Operations Mapping tool

Scatter Diagram

Visualizes the relationship between two quantitative variables and examines patterns, outliers, and groups.

A scatter diagram plots paired observations on x and y axes. Scales, units, horizon, missing data, and potential third variables belong in interpretation; correlation does not establish causality.

Core question

What pattern exists between X and Y, and which observations or groups need explanation?

Plan Scatter Diagram Method guide

Start comparison

Give feedbackIs this method useful to you?

Participants: 1-4
Time: 30-90 min

Scatter Diagram uses paired x-y observations with axes, group encoding, and optional trend analysis. Assessments remain justified and context-bound.

Paper illustration of Scatter Diagram with its method-specific working model.

Define variables
Define variables
Specify X, Y, unit, population, and horizon.
Check data
Check data
Check missing data, duplicates, measurement errors, and range.
Diagram
Diagram
Plot points with suitable scale and relevant segment encoding.
Interpret
Interpret
Describe form, direction, strength, outliers, and alternatives.

Update after new evidence or a material context change and retain the previous version.

A good fit when

For two quantitative variables with paired observations and sufficient variation.

Ideal for

Quantitative root cause analysis
Process and quality analysis
Testing hypotheses with field data
A preliminary step to deeper analysis

Not good for

Very small data sets
Complex multivariate relationships without statistics
Concluding causation without context

Outputs

annotated scatter diagram
annotated scatter diagram with traceable sources, assumptions, and domain decisions.
Decision and review trail
Owners, dates, and next review for annotated scatter diagram.

annotated scatter diagram

Fictional worked example

paired x-y observations with axes, group encoding, and optional trend analysis as a precise working structure with a fictional example.

Variables

X/Y · unit · population

Review minutes / follow-ups; 142 cases.

Data quality

Missing · exclusion · measurement error

One pause outlier corrected.

Pattern

Form · direction · group

Positive; complex cases separate cluster.

Interpretation

Finding · alternative · next test

Segment; no causal claim.

The example demonstrates the domain logic of Scatter Diagram; worksheets remain blank.

NIST Engineering Statistics Handbook: Scatter Plots

First step

Start with the core question: What pattern exists between X and Y, and which observations or groups need explanation?

Open the method guide

Where to go next?

Operations

Root Cause Analysis

Tests the suspected correlation as a hypothesis in a deeper root cause analysis.

Decision Making

Pareto Analysis

Prioritizes the segments that stand out in the diagram by their share of the effect.

Deep dive

Purpose

When the question is whether two measures are related, the method makes patterns in the data picture visible. It separates felt correlations from relationships that actually show up in the data.

How it works

Measurement pairs are collected over a period and read as a scatter cloud. Direction, spread, and outliers produce an initial picture of possible relationships and the limits of what the data can say. This makes correlation checkable without prematurely mistaking it for causation.

In detail

A scatter diagram makes suspected relationships visible as a data pattern before causes are asserted. Clean measurement pairs, sufficient spread, and deliberate consideration of outliers determine how much the data can say. The scatter cloud helps strengthen or weaken hypotheses, or shows when segmentation becomes necessary.

Facilitation

Check whether both measures share the same period, the same unit, and the same context before interpreting the scatter cloud. The insight value often grows more from outliers than from a premature trend line. Close with a follow-up question for deeper analysis and avoid any premature claim about causation.

The method guide walks execution through 4 phases, timing, 4 pitfalls, and clear stop criteria.

Open method guide

Your perspective

Does this method help with your work?

Your feedback helps shape the next improvements to methodatlas.

Sources and topics

Topics

Root cause Quality Visualization

Sources

NIST Engineering Statistics Handbook: Scatter Plotsitl.nist.govNIST Engineering Statistics Handbook; describes scatter plots for examining relationships between two variables.

Artifact templates

Scatter Diagram: WorksheetPlan Scatter Diagram around its domain steps and the concrete decision question.

markdown

scatter-diagram-working-template.md

Plan Scatter Diagram around its domain steps and the concrete decision question.

Scatter Diagram: Worksheet

Question

To be confirmed

Desired outcome

To be confirmed

Scope

Full workshop Time: 30–60 minutes

Complete this worksheet on paper or in your own document during the work.

Preparation for this scope

Method setup

Materials: paired quantitative data, definitions and units, segment and quality attributes, shared workspace, source links, and decision log.
Roles: Analyst · domain expert · data owner
Advance information: Collect paired quantitative data, definitions and units, segment and quality attributes in advance and mark open assumptions.
Overall time needed: 30–60 minutes
Setup: Prepare paired x-y observations with axes, group encoding, and optional trend analysis visibly and calibrate assessment terms before starting.