Change over time

Run chart

Shows observations in run or time order, usually around a median reference.

  • Plot
  • Trend over time
  • Process monitoring

What it answers

Does the process show sustained patterns over time?

Shape
Sequential points with a centre line
What it shows
Runs, shifts and unusual observations.

Example

The question

Is the average call waiting time stable from week to week?

Average call waiting time per week (seconds), with median

Average call waiting time per week (seconds), with medianPoints for weeks 1 to 14 around a median of 52.5 seconds. The last five weeks all sit above the median, a sign of a shift.Seconds30405060701234567891011121314Median 52.5
Average call waiting time per week (seconds), with medianPoints for weeks 1 to 14 around a median of 52.5 seconds. The last five weeks all sit above the median, a sign of a shift.Seconds3040506070135791113Median 52.5
Points for weeks 1 to 14 around a median of 52.5 seconds. The last five weeks all sit above the median, a sign of a shift.

Illustrative data. It belongs to no company.

When to use it

Use it when

Initial process monitoring without calculated control limits.

Avoid it when

When formal control-limit signalling is required.

How to read it

Follow observations against the centre line and inspect runs or shifts.

Note

Unlike a control chart, it does not require statistical control limits.

The data you need

Layout
Long table
Fields
Time: date/datetime or ordered number; Value: number
One row is
One observation at a time or ordered position. What is the grain?
Rules
Parse dates consistently and sort ascending. Resolve duplicate timestamps by a declared rule. Missing values are not automatically zero.
Optional
Optional Series. Use regular spacing for methods requiring it.
Preparation
Preserve observation order, choose a valid centre line such as the median and apply stated run-chart conventions.
Units
Time uses a stated date/time unit and sampling period; the value axis uses the measure's unit. Rates need their own explicit denominator.
Example of the input layout: Long tableA long table: one row per observation, few columns. New data adds rows.TimeValueAABBC
A long table: one row per observation, few columns. New data adds rows.

Worked example

Data 10,11,12,9,10 gives median 10. Plot in order with that reference; the short example demonstrates reading, not a reliable process rule.

TimeValue
2026-01-0130
2026-02-0134
2026-03-0138