Skip to main content
v2026.11,986 entries · CC-BY 4.0

How to Make a Pareto Chart in Minitab: Steps and How to Read It

Make a Pareto chart in Minitab from raw or summarized data, set the dialog options, and read the Other bar and cumulative line correctly.

Written and maintained by CASRAI Editorial Board

Published

On this page

In Minitab, you make a Pareto chart from Stat > Quality Tools > Pareto Chart. You give the dialog either a column of raw defect labels (one row per event) or a column of category names plus a column of counts, and Minitab sorts the bars from largest to smallest and adds a cumulative-percentage line. This guide shows the data setup for each case, the dialog options that change the result, and how to read the output, including the always-last “Other” bar that surprises first-time users.

What Minitab’s Pareto chart is used for in research

Minitab’s documentation says the Pareto chart is used to identify “the most frequent defects, the most common causes of defects, or the most frequent causes of customer complaints,” so that improvement effort goes where the gain is largest. In a research setting the same logic applies to any counted category: reasons a specimen is rejected at intake, error types in a data-entry audit, protocol deviations by type, or causes of failed assay runs.

A Pareto chart is a bar chart sorted from largest to smallest, with frequency on the left axis, cumulative percentage on the right axis and the categories along the x-axis (Minitab, Pareto chart basics). It answers one question, which categories account for most of the count, and it does not test whether differences are statistically significant. For how the chart is built by hand and a laboratory worked example, see our Pareto chart guide. For where it sits among other Minitab tools, see What Is Minitab Used For?, and for control-chart methods that track a process over time, see SPC charts.

How to install or access Minitab

Minitab is commercial software, so access goes through the vendor. Minitab’s free-trial page lists the trial as including Minitab Statistical Software together with dashboards, data preparation and automation tools, collaboration tools, Minitab Workspace and Minitab DOE by Effex. Start the trial from the official Minitab website (minitab.com) rather than a third-party download link. If your university or employer already licenses Minitab, use the installer and licence details your IT or research-computing office provides.

The menu paths in this guide (Stat > Quality Tools > Pareto Chart) are the ones in Minitab’s current help pages. If your version shows a different layout, search the menus for “Pareto” or consult the Minitab help matching your version.

How to make a Pareto chart in Minitab step by step

Step 1: Choose raw or summarized data

Minitab accepts both layouts. With raw data, all observations sit in one worksheet column and each row records one event or defect, for example one row per rejected specimen holding the rejection reason. With summarized data, each row is a category and the value is a count or a calculated value such as a mean (Minitab, Pareto chart data considerations). The data table below sets out the dialog fields that tie to these two layouts.

Step 2: Build the worksheet

  1. Open a worksheet and name your columns.
  2. For raw data, enter one defect label per row in a single column.
  3. For summarized data, enter the category names in one column and the counts in a second column. Make each category name different within its first 15 characters, because Minitab’s documentation notes that the text names must be distinct in that span.

Step 3: Open the Pareto Chart dialog

  1. Choose Stat > Quality Tools > Pareto Chart.
  2. Raw data: put the label column in Defects or attribute data. Leave Summarized variables empty so each row counts as one event.
  3. Summarized data: put the column of category names in Defects or attribute data and the numeric counts column in Summarized variables (optional).
  4. Optionally set a By variable to create a separate chart for each level of a grouping column. All charts share the same y-scales.
  5. Choose the bar-order behaviour for grouped charts: Same bar order per graph (set by the first group) or Independent bar order per graph.
  6. Optionally enter a value for Combine the remaining defects after this cumulative percent. Minitab draws bars until the cumulative percentage passes that value and groups everything after it into “Other.”
  7. Keep Display percent scale and cumulative line selected if you want the right-hand percentage axis and the cumulative line.
  8. Click OK to create the chart.

Worked example with illustrative numbers

The figures below are an illustrative composite, not real laboratory data: 100 rejected specimens from an imaginary intake log. The percentages and cumulative percentages are simple arithmetic on those counts, and they show what the cumulative line will look like.

Rejection reason (category column) Count (Summarized variables) Percent Cumulative percent
Label error 38 38% 38%
Insufficient volume 24 24% 62%
Haemolysis 15 15% 77%
Wrong container 9 9% 86%
Late delivery 6 6% 92%
Clotted 5 5% 97%
Damaged tube 3 3% 100%

Enter the first two columns in the worksheet, place the reason column in Defects or attribute data and the count column in Summarized variables. The tallest bar is label error at 38 of 100, and the first three categories together reach 77%. If you enter 90 in the combine setting, bars run until the cumulative percentage passes 90, which here is after late delivery at 92%, and the clotted and damaged-tube specimens (8 in total) are grouped as “Other.”

How to read the Minitab Pareto chart output

Minitab’s key-results guidance for the Pareto chart has two steps: check the bar order, then check the cumulative line.

Bar order

Bars run from highest to lowest count, so the most frequent category is on the left. Minitab groups the remaining defects into “Other” once about 95% of the defectives are categorized, and the Other category is always displayed as the last bar, even when it is taller than bars to its left (Minitab, key results). In the example above, Other is a bar of 8 at the far right even if a larger Other had formed. Do not read a tall final bar as the biggest problem: it is a bucket of several small categories.

Cumulative line

The cumulative line starts at the top of the tallest bar and rises with each additional category. Minitab’s example reads it by adding categories: two named categories together reaching 65.1%, and the first four categories passing 90%. Use the line to answer how many categories you must address to cover a target share of the count. In our illustrative table, four categories cover 86% and five cover 92%.

Weighted Pareto charts and by-variable charts

Minitab’s basics page describes a weighted Pareto chart that adds a second measure such as cost to rework or severity, because a rare but costly defect can outrank a frequent cheap one. Frequency alone can therefore point effort at the wrong category. With a By variable, the charts share y-scales, which makes groups comparable, while Same bar order per graph keeps the categories in the same positions across groups so you can compare them directly. Independent bar order per graph re-sorts each group by its own counts, which shows each group’s own priorities but makes side-by-side comparison harder. Choose according to whether you are comparing groups or finding each group’s top problem. That choice is an editorial interpretation of the two documented options, not a Minitab recommendation.

The Minitab guidance also advises checking the data period (a short or unstable period can mislead), choosing categories and weights carefully, not ignoring small easy fixes, and keeping the Other category from becoming too large. A Pareto chart is a prioritising aid and does not replace analysis of causes. For cause analysis methods see What Is Root Cause Analysis?.

Troubleshooting Minitab Pareto charts

  • The bar counts look wrong. Check the data layout. If each row is a category with a count, the count column belongs in Summarized variables. If the rows are individual events, leave that box empty, because raw data are counted by rows.
  • Category names are not distinguished as expected. For summarized data, Minitab requires category names to be distinct within their first 15 characters. Shorten or rename them so the differences come first.
  • The last bar is taller than the bars next to it. That is the Other bar. It is always placed last, and it collects categories once about 95% of the defectives are categorized, or the cumulative percent you set.
  • The chart has too many small bars. Use Combine the remaining defects after this cumulative percent to group the tail, but keep Other from growing so large that it hides real categories.
  • Groups look different when using By variable. Check whether you chose same or independent bar order, because the choice changes how bars line up across the charts.
  • The ranking changes with the data period. Minitab warns that a short or unstable period misleads. Collect over a period that represents normal operation before you act on the ranking.

Free alternatives to Minitab for Pareto charts

The R package qcc, which is on CRAN, provides a pareto.chart() function. Per its reference page, data is a vector of values whose names label the bars, plot = TRUE draws the chart, and cumperc sets the tick marks on the right-hand percentage axis. The function returns an object holding the descriptive statistics used to draw the chart. An example from the documentation:

defect = c(80, 27, 66, 94, 33)
names(defect) = c("price code", "schedule date", "supplier code", "contact num.", "part num.")
pareto.chart(defect, ylab = "Error frequency")
Tool How you make a Pareto chart What the source says
Minitab Stat > Quality Tools > Pareto Chart, from raw or summarized data Minitab help pages
R with the qcc package pareto.chart(data) on a named vector of counts qcc reference page on CRAN

The R route needs a script rather than a dialog, but the output holds the same elements: sorted bars, a cumulative percentage axis and a statistics table. For other free statistics programs see Free Statistical Software for Research. If you plan to move on to inferential testing in Minitab, ANOVA in Minitab covers the dialog for comparing groups.

Sources

Data: Minitab Pareto Chart dialog fields and what each controls

Compilation of the Pareto Chart dialog fields documented in Minitab's help pages, with the data type each expects and its effect on the chart. Compiled from Minitab Support documentation read in November 2026.

Period covered: 2026.

Minitab Pareto Chart dialog fields and what each controls
Dialog fieldData layout it applies toWhat it does
Defects or attribute dataRaw data, or the category-name column for summarized dataHolds the defect labels; for summarized data category names must be distinct within their first 15 characters
Summarized variables (optional)Summarized dataNumeric counts or calculated values, one per category row
By variable (optional)EitherCreates a separate chart for each level of a grouping variable; charts share the same y-scales
Same bar order per graphBy-variable chartsBar order is set by the first group and reused for every chart
Independent bar order per graphBy-variable chartsEach chart sorts its own bars by its own counts
Combine the remaining defects after this cumulative percentEitherBars are generated until the cumulative percent passes the value; remaining defects are grouped as Other
Display percent scale and cumulative lineEitherAdds the right-hand percentage axis and the cumulative-percentage line

Sources

Compiled by CASRAI from the sources above. Free to reuse under CC BY 4.0 with attribution.

Follow CASRAI

Research-administration guidance, standards updates and independent tool reviews.

Ask CASRAI · free to try

Ask about How to Make a Pareto Chart in Minitab: Steps and How to Read It

2 free questions a day, no account.

An AI assistant for research: funder rules, compliance, methods and publishing. It links the sources behind its answers and labels answers that come from a web search.

Answers draw on CASRAI's guides and dictionary plus the federal and funder documents we index: Federal Register, Grants.gov, Regulations.gov and UKRI.

Works on this site and inside Claude, Cursor and the AI tools you already use.

Everything CASRAI publishes — this page, the dictionary, the guides and the news — stays open to read, with no account and no card.

Referenced across the research world

University of Cambridge logoColumbia University logoCrossref logoUniversity of Edinburgh logoHarvard University logoUniversity of Oxford logoPrinceton University logoStanford School of Medicine logoUniversity College London logoORCID logoUniversity of Cambridge logoColumbia University logoCrossref logoUniversity of Edinburgh logoHarvard University logoUniversity of Oxford logoPrinceton University logoStanford School of Medicine logoUniversity College London logoORCID logo
  • University of Cambridge logo
  • Columbia University logo
  • Crossref logo
  • University of Edinburgh logo
  • Harvard University logo
  • University of Oxford logo
  • Princeton University logo
  • Stanford School of Medicine logo
  • University College London logo
  • ORCID logo

View CASRAI adoption →