A scatter plot places one dot for each data point using two measurements — one on the X axis, one on the Y axis. The pattern the dots form reveals whether the two measurements are related.
Use the free scatter plot maker to paste X and Y values, add a trendline, and export the result.
The core idea
Every row in your data becomes a single dot. The horizontal position of that dot shows the first measurement (X variable); the vertical position shows the second (Y variable). When you step back and look at all the dots together, the overall pattern tells you whether the two variables move together, move apart, or have no consistent relationship.
This makes scatter plots the standard tool for exploring relationships between two numeric variables.
What patterns mean
- Upward-left-to-right slope → positive correlation. As X increases, Y tends to increase. Example: taller people tend to weigh more.
- Downward-left-to-right slope → negative correlation. As X increases, Y tends to decrease. Example: more hours of TV watched, lower test scores (on average).
- No visible pattern / random cloud → no linear correlation. The two variables don't move together consistently.
- Curved pattern → nonlinear relationship. There's a relationship, but it's not a straight line — a bend, a U-shape, an exponential curve.
- Points far from the main cluster → outliers that may deserve investigation.
Correlation is not causation
A scatter plot shows association, not cause. If study hours and exam scores form an upward slope, it means they move together — not necessarily that studying causes the higher scores. A third variable (student motivation, prior knowledge) could explain both. Scatter plots are the starting point for analysis, not the conclusion.
Reading correlation strength
- Tight cluster along a line → strong correlation. Predictions from X to Y would be fairly accurate.
- Loose cloud with a recognizable direction → weak correlation. Direction is visible but individual predictions are unreliable.
- Horizontal band → no correlation. Knowing X tells you nothing about Y.
Correlation is measured with the correlation coefficient (r), which runs from −1 (perfect negative) through 0 (none) to +1 (perfect positive).
Scatter plot vs line chart
Both use dots on X and Y axes, but they answer different questions:
| Scatter plot | Line chart | |
|---|---|---|
| X axis type | Numeric (continuous) | Usually time / ordered category |
| Purpose | Show relationship between two variables | Show change over time |
| Dots connected? | No | Yes |
| Typical question | "Does X predict Y?" | "How did Y change over time?" |
If your X axis is time and you care about trend, use a line chart. If your X axis is a measurement and you care about whether two variables are related, use a scatter plot.
When to use a scatter plot
- Exploring whether two numeric variables are correlated
- Checking for outliers across two dimensions
- Visualizing regression lines and model fit
- Any "does X predict Y?" question (height vs weight, temperature vs ice cream sales)
FAQ
How many data points do scatter plots need?
Scatter plots work best with 20–500 points. Fewer than 10 points make patterns hard to see; more than a few thousand creates overplotting where dots cover each other. For very large datasets, consider adding transparency or using a hexbin/density plot.
What is the difference between a scatter plot and a bubble chart?
A bubble chart is a scatter plot with a third variable encoded as the size of each dot. Each dot's position (X, Y) represents two variables; the dot's size represents a third. Use a bubble chart when you want to show three numeric dimensions at once.
Can I use a scatter plot with categorical X variables?
Technically yes, but a dot plot or strip plot is a better fit. Scatter plots are designed for two continuous numeric variables. When X is categorical (e.g., department, country), the visual convention is a dot plot or grouped bar chart.
References
How this guide is reviewed
This guide is maintained by the ChartsMakers Editorial Team and reviewed for statistical accuracy, product behavior, and clarity. Sources used for factual checks are listed in the References section. See our editorial policy.