I have previously written about improving research literacy to gain greater understanding of mental health research. In that post, I described some of the terms commonly used in research. In this post, I’ll talk about some of the common research designs for both quantitative and qualitative studies.
Quantitative studies yield quantifiable results that can be statistically analyzed. The researcher identifies a hypothesis that is then tested.
Experiments use control groups and participants are randomly assigned to intervention and control groups. The researcher and participant may both be blinded as to which intervention the participant is receiving (e.g. drug vs. placebo).
- Strengths: experimental studies can provide strong evidence regarding effects of an intervention allow researchers to make strong inferences regarding causality
- Limitations: rigorously designed experimental studies do not replicate real-world conditions, they may not explain why an effect occurs, and they may not be possible or practical for certain research questions
These studies have controls but participants are not randomly assigned to the control or intervention group. Similar groups may be compared, groups of patients receiving the same medication at different doses might be compared, or a series of measurements might be gathered before and after an intervention.
- Strengths: they are more practical in real-world clinical settings, and it may be easier to recruit participants
- Limitations: there is an increased risk of bias, and internal validity (i.e. soundness of the evidence and conclusions drawn from it) may not be as good as experimental designs
In these studies there is no independent variable that is manipulated by the researchers; essentially the researcher is sitting back and observing, describing, and documenting what happens. This may be done retrospectively, such as a “case control” design, or prospectively, such as a cohort design.
- Strengths: this can work for research questions that are not conducive to experimentation (e.g. the effect of taking medications during pregnancy), and if the design is sufficiently rigorous it can allow researchers to make causal inferences
- Limitations: less able to support causal inferences than other designs, potential for selection bias, and relationships may be mediated by various other than those being studied
Qualitative research aims to understand how people experience things. Data may be gained through such means as interviews, written narratives, focus groups, and participant observation. The data is analyzed to find recurring themes and underlying meanings. There are certain elements that support rigour in qualitative research, which differ somewhat depending on the type of design used.
- Phenomenology: this aims to understand the meaning of participants’ lived experience
- Grounded theory: these studies are used to develop theories that are grounded in participant data
- Ethnography: this type of research describes and interprets patterns of values, behaviours, and beliefs of a cultural group
- Autoethnography: This is the method I used for my master’s thesis, and it is a way of studying cultural phenomena using the researcher’s own stories
- Action research: this involves empowering marginalized populations to participate in conducting research within their communities
Qualitative research is often considered as producing lower strength evidence than quantitative research, but it can be an excellent way to provide richer detail of what is studied quantitatively. For example, a quantitative study might look at the effectiveness of interventions to reduce the use of seclusion and restraints in a psychiatric ICU, while a qualitative study might talk to the patients in the ICU and get their descriptions of what it felt like to experience these different types of interventions.
The key point is that not all research studies are created equal, and they don’t all give us the same kinds of answers to questions. When research findings are presented by the media, they often don’t have the research literacy to properly contextualize the results based on the type of study design. That is particularly true when it comes to making inferences regarding causation. There are all kinds of poorly designed studies out there, so it’s important to maintain a healthy level of skepticism, and don’t believe everything you read.