primary data and secondary data
What does each and every research project need to get results? Data – or information – to help answer questions, understand a specific issue or support a hypothesis.
At the Institute for Work & Health, researchers conduct many projects each year. Some projects involve going into workplaces and asking workers questions. Researchers who do this have specific work-health questions in mind that they’d like answered.
The answers – or data – used from the responses are called primary data.
Other Institute projects involve using data that has already been gathered by someone else, such as survey information from the Canadian Census. Researchers then examine this information in a different way to find a response to their question. This data are called secondary data.
What are the advantages of using these two types of data? Which tends to take longer to process and which is more expensive? This column will help to explain the differences between primary and secondary data.
Using primary data
An advantage of using primary data is that researchers are collecting information for the specific purposes of their study. In essence, the questions the researchers ask are tailored to elicit the data that will help them with their study. Researchers collect the data themselves, using surveys, interviews and direct observations (such as observing safety practices on a shop floor).
Let’s take an example. In a recent Institute study, researchers wanted to find out about workers’ experiences in return to work after a work-related injury. Part of the research involved interviewing workers by telephone and asking them questions about how long they were off work and about their experiences with the return-to-work process.
The workers’ answers are considered primary data. From this, the researchers got answers to specific information about the return-to-work process including the rates of work accommodation offers, and why some workers refused such an offer.
Using secondary data
There are several types of secondary data. They can include information from the Census, a company’s health and safety records such as their injury rates, or other government statistical information such as the number of workers in different sectors across Canada.
Secondary data tends to be readily available and inexpensive to obtain. In addition, secondary data can be examined over a longer period of time. For example, you can look at a company’s lost-time rates over several years to see at trends.
In the same Institute study mentioned above, the researchers also examined secondary data. They looked at workers’ compensation lost-time claims and the amount of time workers were receiving wage replacement benefits.
With a combination of these two data sources, the researchers were able to determine which factors predicted a shorter work absence among injured workers. This information was shared with return-to-work professionals to help improve return to work for other injured workers.
Both primary data and secondary data have their pros and cons. Primary data offers tailored information but tends to be expensive to conduct and takes a long time to process. Secondary data is usually inexpensive to obtain and can be analyzed in less time. However, because it was gathered for other purposes, you may need to tease out the information to find what you’re looking for.
The type of data researchers choose can depend on many things including the research question, their budget, their skills and available resources. Based on these and other factors, they may choose to use primary data, secondary data - or both.
Source: At Work, Issue 54, Fall 2008: Institute for Work & Health, Toronto