Data is collected by organizations, businesses, and government agencies. Some is available for free on the web; some is sold. Examples of "free" data on the web include:
Box office and other information about movies
It's possible to go scouting for data to see what you can find.
One method is to go to the research database called Academic Search Premier [see below for link], and try some searches for lists.
Example 1.
a. search for: list AND 500
b. The idea is to see if you can find an article about a list (of anything) that has 500 items, such as the "Fortune 500" companies.
c. With the above search, I found a Green List 500 of companies provided by Newsweek. To see the list and variables associated with it,
d. search Google for: newsweek "green list" 500
Example 2.
a. search for: list AND best
b. the idea is to get lists of the best (of anything).
c. With the search I found a list of the best public golf courses in all 50 states.
d. When I looked over the list, it had over 300 golf courses. However, no associated variables were provided.
e. To gather variables, I would need to google each golf course individually or search the library catalog for a golf course directory with more detail or search google for a source of details about individual golf course. In google, I might try a search for : golf courses united states [and then hunt in the results for directories or other sites that compile information on lots of golf courses]