Homework 1

Due: 2025-01-22, 11:59pm

Submission instructions

This and all subsequent homework should be submitted only on Blackboard.

  • Introduction should be posted on Discussion board.
  • Blood pressure analysis should be posted as a ZIP file and attached to homework.

1. Introduction (50%)

Post an introduction on discussion forum. You should cover the following:

  • Mention what you do or study (program, department, field).
  • Why do you want to take the class? What do you hope to learn?
  • What is your past experience with R and programming languages in general? Did you take BIOE805 or an equivalent course?
  • What is your past experience with statistics and biostatistics?
  • Are there any special techniques or ideas you would like us to cover in this class?

2. Predicting blood pressure using age and sex from Southeastern Chinese cohort (50%)

This is a simple project to revisit material from the previous class (BIOE805) using data from Luo and colleagues collected in a retrospective cohort study in Southeastern China.

ZIP folder directions:

  • Create a folder on your computer called FirstnameLastname-BIOE806-HW01 (use your name instead of “FirstnameLastname”). Inside that create two folders called data and analysis.
  • Download the README and the CSV files from the most recent version of the data. Put these in the data folder.
  • Analyze the data and create a report using a RMarkdown (RMD) or Jupyter (IPYNB) format. If using RMD, put the RMD and HTML report in analysis folder. If using IPYNB, then put that file in the analysis folder.
  • Zip the FirstnameLastname-BIOE806-HW01 folder and attach it to your homework submission on Blackboard.

Filesystem structure:

     FirstnameLastname-BIOE806-HW01 
          - data
              - README.md
              - datafile.csv
          - analysis
              - analysis.Rmd
              - analysis.html
              - analysis.ipynb

Analysis directions:

  • Read in the data, and use the README file to get the variable names.
  • Make univariate displays of the age, sex, and systolic blood pressure distributions (use appropriate figures).
  • Make bivariate displays of age, sex, and systolic blood pressure (you can use the pairs function, for example).
  • Develop a prediction model for systolic blood pressure using age and sex as predictors.
  • How good is the model for such prediction? Do you find this model useful?

Note that the analysis directions leave room for interpretation. Use your best judgement and explain your choices.

3. Acknowledgements

Cite resources or individuals helping you.