# Replication Study

> You do a study again. Then you check that the result is the same.

**Field:** General Knowledge  
**Category:** Research  
**Also known as:** Research Replication, Reproducibility, Replication Crisis

## Think of it like

It is like asking a friend to bake from your recipe. If their cake turns out the same, the recipe works.

## Definition

Replication is repeating a study to see if the result comes out the same. A new team follows the same method, often with new people. If the result holds, it becomes more trusted. If it does not, the first result may have been luck or a flaw. When many famous results failed to repeat, people called it the replication crisis.

## Example

In 2015, a large team tried to repeat 100 psychology studies. Of the originals, 97% had found a clear result. Of the repeats, only 36% did.

## Why it matters

One study can be wrong by chance. A result that repeats is one you can start to rely on.

## Common mistake

Trusting a single striking study. Wait for a repeat before treating it as settled.

## Three principles

- **Do it again.** Same method, new people.
- **Trust grows.** Each repeat adds weight.
- **Failures teach.** A miss may show a flaw.

## Related terms

- [Peer Review](https://learn.benibix.com/term/general/peer-review)
- [Publication Bias](https://learn.benibix.com/term/general/publication-bias)
- [Reliability](https://learn.benibix.com/term/general/reliability)
- [P-Value](https://learn.benibix.com/term/general/p-value)
- [Statistical Significance](https://learn.benibix.com/term/general/statistical-significance)
- [Ego Depletion](https://learn.benibix.com/term/general/ego-depletion)

![Two bars for 100 psychology studies. The first bar, original studies, is 97 percent full and marked clear result. The second bar, repeat studies, is 36 percent full. A note under them says the 2015 project tried to repeat all 100.](https://learn.benibix.com/diagrams/gen2-replication.svg)

---

Source: https://learn.benibix.com/term/general/replication
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.
