Read: An Economist’s Guide to Visualizing Data (JEP, 2014)
A nice intro from Princeton U on the basics of data is here
Data Structures:
Cross-section Data: A group of entities all observed at the same point in time. Read about cross-section data here
Time-series Data: a single entity with data observed over time at a regular frequency. Read about time-series data here
Panel Data: a group of entities observed over time at regular frequency. Read about panel data here
Data File Format:
It is recommended that your data file be stored as a .csv file. This file format is easily read in by all software programs.
Short Video: How to download some data to a CSV file
Missing observations should be denoted with an empty cell, or a single period “.” Do NOT use a zero for missing data.
Data Sources
There are far too many data sources to list here. Below is a sampling of some good resources.
- FRED at Federal Reserve Bank of St. Louis
- Data at the Bureau of Labor Statistics
- Data at the Bureau of Economic Analysis
- WRDS (requires JMU account) – financial data (Compustat and CRSP), Penn World Tables, etc
- World Development Indicators (WDI) country-level data
- IPUMS has census and survey data for the USA and Worl including a easy to use tools to extract data from the Current Population Survey (CPS)
- NBER’s Public Use Data Archive including the Current Population Survey
- Crime data from Uniform Crime Reports, Department of Justice
- Analyze Survey Data for Free: links to many free data sets along with R/SQL code for downloading and reading the data