Exploratory, Descriptive, Explanatory, Causal Research

Two sentences from two dissertation proposals. “I want to find out what gets students into volunteering in the first place.” And: “I want to test whether time pressure reduces how much students volunteer.”

Two good dissertations could grow out of those sentences, yet they call for different kinds of study. Exploratory research investigates a field where little is known so far, descriptive research measures frequencies and distributions as precisely as possible, explanatory research tests theory-based hypotheses about relationships, and causal research also sets out to show that one factor produces a specific effect. By the end of this guide you will know which of the four matches your research question and what that means for your method.

📌 Key takeaways

• Exploratory research explores new ground, descriptive research measures known ground.
• Explanatory research tests hypotheses, causal research establishes cause and effect.
• Marketing textbooks say causal where social scientists say explanatory.
• Exploratory is a research aim, not automatically a qualitative method.
• Oxford Learner's Dictionaries gives prescriptive as the opposite of descriptive.

Exploratory, descriptive, explanatory and causal research: how the four differ

Exploratory, descriptive, explanatory and causal are not data collection methods but research aims. Each label tells you how much is already known about your subject and what your own study is supposed to add. The method comes afterwards: whether you interview people, run a standardised survey or set up an experiment follows from the aim, not the other way round.

Social science methods teaching usually works with three types, sorted by what a study wants to find out: exploratory, descriptive and explanatory. The fourth label, causal research, belongs mainly to marketing research, which says causal at the point where sociologists and psychologists say explanatory. So if the core textbook on your reading list names three types and the slides for your marketing module name four, the two sources are not contradicting each other. They come from two traditions that put different labels on much the same idea.

The order of the rows is not a ranking. A careful exploratory dissertation beats a causal design that your sample could never have supported. To see where your project sits in the whole sequence from first question to final write-up, have a look at our overview of the empirical research process.

Four research questions, four research types

The quickest way to identify the research type is to look at the question itself. The same topic can be phrased in all four ways, and each phrasing needs a different kind of data collection. Take student volunteering as an example.

The causal version is the riskiest of the four. A question about effects takes one line to write down, but it demands a design that most undergraduate and master's dissertations simply cannot deliver.

Exploratory or explanatory? Two words that are easy to mix up

Exploratory and explanatory look almost identical on the page but point in opposite directions. Exploratory comes from explore and means finding out what is there, explanatory comes from explain and means testing why something happens. A proposal that promises an explanatory study when the author means an exploratory one will be read, and marked, against the wrong expectations.

Several other labels in your reading point to the same four aims. An exploratory study, an exploratory design and exploratory research all describe one and the same aim, and the same goes for a descriptive study and a descriptive survey. Now and then you will also meet explanative, a less common form with the same meaning as explanatory. Description, on the other hand, is not a research type at all but the result of describing something.

Exploratory research: when almost nothing exists on your topic

Exploratory research investigates a field for which there are no reliable findings or usable theories yet. Its aim is not to test an assumption but to produce one: at the end you have concepts, patterns and hypotheses that a later study can put to the test.

The attraction is obvious, and so is the risk. With so little groundwork, there are no validated questionnaires, no benchmark figures and no expectation to hold your results against. For that reason exploratory projects usually rely on open questions and small samples, and for the same reason the analysis takes longer than most students allow for. The word already carries its meaning: Oxford Learner's Dictionaries defines exploratory as something done “in order to find out more about it”.

Exploratory research questions sound like this:

• How do NHS ward nurses experience the move to digital patient records?
• What reasons do students give for giving up a part-time job during term?
• What stops members of a local sports club from joining the committee?
• What role do voice notes play in how study groups organise themselves?

A common claim is that exploratory research and qualitative research are the same thing. That holds as a tendency, not as a rule. Exploratory describes a research aim, qualitative describes a family of methods, and the two often overlap without having to. An open online survey with 400 free-text responses pursues an exploratory aim and is still partly analysed with counts and percentages. Our comparison of qualitative and quantitative research shows how to keep the two ideas apart.

Exploratory methods: how you investigate a new field

Exploratory methods follow one shared principle: they let the participants or the field decide which topics come up at all. That is why they work with few constraints and small samples, and why most of the effort only arrives at the analysis stage. These are the methods you will meet most often in exploratory studies:

• semi-structured interviews with a handful of open questions
• focus groups with six to ten participants
• expert interviews with practitioners in the field
• participant observation, the standard approach in ethnographic fieldwork
• a case study of a single company, club or project
• an open online survey with free-text boxes instead of scales
• secondary analysis of existing documents and datasets

For secondary analysis you do not have to start from scratch. The UK Data Service, funded by UKRI through the Economic and Social Research Council, describes its holdings as the UK's largest collection of economic, population and social research data. A case study is another natural way in for students, for example in the organisation where you spent a placement year, because a single case is accessible and still allows depth. Its limit is transferability: one case tells you nothing certain about all the others.

Hypotheses in an exploratory dissertation: do you need them?

Hypotheses come at the end of an exploratory study, not at the beginning. An exploratory dissertation that states hypotheses up front and then tests them works against its own aim, because it takes for granted exactly what it was meant to generate.

Write research questions instead and put the expectations you discover into your findings chapter. Anything you derive from your data as a working assumption should be presented as a hypothesis developed from the material and clearly marked as untested. That is the wording markers look for in an exploratory dissertation.

Descriptive research: measuring frequencies and distributions precisely

Descriptive research describes a subject that is already known as precisely as possible: frequencies, proportions, averages and distributions. It answers what, where, when and how questions reliably. Why questions lie outside its reach, because describing something and explaining it are two different claims.

A typical UK example is the Community Life Survey, which the Department for Culture, Media and Sport publishes as official statistics for England. According to the 2024/25 release on volunteering, 28% of adults had taken part in formal volunteering at least once in the last 12 months and 17% at least once a month. Those figures tell you how many people volunteer and how often, but not why, which is exactly where a descriptive study stops.

Descriptive projects are the most common kind of dissertation and still the most underrated. They look undemanding because nobody has to prove anything. The real challenge lies elsewhere: the whole value of the work depends on the sample. A description only ever applies to the group your responses came from, and a survey shared around your own course is not “students in the UK”. Our guide to the representative survey explains what it takes to go further.

A descriptive study is only as good as its sample. You are always describing the people who actually replied.

For data collection this means a standardised questionnaire, the same answer options for everyone and as little free text as possible. Only then can responses be added up, and only then is the description more than a collection of individual voices.

Descriptive research questions: four examples

Descriptive research questions ask about share, frequency, distribution or level and contain no assumption about causes. Most of them begin with “how many”, “how often”, “how widespread” or “which”. These four show the pattern:

• How often do ward nurses use the digital patient record during a shift?
• Which part-time jobs do second-year students hold during term?
• How long have the members of a local football club belonged to it?
• What proportion of respondents have no management experience?

The test for your own question is short. As soon as a “why” or a “because” appears in it, the question is no longer descriptive, and your methodology chapter has to reflect that.

Quantitative descriptive research design: what the term means

A quantitative descriptive research design combines a descriptive aim with quantitative data collection, which makes it the standard case of a questionnaire study that sets out to describe. The first half of the term says what you want to know, the second half says what kind of data you will answer it with.

Naming both the aim and the type of data is common practice in a methodology chapter, because the two are chosen independently. A descriptive aim can just as well be pursued qualitatively, for instance through structured observation notes. Our guide to research design shows how to bring aim and method together into a design that holds up.

Explanatory and causal research: explaining is not the same as proving

Explanatory research tests theory-based hypotheses about relationships between variables, while causal research goes a step further and sets out to show that one factor produces a specific effect. The difference does not lie in the topic but in what your research design allows you to claim.

The two labels sit closer together than a four-way split suggests. In many textbooks explanatory covers exactly what others call causal, so for your dissertation the label matters less than how much weight your data can bear. Explanatory work is deductive: you take an existing theory, derive an expectation, make it measurable and test it against your data. Our article on deductive and inductive research follows that route from theory to testable statement. You may only speak of a genuine cause when three conditions hold together:

1. Covariation. The two variables change together in a systematic way.
2. Temporal precedence. The presumed cause demonstrably comes before the effect.
3. No better alternative. No third variable explains the relationship better.

A one-off online survey only delivers the first condition. For that reason the sentence “the survey shows that time pressure leads to less volunteering” is almost always overstated in student work, and markers reliably pick it up. A genuine causal design would need a control group and at least two points of measurement.

Exploratory and descriptive in medicine, psychology and marketing research

Exploratory and descriptive point to a similar aim in every discipline, but each discipline ties them to something different: medicine to what a study measures, psychology to what was decided in advance and marketing research to the stage of a project. When you read a source from another field, read that reference point along with the definition.

Two consequences follow for your dissertation. First, always cite a definition together with the discipline it comes from. Second, use the classification of your own department, even if a neighbouring subject counts differently.

Medicine and health: descriptive means prevalence at a point in time

In medicine, descriptive is linked to what a study measures rather than to the overall research type. The BMJ's introductory text Epidemiology for the Uninitiated explains that a cross sectional study measures the prevalence of health outcomes or their determinants in a population at one point in time, and warns that the design can make it hard to tell cause from effect.

If your project takes place in an NHS or social care setting, a second distinction matters before you start. Guidance from the University of Warwick on classifying a study separates research, which seeks generalisable new knowledge and includes studies that generate hypotheses, from service evaluation, which only judges current care, and clinical audit, which measures care against a standard. The category can change which approval you need, so settle it with your supervisor early.

Psychology: exploratory versus confirmatory

In psychology, exploratory usually stands opposite confirmatory rather than next to descriptive, with confirmatory meaning research that tests hypotheses fixed in advance. The open science guidance of the School of Psychology at the University of Aberdeen sees exploratory experiments as a way to generate and refine hypotheses, while confirmatory experiments have to be planned ahead and should be preregistered as a matter of course. What counts in psychology, then, is when the decisions were made.

Marketing research: from exploring to testing

In marketing research the three labels form a sequence within one project. A focus group comes first as the exploratory step before a product test, a descriptive survey on customer profile and usage follows, and finally a causal test compares two price points in two comparable groups. That sequence is the origin of the four-way split you will meet in business school modules.

What else does descriptive mean? Three senses that get confused

Descriptive simply means “describing”. Because that is so general, the word turns up in three quite separate contexts: as a research type, as a branch of statistics and as the opposite of prescriptive. Apart from the word itself, the three have nothing in common.

Mixing them up has consequences, because it leads to methodology chapters that contradict themselves. Write “descriptive study” when you mean “descriptive statistics” and you are suddenly making a claim about your whole research design instead of about the way you analysed the data.

Descriptive as a research type

As a research type, descriptive names the aim of the entire study: a known subject is to be captured more precisely, not explained. This sense concerns how the dissertation is set up and therefore belongs in the methodology chapter, usually as one clear sentence near the start.

Descriptive statistics: the counterpart is inferential statistics

Descriptive statistics is a way of analysing data, not a research design. It summarises the data you already have with means, medians, measures of spread and frequency tables. Its counterpart is inferential statistics, which draws conclusions from a sample about a wider population. Both can be used in a descriptive study as well as in an explanatory one. Our article on descriptive and inferential statistics explains the difference.

Exploratory data analysis is a third case and fits neither category. The term goes back to John W. Tukey's 1977 book “Exploratory Data Analysis” and means searching data systematically for patterns, mostly with charts rather than tests. Exploratory data analysis is therefore part of the analysis, not a research type, even though both carry the same word.

Descriptive versus prescriptive: the real opposite

The linguistic opposite of descriptive is prescriptive, which means laying down rules. In its linguistics sense, Oxford Learner's Dictionaries uses descriptive for saying how language is actually used without setting rules for it, and labels prescriptive as the opposite. Economics and ethics draw the same line as descriptive versus normative: a descriptive statement says how things are, a normative one says how they ought to be. None of this has anything to do with the four research types.

Which research type fits your dissertation?

The right research type follows from the state of the literature on your topic. The more solid prior work there is, the further you move from exploratory towards explanatory and causal. The reverse holds too: if all you can find is work on neighbouring topics, exploratory is the honest choice.

The second test is feasibility. A causal design without a control group remains a statement of intent, and an explanatory design without established scales turns the analysis chapter into guesswork. Check both together: what the literature allows, and what your timetable, your access to the target group and your likely sample size will support.

The research type directly shapes your questionnaire. Exploratory means plenty of open questions and few constraints, while descriptive and explanatory mean closed questions and scales, because frequencies and relationships can only be calculated from those. Our comparison of open and closed questions shows which format does which job, and our guide to creating a questionnaire covers the structure itself.

No survey tool can choose the research type for you. Free-text boxes and rating scales are standard features everywhere, including in empirio.ai, an online survey tool from Germany. The difference is made before that, in your research question, and becomes visible afterwards in your methodology chapter.

Exploratory work in an undergraduate or master's dissertation: judging the workload

An exploratory undergraduate or master's dissertation takes considerably more analysis time than a descriptive one, because every interview and every free-text answer has to be coded individually. Work out how long the analysis will take before you agree an exploratory approach with your supervisor.

Exploratory work pays off above all when you have access to a field that nobody else can reach, such as the company where you did your placement year, a school where you work as a teaching assistant or a club you belong to. Without that kind of access, an exploratory dissertation often gets stuck at general statements, and markers notice.

Descriptive work in an undergraduate or master's dissertation: where the marks are

A descriptive undergraduate or master's dissertation earns its marks not through its results but through how well it justifies the sample and how carefully the questionnaire is put together. So describe precisely whom you reached, whom you missed and what that means for how far your figures can be generalised.

A master's dissertation is held to a higher standard than an undergraduate one. Description alone is rarely enough, and markers will also expect you to set your findings against existing research. A descriptive aim is still perfectly legitimate, as long as the dissertation says so openly and does not upgrade it to an explanation after the fact.

Common mistakes when choosing a research type

Most problems do not arise when the research type is chosen but when the dissertation is written. The type sits neatly in the methodology chapter, and then the discussion fills up with claims that the type never covered.

The four cases below come up in student dissertations again and again. All four can be fixed in a few sentences, provided you spot them before you submit.

Exploratory as an excuse for a thin literature review

Exploratory means that little is known about the subject, not that the reading was rushed. Present a well-researched topic as exploratory and your supervisor or second marker will still ask what the literature says. Search at least two subject databases from your university library beforehand to check that the gap really is a gap.

Reporting descriptive results in causal language

Choosing stronger words does not turn a description into an explanation. Phrases such as “leads to”, “causes” or “results in” claim a direction of effect that a one-off survey cannot support. Search your draft for those phrases before submission and replace them with wording that names an association.

Never naming the research type

Many dissertations only reveal their research type indirectly, through the method they use. That costs marks for no reason, because methodological positioning is part of the marking criteria. A single sentence will do: “This study has a descriptive aim and sets out the distribution of X within group Y.”

Explanatory without theory

An explanatory study tests hypotheses, and hypotheses do not fall from the sky. Making up expectations on a hunch and then running significance tests on them is not an explanatory design but a hunt for chance findings. Our guide to formulating a research question and hypotheses shows where defensible hypotheses come from.

Conclusion

The research type is not a label you stick on at the end. It is the first real decision after choosing your topic. Choose it according to the state of the literature and to what you can realistically collect, then state it in one clear sentence in your methodology chapter. A dissertation that honestly calls itself descriptive is far stronger than one that claims causal findings it cannot back up.

Where to go next

• Want to see the whole sequence at a glance? The empirical research process
• Looking for the basics behind it? Empirical research: definition and methods
• Need to sharpen your question? Writing a research question and research aim
• Collecting your data online? The online survey as an empirical research method

Research type settled, but no questionnaire yet?

In the empirio.ai template collection you will find ready-made question sets for descriptive and for hypothesis-testing surveys that you can adapt to your own topic.

Browse the questionnaire templates