Welcome to the Libraries' Guide to numerical data! This guide is designed to help you find data that you can use in your classes and your research. If this guide does not have the information you are looking for, don't hesitate to email me at email@example.com and I will be happy to help you find what you are looking for.
Recently I've met some people who use the terms "data" and "statistics" interchangeably. But while they are both numeric, they mean different things to researchers and the world of academia.
Data is raw, unadulterated information, like the number of bars in a city, the number of pigs in the state, or the temperature. With statistics, someone has "done something" to the data, or manipulated it in some way. Examples of statistics include the number of bars per person, population density, the average daily temperature.
Data can be expensive and time-consuming to produce and process - often depending on its size, scope, complexity, and available funding. The more people a survey includes, or the more observations that are recorded, the longer it will take for the data to be collected and processed, and the more expensive it is.
Data can also be embargoed. This is a ban on the publication of documents (or in this case data), for security or copyright reasons. Scientists can wait until they have finished analyzing their data before making it available. The US Census does this as well; reports on the changes in the population were available before the data was released to the general public.
Copyright law does not apply to facts, data, or ideas. However, it does apply to their arrangement (as in a data base). But, just because data is not protected by copyright, it does not mean there are not other legal considerations.
The most common is privacy. Research in medicine, sociology, education, and public policy may include information about individuals that is protected either by federal privacy legislation or by commitments made by the researchers who collected it. Attempts to anonymize data before sharing it do not ensure that individual research subjects will not be identifiable, thus compromising privacy. For more information, check out Facts and Data from the University of Michigan.