Statistical data can be broadly classified into two parts: primary and secondary on the basis of the source of the data.
- 1.) Primary Data: The statistical data which are collected by the investigator for his own interest or use by himself are the primary data. These data are obviously original.
Suppose you are interested in measuring your height, measure your height using a scale . These data are primary to you.
These data are more reliable and you can use it being sure that these are genuine, since you yourself have collected these data. These are easy to use for you since you yourself organised these data.
The limitation of these data is that it is not always possible for one to collect all the data directly from the spot since there are resource, money, time and feasibility constraints.
2.) Secondary Data: Statistical data which is not directly collected by the investigator but collected from another source, who had collected the data for their own use are called secondary data.
In this kind of data the collector and the user of data are different and also the purpose. These are not original data as the user do not collects the data directly.
Data collected from some survey-results for some research work is the secondary data to the research scholar.
The main advantage of these kind of data is the convenience to collect it. These data saves a lot of money, man power and time.
But secondary data have some serious drawbacks. The main drawback is that secondary data contains errors since it is collected from another source which may not be reliable and also since the purpose was different. While using these data, the user must be careful about making the data error free and relevant.
It is obvious that same data primary to one may be secondary for another one.