Guide
Quantitative research
Quantitative research measures variables as numbers to test hypotheses and quantify relationships, using larger, representative samples and statistical analysis to produce findings that can be generalised to a wider population.
The step most authors miss
Doing CRediT right? Don’t stop at the statement.
A CRediT statement credits you inside one paper. The recognition CRediT was built for happens when those roles are tied to you, persistently. Sign in with your ORCID — free — and claim your CRediT contributions on casrai.org, the home of the standard. They become a verified, portable part of your identity, not a line that disappears into one PDF.
Free: claim your contributions, then export a journal-ready CRediT statement, schema.org structured data, JATS XML, CSV or BibTeX — and preview your public profile. A membership publishes that profile publicly and verifies the journals you serve.
What quantitative research is
Quantitative research is an approach that expresses phenomena as numbers in order to measure them, test hypotheses and quantify the relationships between variables. Its logic is deductive: the researcher begins with a theory or prediction, defines variables precisely through operational definitions, then collects structured data to confirm or reject that prediction. Because the aim is to estimate how much, how many, or how strongly things are related — and to generalise beyond the people studied — quantitative designs rely on larger samples chosen to represent a wider population. Data collection is standardised so that every case is measured the same way, and analysis is statistical. The result is evidence that is precise, comparable across cases and, when well designed, replicable by other researchers using the same procedures.
Defining characteristics
Quantitative work has a recognisable profile. Questions are framed as testable hypotheses about variables. Designs are fixed and planned in full before data collection begins, so that procedures cannot drift and bias the result. Measurement is structured and standardised, using instruments such as questionnaires, scales, tests or sensors that yield numerical values. Samples are larger and selected — ideally through probability sampling — to support statistical generalisation from sample to population. The researcher aims for objectivity and distance, minimising their influence on what is measured. Rigour is judged by validity (does the instrument measure what it claims to, and are the causal conclusions sound?) and reliability (does it measure consistently, producing stable results on repetition?). These standards are what allow numbers from one study to be trusted and compared with another.
Common research designs
Quantitative research uses several core designs. Experimental designs, including the randomised controlled trial, manipulate an independent variable and randomly assign participants to conditions so that differences in the outcome can be attributed to the intervention — the strongest basis for causal claims. Quasi-experimental designs do the same without full randomisation, trading some internal validity for feasibility. Survey designs collect standardised data from a sample, usually with questionnaires, to describe characteristics, attitudes or behaviours across a population. Correlational designs measure two or more variables as they naturally occur to assess whether and how strongly they are associated, without manipulating anything — and so describe relationships but cannot, on their own, establish cause. Choosing among them depends on whether the question is descriptive, relational or causal.
Data, measurement and statistical analysis
Sound quantitative research depends on careful measurement. Concepts are operationalised into measurable indicators, and data are classified by level of measurement — nominal, ordinal, interval or ratio — which determines what analysis is appropriate. Analysis then proceeds in two broad stages. Descriptive statistics summarise the data: measures of central tendency (mean, median, mode), measures of spread (range, standard deviation) and frequencies or visual summaries. Inferential statistics go further, using a sample to draw conclusions about a population: hypothesis tests, confidence intervals, comparisons of groups and models of association such as correlation and regression. Throughout, the trustworthiness of the numbers rests on the validity and reliability of the instruments and on a sample large and representative enough to support the inferences being made.
Strengths, limitations and when to use it
The strengths of quantitative research are generalisability, precision and replicability: representative samples allow findings to be extended to a population, standardised measurement makes results comparable, and well-documented procedures let other researchers reproduce the study. Experimental designs can also support strong causal inference. The limitations are the cost of that structure. Numbers capture how much but say little about why or how something happens, so quantitative work offers less depth and context and can miss meaning that does not fit the predefined variables; poorly chosen measures can also reduce a rich concept to a thin proxy. Use quantitative methods when you need to test a hypothesis, measure prevalence or magnitude, compare groups, or assess relationships and effects across a population. Where you need to understand experience and meaning instead, qualitative methods fit better — and mixed methods research combines both to test and explain in the same programme of work.
Key facts
At a glance
- Definition: measures variables numerically to test hypotheses and quantify relationships
- Logic: deductive — predictions tested against structured data
- Sampling: larger, representative samples for statistical generalisation
- Designs: experimental, quasi-experimental, survey, correlational
- Analysis: descriptive and inferential statistics
- Rigour: validity and reliability of measurement and inference
Common questions
FAQ
Can quantitative research prove cause and effect?+
Only some designs can. A well-conducted experiment or randomised controlled trial, which manipulates a variable and randomly assigns participants, supports strong causal claims. Survey and correlational designs measure variables as they naturally occur and can show that variables are associated, but association alone does not establish causation.
What is the difference between descriptive and inferential statistics?+
Descriptive statistics summarise the data you have — using means, standard deviations, frequencies and charts to describe a sample. Inferential statistics use that sample to draw conclusions about a wider population, through hypothesis tests, confidence intervals and models such as correlation and regression, accounting for the uncertainty of generalising beyond the cases studied.
How is rigour assessed in quantitative research?+
Mainly through validity and reliability. Validity asks whether an instrument measures what it claims and whether causal and population conclusions are sound; reliability asks whether measurement is consistent and repeatable. Adequate, representative sampling and standardised, well-documented procedures underpin both — and contrast with the trustworthiness criteria used to judge qualitative research.
Going deeper
