Aaron has told me that you will be working on a project to assess the
impact of the 2000 Senior Citizens Freedom to Work Act, which repealed
the earnings test for retirees receiving Social Security benefits.
Two government datasets present themselves as possibilities for investigating this question as they both contain data about individuals' age, income, and Social Security benefits; and both provide cross section data representative of the population of the United States before and after the passing of the legislation. The datasets are the Survey of Income and Program Participation, or SIPP, and the Current Population Survey, or CPS, March Supplement.
You will need to investigate these two datasets, their structure,
methodology, purpose and the variables they contain to decide on one and
use it for analysis. Documentation and metadata are available for this
purpose and are linked below.
Because both of these datasets are very large, you will need to create a subset of the data, pulling just the variables you will need from the whole. To create a subset, you'll use a specialized software called Data Ferret.
Data Ferrett is software that allows for distribution of several government public use microdatasets. You will need to install it (on a Mac) or install a security policy (on a Windows machine) in order to use it. These videos demonstrate the setup process. The videos in the following sections provide detailed instructions for using Data Ferrett to download subsets of the SIPP or the CPS.
Warning: On lab machines, Data Ferrett only works on the Windows side.
Installing and getting started with Data Ferrett:
Go to Data Ferrett.
Step 1: Get to know the dataset and choose your variables.
Video: Understanding the CPS (3:07 min.)
Step 2: Subset and download your data.
Downloading CPS Data with Data Ferrett (on a PC)