40% of overall course grade.

Notice: This assignment is an individual assignment and must be your own 

individual work.