A one-shot case study is the simplest type of research design: a single group receives a treatment or intervention, and then researchers measure the outcome once. There is no comparison group, no baseline measurement before the treatment, and no repeated observations. In research notation, it’s written as X O, where X represents the intervention and O represents the single observation that follows.
This design falls into the category of pre-experimental designs, meaning it lacks the controls needed to establish cause and effect with any confidence. It’s widely taught in research methods courses as a starting point for understanding why more rigorous designs exist, but it also has legitimate, if narrow, uses in real-world research.
How the Design Works
The structure is exactly as minimal as it sounds. A researcher introduces some kind of treatment, program, or event to a group, then measures what happens afterward. A teacher might try a new math curriculum for a semester and then give students a test. A company might roll out a workplace wellness program and then survey employee satisfaction. A therapist might try a new technique with a client and then assess their symptoms.
What’s missing is everything that would let you draw firm conclusions. You don’t know what the group looked like before the intervention, so you can’t measure change. You don’t have a comparison group that didn’t receive the intervention, so you can’t rule out other explanations. The single observation gives you a snapshot, but no context for interpreting it.
Why It’s Considered Weak
The one-shot case study is vulnerable to nearly every major threat to internal validity, which is a researcher’s ability to confidently say the intervention caused the observed outcome.
- No baseline. Without a pretest or prior measurement, you have no way to know whether the group changed at all. If students score 75% on a test after a new curriculum, was that an improvement? A decline? You simply don’t know.
- History. Any event that happens alongside your intervention could explain the results. If employee satisfaction is high after a wellness program, maybe it’s because the company also gave raises that quarter.
- Maturation. People change naturally over time. Students learn, patients recover, employees adjust. A single post-treatment observation can’t separate the effect of your intervention from the effect of time passing.
- Selection bias. Without random assignment or a comparison group, you can’t account for the possibility that the people in your study were already predisposed to the outcome you observed.
- No comparison group. Group designs use control groups to absorb and account for all of these threats. The one-shot case study has no such safeguard.
The absence of a pretest is the most commonly cited problem. As one research example illustrates, if you implement a new hand hygiene intervention at a hospital and then measure infection rates, you have no way to determine whether the rates you observe are better, worse, or the same as they were before. Any differences between facilities could reflect pre-existing factors like staffing rather than the intervention itself.
How It Compares to Other Pre-Experimental Designs
The next step up in rigor is the one-group pretest-posttest design, which adds a measurement before the intervention. Its notation is O X O: observe, intervene, observe again. This solves the baseline problem, because you can at least see whether something changed. It still lacks a control group, so you can’t rule out history or maturation, but it gives you significantly more information than a single post-test observation.
Adding a control group that doesn’t receive the intervention takes you into quasi-experimental territory. Adding both a control group and random assignment gets you to a true experimental design. Each step addresses specific validity threats that the one-shot case study leaves wide open.
When Researchers Still Use It
Despite its limitations, the one-shot case study isn’t always the wrong choice. It serves a purpose in specific situations where more controlled designs aren’t feasible or necessary.
Exploratory research is the most common use case. When a researcher is investigating a new idea, testing the waters before committing to a larger study, a one-shot observation can provide initial data worth examining further. It’s economical in every sense: money, time, effort, and personnel. This matters especially when studying complex phenomena where a full experimental design would be prohibitively expensive.
It can also be useful when studied conditions are rare, when researcher resources are severely limited, or when evaluating a novel or expensive intervention for the first time. In these cases, the goal isn’t to prove causation. It’s to gather preliminary evidence that justifies a more rigorous follow-up study.
The key distinction is that a one-shot case study can suggest something interesting is happening. It cannot demonstrate that a specific intervention caused it.
Generalizability Concerns
Beyond internal validity, the design also struggles with external validity, which is the ability to apply your findings to other groups or settings. Studying a single group in a single context, with a single measurement, provides very little basis for claiming results would hold elsewhere. Group designs are generally considered superior because they minimize, though don’t necessarily eliminate, the major validity threats that make it hard to draw scientifically sound conclusions.
Some researchers have argued that single-case approaches can actually increase ecological validity, meaning the results reflect what happens in real, naturalistic settings rather than controlled lab environments. But this benefit doesn’t offset the fundamental inability to establish causation. Case-based methods are not positioned to replace group designs as the standard for experimental research, and that isn’t their purpose.
Avoiding Common Confusion
The one-shot case study is sometimes confused with single-case experimental designs, which are a distinct and more rigorous methodology. Single-case experimental designs involve purposeful manipulation of variables and repeated measurements over time. They can include baseline phases, intervention phases, and withdrawal phases that allow researchers to observe patterns of change. The one-shot case study does none of this. It measures once, after a single intervention, with no systematic attempt to control for alternative explanations.
It’s also different from a clinical case report, which describes the management of a patient or small group of patients without necessarily manipulating any variable or taking repeated measures. A case report documents what happened. A one-shot case study, minimal as it is, at least involves an intentional intervention followed by a planned observation.