What the exam asks
- Identify the experimental units (or subjects), explanatory variable(s) (factors), treatments, and response variable in a study description.
- Identify or describe the four elements of a well-designed experiment: comparison, random assignment, replication, and direct control.
- Explain how confounding occurs when an extraneous variable is associated with both the explanatory and response variables, and how random assignment or direct control reduces the potential for it.
- Explain the purpose of a control group, a placebo, and single- or double-blinding in context.
Core ideas
Experimental vocabulary and confounding
An experiment deliberately imposes treatments (specific values or combinations of the explanatory variable, also called a factor) on experimental units (called subjects or participants when they are human) to measure changes in a response variable.
An extraneous variable is any variable other than the explanatory variable that might affect the response. Confounding happens when the effects of an extraneous variable and the explanatory variable on the response cannot be distinguished from each other because the extraneous variable differs systematically between treatment groups.
The four elements of a well-designed experiment
| Element | What it means | Why it matters |
|---|---|---|
| Comparison | Include at least two treatment groups (often one is a control group). | Gives a baseline to see how the response differs across treatments; without a comparison group, you cannot tell whether changes in the response were caused by the treatment or by outside factors. |
| Random assignment | Use a chance process (random number generator, slips of paper, coin tosses) to assign experimental units to treatments. | Tends to create treatment groups that are roughly equivalent with respect to known and unknown extraneous variables at the start of the study, reducing the potential for confounding and justifying a cause-and-effect conclusion. |
| Replication | Assign multiple experimental units to each treatment group (not just one unit per treatment). | Allows researchers to measure natural variability in the response among units receiving the same treatment and increases sensitivity to detect real treatment differences. |
| Direct control | Hold extraneous variables constant across all experimental units (e.g., same room temperature, same watering schedule). | Prevents those extraneous variables from becoming confounding variables and reduces variability in the response variable, making treatment effects easier to see. |