Secondary data analysis
Secondary data analysis is the analysis of data from other sources.
Sometimes it is easier to take data from another source than to collect the data yourself. For example, the addresses of a districts in a neighborhood are easier to retrieve from the population register of the city than to walk through all the houses to write down the names of the residents. Patient data can be taken from the patient file more easily than by re-examining the patient. The turnover of a company from day to day is easier to get from the business administration than to register all sales again.
There can be two obstacles in obtaining this type of data: the data has not yet been collected or the data is not available. The population registers sometimes lag behind, and not everyone has access to that information. Confidential information from patients is difficult to obtain anyway. Often an informed consent must first be signed, stating that the patient gives permission to copy the data from his file.
Although it seems easy to copy the data, it often still has many snags. Sometimes the data is hidden in the files and sometimes the data has to be retyped. With the latter, mistakes can easily be made and that is a form of bias. Therefore, these data must be thoroughly checked before they can be subjected to the (secondary) analyzes.