This milestone involves:
Keep an eye on how other papers present their summary statistics (typically it is Table 1) and you might find some to model your table on.
Organize your folders and start to document what you do with the data. This may involve a considerable amount of time, so plan accordingly. The goal is to clean each individual dataset, and then merge them together to create a single dataset (“analysis dataset”.)
Have a separate DO file to clean each dataset. Then have one DO file that merges all the datasets together.
For an example of how to do all this in STATA, see Application 6 - Data Cleaning
At this stage, you’ll want all of your DO files used for cleaning and merging that are well documented and organized. Put this in your DO folder in Google Drive.
Summary statistics typically include “Table 1” which presents the
variables you will be using in your analysis, the number of observations
for each variable, and the mean, SD, min, and max. If there are two
distinct groups that you are comparing (i.e: treatment and control), you
can present summary statistics for each group. I am happy to provide
guidance on what your table should look like.
Every thesis is different, and so you should feel free to include
additional figures or tables that you believe highlight important
aspects of your data.
See examples of “Table 1: Summary Statistics” at the end of this document.
Submit a table via Slack DM to me by the deadline. Your Google Drive folder should contain all the DO files that allow me to replicate your results.