Skip to Main Content

CUIN 7303 - Professional Seminar I

This guide is intended to introduce you to information and tools relevant to educational research

Downloading and Opening Data

Before you download the data, think about the following:

  • What formats are available?
  • What information do you know about the data.

There are different types of data formats. Common ones are: Comma-separated Value (CSV),Excel,xml, json, spss, sas,etc.Consider what software you have to open the data before downloading.

Tips for troubleshooting any opening and access issues:

  1. Understand the file. Do you have a compatible program to open it? Can I convert it?
  2. Uncompress the file. If you download a compressed file (.zip or .tar .gz), use Winzip or Archive Utility to uncompress first.
  3. Google your issue. If you encounter a problem, search for it. Someone probably encountered the problem already. It's useful to search for the error message, or include some specifics, such as "can't open .tar files".

To find information about the data, you want to look for data documentation. Common types of documentation includes:

  • Codebook, which describes the context, structure and layout of a dataset. It also gives you details about the variables.
  • Data dictionary, which is used to catalog and communicate the structure and content of data.
  • Readme file, usually readme.txt file that outlines information required to use a file.

The example below shows you the data download page from Social Explorer. It gives you different file formats to download, as well as the data dictionary for you to understand the data. Remember to check "output column labels in the first row" when downloading data from Social Explorer. This way, you will see meaningful variable names. If you don't do this, you will have to search in the data dictionary to find out what the code means for your variables. 

This is the data download page for ReferenceUSA. You can select the file format you need. The default is to download the summary data, but if you need more details, choose the custom report to add variables you are interested in.