Upload your Final Project here

100 points

The goal of the final is for you to use the material we learned in Biostat 212 to take raw data and turn it into a publishable product.  This will require understanding the data, developing a research question, importing the data into Stata, generating derived variables that you will use for your analysis, labeling your variables, doing the analysis, saving and documenting your analysis, and producing a table and figure that readers can understand. In keeping with the spirit of TICR, we hope you will take advantage of this opportunity to analyze your own data, and produce a table and figure that you can use in a manuscript.

Create a publication quality tableand figure: 

Create a table, formatted as required for submission to an appropriate journal, complete with title, headings, data, and footnotes (including spelled-out versions of all abbreviations and other notes as needed to clarify meaning or methodology). You can create the table using MarkDoc with thetblcommand or use taboutto generate LaTeX code or export directly into a word document.  

Use commands that export your data directly into a table (avoid copying and pasting cells)

Create a figureof quality suitable for submission to a journal.  This should be produced within Stata. The figure should have a legend, title and a note. The reader should be able to easily understand the figure without any outside information.  

Turn in: 

A PDF, html OR DocX with both your commands, the table and the figure. 

Your .do file

An example final project is posted on the course website

You will not be graded on the data-prep/data cleaning steps. It’s your choice if you want to include it in the document you turn in. 

You can use MarkDoc and/or LaTeX to create your final document. 

A note on data sets:

If you do not have access to your own data, please ask for some from your mentor. If your mentor does not have any data you can look for publicly available datasets.

Use a health-related data set (not auto.dta!)

Do not use NHANES, as we use it a lot in class