# Experiment

> A test that changes one thing on purpose to see what it causes.

**Field:** General Knowledge  
**Category:** Research  
**Also known as:** Controlled Experiment, Scientific Experiment

## Think of it like

It is like baking two cakes the same way. One gets more sugar. Then you taste both.

## Definition

An experiment tests a cause by changing one thing on purpose and measuring what happens. The thing you change is the variable under test. Everything else is kept the same, so it cannot explain the result. Results are compared with a group that did not get the change. It is the strongest way to show that one thing causes another.

## Example

Jack gives one group of plants extra light and keeps a second group the same in every other way. After a month, he measures both groups.

## Why it matters

Watching alone can only show links. Changing one thing yourself is how you show a cause.

## Common mistake

Changing two things at once. Then you cannot tell which one made the difference.

## Three principles

- **Change one thing.** Only the variable under test.
- **Keep the rest.** Everything else stays the same.
- **Compare.** Against a group with no change.

## Related terms

- [Control Group](https://learn.benibix.com/term/general/control-group)
- [Randomized Controlled Trial (RCT)](https://learn.benibix.com/term/general/randomized-controlled-trial)
- [Hypothesis](https://learn.benibix.com/term/general/hypothesis)
- [Causation](https://learn.benibix.com/term/general/causation)
- [Observational Study](https://learn.benibix.com/term/general/observational-study)
- [Independent Variable](https://learn.benibix.com/term/general/independent-variable)
- [Dependent Variable](https://learn.benibix.com/term/general/dependent-variable)

## Told apart from

- [Experiment vs Observational Study](https://learn.benibix.com/compare/experiment-vs-observational-study): People think a big study that finds a link has found a cause. It has not. An observational study only watches, so a hidden factor may explain the link. An experiment changes one thing on purpose and compares it with a group left alone. That is how it can show a cause. Watching alone usually cannot.

![A group of people at the top is split at random into two groups. The left group, marked treatment, gets the real pill. The right group, marked control group, gets a look-alike pill with nothing in it. A band across both groups is marked blind: nobody knows which pill they got. At the bottom, the two groups' results are compared.](https://learn.benibix.com/diagrams/gen2-rct.svg)

---

Source: https://learn.benibix.com/term/general/experiment
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
