Start from your research problem — not from a statistical test. This guide walks the whole journey and shows, at each step, which choices fit which design.
Answer one or two questions about your research aim. The helper recommends a design — always read its page before you commit.
Seven core designs used in management and social-science research. Each page covers when to use it, how to sample and collect data, and which statistical methods fit — with direct links into the Statistical Methods Atlas.
An open-ended first look at a problem you know little about — built to generate constructs, questions and hypotheses, not to test them.
Flexible / hypothesis-generating
Systematically measures and summarizes the characteristics of a population or phenomenon — what, how much, how often — without testing why.
Quantitative / non-experimental
Measures two or more variables as they naturally occur and tests whether — and how strongly — they are related. It cannot, by itself, establish causation.
Quantitative / non-experimental
Manipulates the independent variable and randomly assigns participants to conditions — the strongest design for establishing cause and effect.
Quantitative / causal
Tests an intervention's effect when random assignment is impossible — using comparison groups, pretests and time series to rule out rival explanations one by one.
Quantitative / causal-comparative
Studies experiences, meanings and processes in depth through words, observation and artefacts — answering how and why questions numbers cannot reach.
Qualitative / interpretive
Deliberately combines quantitative and qualitative strands in one study — so that numbers gain explanation and narratives gain scale.
Mixed / integrative
Cross-cutting guides that apply to every design — from writing a sound research question to interpreting and reporting your results.
Everything downstream — design, sampling, analysis — inherits its quality from the question. Here is how to write one worth answering.
Name each variable's role, know its level of measurement, and operationalize it well — three decisions that quietly determine which analyses are even possible.
Who gets into your study, how they get in, and how many you need — the decisions that set the ceiling on generalizability and power.
Surveys, interviews, focus groups, observation, experiments and archives — what each is good for, what it costs, and how to keep bias out of the pipeline.
Choosing the right analysis, reading results honestly — significance versus effect size — and writing conclusions your design can actually support.