Regression Residual Plot screenshot

Regression Residual Plot

Residuals from the least-squares line, drawn against x, with the largest absolute residual.

Privacy First
0 Runs
Updated 2026-11-06
No upload
Runs in this tab
No signup

What this page computes

Type the x and y values as comma-separated lists. The page fits the least-squares line, then draws e_i = y_i − (a + bx_i) against x, with a dashed zero line, the largest absolute residual in the title and one point per observation. The output pane holds the SVG source, which you can copy or download.

The shape is the diagnostic: a curve means the straight line is the wrong form, and a fan means the variance is not constant. The page draws the picture and computes nothing further; it reports no test and no confidence band. Fewer than three points, or a constant x column, is refused.

The residuals are computed in this tab from the same least-squares arithmetic the regression page uses, so identical data always draws the same plot.

The page fits the least-squares line to paired values and plots each residual — the vertical distance from a point to that line — against x. It needs at least three points, and a constant x column is refused because there is no line to take residuals from. The pattern in the residuals is the point: a curve or a fan means the straight line is not the whole story, and a shapeless band is what a straight-line fit is supposed to leave.

Plot residuals against x to see whether a straight line actually fits. Two comma-separated lists in.

How to use it

Type the x values as a comma-separated list and the y values the same way; the lists must be the same length and are read position by position. The fitted line is computed from the same data and the residuals are drawn on their own axis, so the plot is a diagnostic rather than a second view of the same points.

What the pattern in the residuals means

Each residual is y minus the fitted value, so a point above the line has a positive residual. A horizontal band is the ideal; a U-shape says a curve is being fitted with a straight line, and a widening fan says the spread of the errors grows with x, which is the assumption a regression test depends on. The page draws the diagnostic and does not compute a test for it.

What to Expect

Best for

  • Checking a linear fit before quoting its slope

What this tool keeps

  • Nothing leaves this tab: the arithmetic runs in the page you are reading, and a reload discards both the input and the result.

Frequently asked questions

What is a residual here?

The vertical distance from an observed point to the least-squares line: y minus the fitted value, so a point above the line has a positive residual.

What should the plot look like?

A shapeless horizontal band. A curve means a straight line is the wrong shape for the data, and a fan means the spread grows with x — either is a reason to look again before trusting the slope.

Is my data uploaded?

No. The fit, the residuals and the SVG are computed in this page, and nothing is posted to a server or stored.

Developer program

Build custom tools for your store

Join the SDK program to create useful ecommerce utilities for your store.