Exploratory vs. confirmatory research: which is right for your study?
Research is about discovery. It’s about testing ideas and finding answers to burning questions. Through this, we can better understand the world and solve its problems, big and small.
But not all approaches to research are the same. In fact, there are two distinct types you need to be aware of – exploratory and confirmatory.
And it’s vitally important that you can tell the two apart.
In this post, we’ll explain why getting them confused is so dangerous and show you how to decide which is the best choice for your study.
Firstly, how do you choose between exploratory vs. confirmatory research? While it depends on the type of study you want to conduct, it’s also important to have a clear understanding of the two options.
As it sounds, exploratory research is about exploring a subject. You’re not testing a specific hypothesis here. Researchers usually explore an idea before confirming it. This gives them a broader understanding of the topic.
Exploratory research is especially useful if you’re studying a topic that doesn’t have a long history of empirical research behind it. It can be a great starting point to find potential connections between variables. You can form a hypothesis with these to confirm or deny in future research.
Exploratory research is more open than confirmatory research. This means you’ve got more scope to discover new information that you might have otherwise missed.
It's possible to corrupt exploratory research. According to The Royal Statistical Society, one way this can happen is through “fudging”. This is where a researcher “fudges” (edits) a hypothesis so that it fits the data. For example, a researcher might add new details to a hypothesis to accommodate contradictory data. Instead, they should acknowledge how the data questions the hypothesis.
In contrast, confirmatory research tests specific ideas about the relationships between variables. It’s also referred to as “hypothesis-testing” research.
You usually do confirmatory research when there’s already research around a topic. This may have been gathered through exploratory research.
In exploratory research, you’re gathering data without trying to establish a particular theory.
In confirmatory research, your goal is to find evidence for (or against) a hypothesis.
Let's say exploratory research found a connection between walking and positivity. Confirmatory research could confirm (or disprove) this.
Confirmatory research has stricter boundaries than exploratory research. You can’t simply change your hypothesis in the middle of a study. That’s because it can potentially lead to poor research practice...
Exploratory and confirmatory research can inform one another in positive ways. Exploratory research pinpoints potential links between variables. Meanwhile, confirmatory research backs these links up with evidence - or disproves them.
However, it’s dangerous to confuse the two. Why? Because of HARKing.
HARKing was developed by the social psychologist Norbert Kerr. It stands for “Hypothesising After the Results are Known”. This is where you take the hypothesis from your results (post-hoc hypothesis) and present it in your study as if it were your original hypothesis (a priori hypothesis).
HARKing causes issues in research as it can lead to false positives. That’s because your original hypothesis will be backed up by other evidence from previous studies. A post-hoc hypothesis is usually just supported by evidence from that particular study. Switching the two can make a study’s findings appear more definitive than they are. It also makes it harder to reproduce or generalize the findings of the study.
If you mix up these two forms of research, you risk presenting exploratory findings as confirmatory. This is a form of HARKing. This can happen when researchers want to boost their chances of being published. If you want to ensure you avoid HARKing in your study, pre-register your research.
Choosing between exploratory vs. confirmatory research depends on the subject of your research. If there’s little to no empirical evidence surrounding the topic, then exploratory research could be the best choice. This would give you an opportunity to gather data and discover interesting leads.
Let’s say a soft drinks company is producing a new product aimed at post-graduate students. They might do some exploratory research to discover the drinks these students enjoy. They might also research their general drinking habits.
But, if there’s already significant research on the topic, it might be best to investigate a particular theory. In this case, you’d want confirmatory research. If the soft drinks company is developing a new drink aimed at teens, it’s more likely to have data ready to analyze. Researchers could test an established hypothesis here. This could be that teens prefer apple-flavored drinks to pear-flavored drinks, for example.
These two types of research often work best when used together. For example, exploratory research might find that most post-grad participants enjoyed iced tea. Confirmatory research could then test whether iced tea is the most popular drink among post-grad students.
Want to create a research study? Whether you choose exploratory or confirmatory research, you'll always need high quality data. Prolific is on hand to help with your data needs.
With over 130,000 reliable research participants active on our platform, it’s never been easier to get the high-quality data you need. Prolific works seamlessly with all your favorite research apps. Plus, there’s even the option for research consultancy to help you feel confident in your survey.
It’s time to get the ball rolling. Get started with Prolific now.
Today Prolific is turning 5 years old – Happy Birthday to us! 🥳 It's been a remarkable journey so far. 3000+ researchers from science and industry have used Prolific last year, we have 45,000 quarterly active participants, and we've seen 200% year-on-year growth. But we're only getting started. In this post, I'll tell you a little bit about our journey, give credit where it's due!, and tell you about our exciting plans for the future.
Fresh out of YC's Summer 2019 batch, we want to share some of our most interesting learnings. If you're a startup founder or enthusiast and want to learn about product-market fit, growth experimentation and culture setting, you're in the right place!