Go to app
GuidesResearch methodsData sources in research: A quick guide

Data sources in research: A quick guide

Last updated

18 April 2023


Dovetail Editorial Team

Reviewed by

Cathy Heath

The key to performing quality research is to begin with good data. No matter how you bend the conclusions, your research will be fatally flawed if the data is faulty.

Whether researching for a school or academic project, to advance medical science, or to discover historical treasures, you must understand what a data source is and why data sources are important. 

Analyze all your data in one place

Uncover hidden nuggets in all types of qualitative data when you analyze it in Dovetail

Analyze with Dovetail

What is a data source?

A data source is any location where you can find facts, figures, or other relevant information to support your research. You may create your own data source through experimentation, surveys, or observations, or you may choose to use data produced by other researchers. Both methods have advantages and disadvantages, depending on your research and the quality of the existing data you can find. 

In the digital age, finding data sources has become much easier, though whether those sources will meet your research goals needs to be thoroughly investigated.

Finding reliable data sources, understanding how appropriate they are to your research, and then citing them is the researcher’s responsibility. 

How do you identify data sources?

Data sources should be identified from their primary sources using bibliographic referencing. Those sources found in government, academic, and non-profit data repositories are often considered the most reliable in terms of quality. 

How do you select data sources?

You should select data sources based on relevance, reliability, context, and perspective. Selecting poor data sources will ruin your chances of a successful research outcome. Think of the coding phrase: "Garbage in, garbage out."

Data sources versus reference sources

Reference sources are often a great place for researchers to begin their studies before they start taking a deeper dive into data sources to back up their own research. Reference sources offer a more expansive overview of a topic as they refer to conclusions from previous researchers’ studies. 

In contrast, data sources provide the facts and figures that can drive research forward and uncover new insights. 

Why are data sources important?

In most research, you start with a hypothesis and seek to find data to support that hypothesis, or you start with an open mind about a conclusion and follow the data to where it leads. In either case, you need a large enough data set to draw conclusions and data that are relevant and accurate. 

In any academic, medical, or historical field, your research will be subject to review by your peers, so data sources are important. Others must be able to repeat your research and come to the same conclusions or at least understand why you came to the conclusions. 

Examples of sources of data

Data sources abound in nearly every field of research. Databases from governmental (.gov), academic (.edu), and non-profit (.org) sources are considered more reliable than those from commercial enterprises due to possible bias—but some data from commercial areas is valid and useful. 

If undertaking medical research, you can find databases from the National Institutes of Health, the Centers for Disease Control, the Federal Drug Administration, and more. These sources would be considered more authoritative than something you might find on WebMD or Wikipedia. However, you’ll also find solid research through university websites or medical facilities, such as the Mayo Clinic or MD Anderson Cancer Center. 

Researchers doing historical work can access reliable data through similar sources, such as the National Archives (.gov), the Smithsonian Institution (.edu), and many academic sites from universities and colleges. 

They might also find information through presidential libraries, national and local historical societies, and media and business databases. 

If economic research is your thing, the Federal Reserve, the Department of Labor, and academic sites provide large research databases. Or, if you're into politics, you can source data from county voting records, state election departments, and even polling organizations such as Gallup or Harris. 

How many sources of data are there?

Thousands of data sources exist, but the key is finding relevant and factual data sources to meet your research goals. 

Types of data sources

Data sources can be split into two categories: primary and secondary. Both are valid resources, depending on the type of research you’re conducting. 

Primary data sources

When a researcher or research team develops their data from experimentation, surveys, or observation, these are classified as primary data sources. This research generates its own new data sets to support specific research.  

Direct quantitative measurements

Experiments by researchers generate quantitative measurements in a lab, nature, or other controlled environments to test specific outcomes. For example, if agricultural researchers want to see how a certain crop grows under various conditions, they create an environment that mimics those conditions and quantifies the outcomes. 

In such a case, the researchers must report how they created the conditions and measured the outcome.

In social sciences, researchers craft surveys or questionnaires to judge how people would respond to a situation. These researchers would be responsible for sampling a representative population and preparing questions without bias. 


Observational researchers might count the number of species in a given environment or look at how environmental changes might affect a given species. Social researchers also use observational techniques to judge how people react to various situations. 

The advantages of primary data sources

Primary data offers the advantage of giving researchers control over their entire environment and the flexibility to adapt their experiments when necessary. They can also provide answers to a new or novel situation that has never existed. 

For example, when testing a newly invented medicine, researchers must experiment with animals or humans to discover its effectiveness and safety outside the test tube. They have no specific historical data to fall back on, so primary research, like a clinical trial, starts to build knowledge about that particular medicine. 

Secondary data sources

Secondary data sources are those produced from previous research. In our digital world, secondary data is readily available through online databases maintained by hundreds of organizations. Using secondary data sources is less costly than primary data research and offers the advantage of speed since researchers don't need to wait for the data to play out—it's readily available. 

Researchers, however, must judge whether the data applies to their particular research question, as they must account for potential bias, location, demographics, etc. The data also must be well-sourced and reliable for the researcher to make those judgments. 

Databases and data repositories

Any number of agencies, organizations, or commercial enterprises maintain databases and data repositories. These generally are secure environments, with some behind paywalls, and are maintained and updated as new data becomes available.   

Using publicly available data sources

Publicly available data sources abound on the Internet, allowing researchers to access information quickly. Many of these data repositories are maintained by government agencies or non-profit groups created to represent certain fields of study, such as biomedical research or physics. 

It’s the role of the researcher to observe the terms of use for the data and check the methodology employed in the research to ensure it matches their research criteria. 

Understanding the context around the data

Any researcher must understand the context behind a data source before they adopt it into their research. The date of when the research was conducted, the population surveyed, and the location are key pieces of information a researcher must consider. For example, biomedical research that is ten years old might contain little useful information because the field has changed so dramatically. 

But the researcher must also understand who conducted the primary research, what their motives were, and how they took their measurements. All this context would affect how the researcher can apply the data to current research. 

Perspectives on data sources to bear in mind

Researchers should craft "inclusion criteria" for what data sources will be acceptable. These rules will ensure they understand the perspective of any data sources used for the research. 

Sources with a more extensive data set will be more reliable and fit better into new research.

Should you be using a customer insights hub?

Do you want to discover previous research faster?

Do you share your research findings with others?

Do you analyze research data?

Start for free today, add your research, and get to key insights faster

Get Dovetail free

Editor’s picks

What is a good example of a conceptual framework?

Last updated: 18 April 2023

What is a cross-sectional study?

Last updated: 6 February 2023

What is face validity?

Last updated: 5 February 2023

Diary study templates

Last updated: 13 May 2024

Related topics

User experience (UX)Product developmentMarket researchPatient experienceCustomer researchSurveysResearch methodsEmployee experience

Decide what to build next

Decide what to build next

Get Dovetail free


OverviewAnalysisInsightsIntegrationsEnterpriseChannelsMagicPricingLog in


About us
© Dovetail Research Pty. Ltd.
TermsPrivacy Policy

Log in or sign up

Get started for free


By clicking “Continue with Google / Email” you agree to our User Terms of Service and Privacy Policy