Definition Secondary data

Secondary data are data, which cannot be traced back to the level of individual cases of statistical units. In contrast to primary data it does not allow for mathematical calculations such as determining an arithmetic mean, a correlation, etc.

An example:

In a survey 10,000 people were questioned about how many hours during a week they practice sports. The raw data (or primary data) set consists of 10,000 specific answers stating the amount of hours each person practices sports. An example of a secondary data set would be a table showing how many people have put in 0-2 hours, 3-4 hours, etc. of physical activities.

While we can calculate a correct arithmetic mean for the sample, the table with the secondary data will only allow us an approximation. If there were 500 people who fell into the category '0-2 hours', the table would give us no information about exactly how many people stated '0 hours'. 

Please note that the definitions in our statistics encyclopedia are simplified explanations of terms. Our goal is to make the definitions accessible for a broad audience; thus it is possible that some definitions do not adhere entirely to scientific standards.