Secondary Data refers to data that has been collected and gathered by third parties which can be accessed by the researcher. For example, governments compile information about the population when conducting the census. Some agencies also collect and publish data about customer consumption habits.
All of the above are examples of secondary data since they are available to be used by the researcher. The researcher takes no part in the data collection. We now list out some of the merits and demerits of using secondary data for conducting research in statistics.
Advantages of Secondary Data:
- Since the data has already been collected and compiled by third parties, the researcher does not need to spend time or money to collect the data. Even if the data needs to be puirchased from an agency, the effort and cost is less compared to personally collecting the required data.
- It is very convenient for the researcher since a lot of secondary data is available to access freely on the internet.
- Usually any given piece of secondary data has already been analysed many times previously. Looking at the previous analysis allows the researcher to understand the data better and design a better study.
- Secondary data collected by governement authorities encompasses a long period of time. These kinds of data are very helpful for conducting a long term study.
- If the agency collecting the data is reputable, then there is no need to worry about the accuracy and reliability of the data.
- Secondary data is usually collected, compiled and edited under the supervision of subject matter experts. This ensures that the data is accurate and useful.
- Secondary Data can be used to form a preliminary judgement or opinion about a particular phenomena under study.
Disadvantages of Secondary Data:
- The researcher has to inquire about the reliability and integrity of the organization collecting the data. This is a time consuming process for the investigator. If the data collecting organization is not reputable, then any data published by it becomes unreliable.
- Sometimes data collecting agencies have a vested bias and these errors creep into the data. For example, a cigar company might try to collect survey data suggesting that smoking is not harmful to health.
- Even if the collected data is reliable, it might not be edited in a manner useful to the researcher. For example, suppose a researcher requires monthly data. If an agency collects data and publishes it in a year to year format then that data is not very useful to the researcher.
- The published data may not be available for the required time period. For example, if we are given the data regarding the profits of a company 10 years ago then it is not very helpful to allow us to understand the recent performance of the company.
- Sometimes the secondary data compiled by various companies infringes on the right to privacy of consumers. Many companies collect data on consumer habits without informed consent.