Your study design is the plan for conducting your research. While your research methodology informs your choice of design, in quantitative research it is mainly shaped by practical and theoretical considerations. These include sample size, potential sources of bias and confounding, the ability to draw causal inferences, measurement validity and reliability, ethical considerations, time and resource constraints, and the generalisability of your findings.
Quantitative study designs are generally grouped into two main types:
Observational designs, where the researcher observes and measures variables without intervening.
Experimental designs, where the researcher actively intervenes to test a hypothesis - typically by assigning participants to different conditions or treatments.
If you would like to learn more about the difference between observational and experimental designs, you may like to view the short video Observational Studies & Experiments.
There are various observational and experimental study designs to choose from, but this page outlines the key features of six of the most commonly used.
A cross-sectional study is an observational study that analyses data from a population at a single point in time to assess prevalence. This type of study design is useful when you want to estimate the prevalence of a health condition, behaviour or exposure and to explore associations in a defined population.
Seminal authors: Levin
Common data collection methods: questionnaires or existing records, administered/obtained at a particular point in time
Common data analysis techniques: descriptive statistics; t-tests and ANOVA; Chi-square test, correlation and regression
Example thesis: Digital Financial Services Acceptance Among Low-Income Households in Miri, Sarawak: A Perspective from the Cultural Dimensions Theory
A cohort study is an observational study where a group of people is followed over time to assess the relationship between exposures and outcomes. This may be done prospectively (prospective cohort study) or retrospectively (retrospective cohort study). This type of study design is useful when you want to examine the incidence of an outcome and establish a temporal relationship between exposure and outcome.
Seminal authors: Doll, Hill, Rothman, Greenland and Lash
Common data collection methods: questionnaires, existing records or biological samples, administered/obtained at baseline and during follow-up
Common data analysis techniques: descriptive statistics; regression; survival analysis; relative risk and hazard ratios
A longitudinal study is a study design in which the same individuals are followed and assessed at multiple time points to observe changes over time. Cohort studies are one kind of longitudinal study, but others can be experimental or use different approaches to repeated measurements. This type of study design is useful when you want to track individual-level change, development, or progression over time.
Seminal authors: Piaget and Terman
Common data collection methods: questionnaires, clinical or physiological assessments, existing records or observations, administered/obtained repeatedly over time
Common data analysis techniques: descriptive statistics; repeated measures ANOVA; linear mixed models, generalised estimating equations, growth curve modelling
Example thesis: Factors affecting student adjustment as they transition from primary to secondary school: a longitudinal investigation
A case control study is a retrospective observational study that compares individuals with a specific outcome (cases) to those without it (controls) to determine associations with prior exposures or risk factors. This type of study design is useful when you want to investigate potential risk factors for a rare outcome in a time and cost efficient way.
Seminal authors: Cornfield, Doll and Hill
Common data collection methods: existing records or questionnaires
Common data analysis techniques: descriptive statistics; Chi-square test, regression; odds ratio
Example thesis: Tea, coffee and prostate cancer: A case-control study in Vietnam
A randomised controlled trial (RCT) is an experimental study in which participants are randomly allocated to intervention or control groups to assess the effect of an intervention on specific outcomes. This type of study design is useful when you want to evaluate the causal effect of an intervention and to minimise bias and confounding.
Seminal authors: Hill, Cochrane
Common data collection methods: questionnaires, existing records or clinical or physiological assessments
Common data analysis techniques: t-tests and ANOVA; Chi-square test and regression; survival analysis; intention-to-treat analysis
If you would like to learn more about randomised controlled trials, you might be interested in the following videos:
A quasi-experimental design is an experimental study that evaluates the effect of an intervention or exposure without random assignment of participants to groups. This type of study design is useful when randomisation is not feasible or ethical, but you still want to assess causal relationships.
Seminal authors: Campbell, Stanley, Cook
Common data collection methods: questionnaires, existing records or clinical or physiological assessments
Common data analysis techniques: t-tests, ANOVA and ANCOVA; Chi-square test and regression; survival analysis
Example thesis: Fluency Strategy Training and the L2 Oral Task Performance of Indonesian EFL Classroom Learners
If you would like to consolidate your understanding of the quantitative study designs outlined above, you may find the following activity helpful: