Charts

Scatter Plot Generator

An XY scatter plot with a least-squares trend line and the correlation coefficient stated.

Loading the tool…

Processing happens locally in your browser. What you paste or load is processed by this page and is not uploaded to a server. Nothing is stored unless you use a control that says it stores something, and you can clear anything this site has kept from the privacy page.

How to use this tool

  1. Paste two numeric columns: x first, then y. A third column is used as a label on each point.
  2. Select Plot the points.
  3. Read the r value in the summary before you trust the line. Below about 0.3 the trend line is drawing a relationship that is not in the data.
  4. Look at the cloud itself for a curve or two separate clusters — a straight-line fit reports neither.

What scatter plot generator does

A scatter plot is the chart that can tell you it has nothing to say. Every other chart type will happily draw a shape out of noise; a scatter shows the cloud as it is, and the shape either appears or does not. That makes it the right first look at any two variables you suspect are related.

Paste an x column and a y column and this plots them, fits a least-squares line and reports its equation along with Pearson’s r so you can see how much the line is worth. A third column is read as a point label. The correlation is stated plainly and so is the caveat: r measures how well a straight line fits, not whether one thing caused the other.

Frequently asked questions

Pearson’s r measures how closely the points follow a straight line, from −1 through 0 to +1. Roughly: above 0.8 is strong, 0.5 to 0.8 moderate, 0.3 to 0.5 weak, and below that the line is essentially decoration. It says nothing about the slope being large or important — only about how tightly the cloud hugs it.

No, and it is worth saying flatly because the line makes it feel proven. A correlation is consistent with causation in either direction, with both being driven by a third thing, and with coincidence. The plot tells you there is something to investigate; the investigation is a separate piece of work.

Almost always because the relationship is not straight. A least-squares line is the best straight line through the points and it will happily be fitted to a curve, a step or two separate clusters, reporting a middling r while describing none of them. Look at the cloud — that is what the chart is for.

Yes — add a third column and its text is attached to that point, shown when you hover over it in the rendered chart and carried in the SVG you download. It is useful for the handful of points you want to be able to identify without labelling all several hundred of them on the face of the chart.