I'm looking for a data set of US citizens/residents, etc. With data on things such as age, geographic location, gender, income, marital status, etc. The more the better. Where can I find an appropriate set of data? A sample population made up of individuals.
-
2Does it have to be current? The US census doesn't release data on individuals for 72 years : census.gov/history/www/genealogy/decennial_census_records/…– JoeCommented May 27, 2015 at 21:59
-
That's the case for identifiable data. Is that really needed here? For "anonymised" data the situation is different ...– Maître PeseurCommented May 28, 2015 at 6:24
-
@AndréPeseur : is anything really anonymized? The census releases aggregated data earlier (for a given area, number of people that fit into various groupings), but I don't believe that they break it down specifically to individuals. And let's be honest -- if the info were up to date, this info is significantly valuable to companies (marketing) and criminals (scam artists and identity thieves). Odds are, any company that has this data is selling it, not just giving it away.– JoeCommented May 28, 2015 at 9:28
-
Of course, we could troll about anonymisation and wether it is possible at all. But what I mean here by anonymised data, is data where you remove information that allows to identify individuals. This includes names, adresses, birthdays ... And yes, you can obtain such data at the individual level. See e.g opendata.stackexchange.com/questions/5339/… or opendata.stackexchange.com/questions/5338/…– Maître PeseurCommented May 28, 2015 at 11:04
-
1maybe start at asdfree.com– Anthony DamicoCommented May 29, 2015 at 5:34
2 Answers
Integrated Public Use Microdata Series (IPUMS USA) is a pretty amazing data source. It is one of the largest public tools for individual level data in the world. It allows you to extract data from previous census years as well as across census years. Many many variable choices are available including age, geographic location, gender, income, marital status
as well as many others.
-
1This was pretty much going to be my suggestion for the anonymized data. I do highly recommend use of this resource which transforms Decennial Census Short Form , Decennial Census Long Form, and American Community Survey data.– KotebiyaCommented May 31, 2015 at 13:36
State voter files are a source for data about residents who have registered to vote. This data gives name, address, age, and sometimes more (like party affiliation) for millions of people. Economic demographics would have to be infered by matching to census blocks.
For example, the Ohio Secretary of State site hosts data here:
http://www2.sos.state.oh.us/pls/voter/f?p=111:1
Not all states have public voter data, for example, the state of Wisconsin.