Primary research articles provide a report of individual, original research studies, which constitute the majority of articles published in peer-reviewed journals. All primary research studies are conducted according to a specified methodology, which will be partly determined by the aims and objectives of the research.
The following sections offer brief summaries of some of the common quantitative, qualitative, and mixed-methods study designs you may encounter.
A randomised controlled trial (RCT) is a study where participants are randomly allocated to two or more groups. One group receives the treatment that is being tested by the study (treatment or experimental group), and the other group(s) receive an alternative, which is often the current standard treatment or a placebo (control or comparison group). The nature of the control used should always be specified.
An RCT is a good study choice for determining the effectiveness of an intervention or treatment, or for comparing the relative effectiveness of different interventions or treatments. If well implemented, the randomisation of participants in RCTs should ensure that the groups differ only in their exposure to treatment, and that differences in outcomes between the groups are probably attributable to the treatment being studied.
In crossover randomised controlled trials, participants receive all of the treatments and controls being tested in a random order. This means that participants receive one treatment, the effect of which is measured, and then "cross over" into the other treatment group, where the effect of the second treatment (or control) is measured.
RCTs are generally considered to be the most rigorous experimental study design, as the randomisation of participants helps to minimise confounding and other sources of bias.
A cohort study identifies a group of people and follows them over a period of time to see who develops the outcome of interest to the study. This type of study is normally used to look at the effect of suspected risk factors that cannot be controlled experimentally – for example, the effect of smoking on lung cancer.
Also sometimes called longitudinal studies, cohort studies can be either prospective, that is, exposure factors are identified at the beginning of a study and the study population is followed into the future, or retrospective, that is, medical records for the study population are used to identify past exposure factors.
Cohort studies are useful in answering questions about disease causation or progression, or studying the effects of harmful exposures.
Cohort studies are generally considered to be the most reliable observational study design. They are not as reliable as RCTs, as the study groups may differ in ways other than the variable being studied.
Other problems with cohort studies are that they require a large sample size, are inefficient for rare outcomes, and can take long periods of time.
A case-control study compares a group of people with a disease or condition, against a control population without the disease or condition, in order to investigate the causes of particular outcomes. The study looks back at the two groups over time to see which risk factors for the disease or condition they have been exposed to.
Case-control studies can be useful in identifying which risk factors may predict a disease, or how a disease progresses over time. They can be especially useful for investigating the causes of rare outcomes.
Case-control studies can be done quickly, and do not require large groups of subjects. However, their reliance on retrospective data which may be incomplete or unreliable (owing to subject ability to accurately recall information such as the appearance of a symptom) can be a difficulty.
A cross-sectional study collects data from the study population at one point in time, and considers the relationships between characteristics. Also sometimes called surveys or prevalence studies.
Cross-sectional studies are generally used to study the prevalence of a risk factor, disease or outcome in a chosen population.
Because cross-sectional studies do not look at trends or changes over time, they cannot establish cause and effect between exposures and outcomes.
A case series is a descriptive study of a group of people, who have either received the same treatment or have the same disease, in order to identify characteristics or outcomes in a particular group of people.
Case series are useful for studying rare diseases or adverse outcomes, for illustrating particular aspects of a condition, identifying treatment approaches, and for generating hypotheses for further study.
A case report provides a study of an individual, rather than a group.
Case series and case reports have no comparative control groups, and are prone to bias and chance association.
Expert opinion draws upon the clinical experience and recommendations of those with established expertise on a topic.