index Introduction
Concepts, Techniques and Tools

Diagnostic Root Cause Analysis

Why did it happen?
Set 03 · Level 3 of the Analytics Ladder

From Symptoms to Root Causes

Descriptive analysis told you what happened. Now you find out why.

3Analytics Ladder · Level 03 of 10

A production line slows down. Customer complaints spike. A project runs over budget. These are symptoms. Diagnostic analysis asks the harder question: what actually caused this? Without a rigorous answer, organisations treat symptoms — spending resources on solutions that leave the underlying problem untouched.

Fixing a symptom feels productive. Fixing a root cause prevents the problem from returning.
8
Techniques
5
Tools Covered
80/20
Pareto Principle
5
Whys to Ask
Technique 01

Fishbone (Ishikawa) Diagram

Maps potential causes of a problem across six standard categories: People, Process, Equipment, Material, Method, Environment.

Technique 02

5 Whys

Iterative questioning technique. Ask "why?" five times in sequence to drill past surface explanations to the root cause.

Technique 03

Pareto Analysis (80/20)

Identifies the "vital few" causes — typically 20% of causes that produce 80% of the effect. Prioritises where to act first.

Technique 04

Correlation Analysis

Quantifies the strength of the relationship between two variables. Helps identify which factors move together with the problem.

Technique 05

Scatter Plot Analysis

Visualises the relationship between two numeric variables. Reveals direction, strength, and whether the relationship is linear.

Technique 06

Process Mapping

Documents a workflow visually to identify where failures, delays, or inefficiencies occur within a sequence of steps.

Technique 07

Cause-and-Effect Matrix

Rates potential causes by their impact score, combining structured thinking with numerical prioritisation.

Technique 08

FMEA

Failure Mode and Effects Analysis. Identifies potential failure points and calculates their Risk Priority Number (RPN = Severity × Occurrence × Detection).

Important — Correlation is not causation

Correlation analysis (Technique 04) identifies variables that move together — it does not prove one causes the other. A strong correlation is a starting point for further investigation, never a conclusion. Causation requires the deeper methods covered in Sets 04 and 05.

Techniques 01 & 02

Fishbone Diagram & 5 Whys

Two structured methods that turn vague frustration into specific, actionable root causes.

Fishbone (Ishikawa) Diagram

The fishbone diagram gets its name from its shape: a horizontal "spine" representing the problem, with diagonal "bones" branching off representing categories of causes. It was developed by quality engineer Kaoru Ishikawa and is now standard in manufacturing, healthcare, and service industries worldwide.

The six standard categories — remembered with the mnemonic 6M — are: Man (People), Machine (Equipment), Material, Method, Measurement, Mother Nature (Environment). In service environments these are often adapted to: People, Process, Technology, Policy, Place, Procedure.

PROBLEM STATEMENT People Training Fatigue Method Procedure Standards Machine Maintenance Calibration Material Quality Supplier Measurement Accuracy Environment Temperature Fishbone (Ishikawa) Diagram — 6M framework

5 Whys Method

The 5 Whys is the simplest root cause technique. Start with a problem statement and ask "why?" — each answer becomes the next question. Five iterations typically reach a root cause that is actionable, rather than a symptom.

Business Example — Manufacturing
Why did the machine stop?
IterationQuestionAnswer
Why 1Why did the machine stop?The fuse blew due to an overload.
Why 2Why was there an overload?The bearing was not lubricated properly.
Why 3Why was it not lubricated?The lubrication pump was not working.
Why 4Why was the pump not working?The pump's intake shaft was worn.
Why 5Why was the shaft worn?There was no maintenance schedule or filter on the pump.

Root cause identified: No preventive maintenance schedule. Fix: implement scheduled maintenance and install a filter — not replace the fuse.

When 5 Whys falls short

The 5 Whys works best for simple, linear cause chains. When a problem has multiple interacting causes (which most complex business problems do), a fishbone diagram or FMEA is more appropriate — it forces you to explore all categories simultaneously rather than pursuing a single thread.

Technique 03

Pareto Analysis — The 80/20 Rule

Not all causes are equal. A small number of causes produce the majority of the effect.

The Pareto Principle, named after Italian economist Vilfredo Pareto, states that in many systems, roughly 80% of effects come from 20% of causes. In business diagnostics this translates to: a small number of failure types, complaint categories, or defect causes are responsible for most of the problem.

Pareto analysis is not a precise law — sometimes it is 70/30 or 90/10. What it reliably tells you is that causes are not equal, and acting on the top contributors delivers far more return than addressing all causes equally.

Business Example — Customer Service
Complaint types ranked by frequency

A service manager has 1,200 complaints to address. Instead of allocating resources equally across all complaint types, she runs a Pareto analysis and discovers that two categories — Late Delivery and Wrong Item — account for 63% of all complaints. Solving just these two issues eliminates over half the complaint volume.

How to build a Pareto chart

StepActionPurpose
01List all causes/categories and count their frequencyEstablishes the raw data
02Sort from highest to lowest frequencyRequired for the visual to work correctly
03Calculate each category's % of totalIdentifies individual contribution
04Calculate cumulative % as you move down the listThis is the key line — shows where 80% is crossed
05Draw bars (frequency) + line (cumulative %)Creates the dual-axis Pareto chart
06Draw a horizontal line at 80% on the cumulative axisEverything to the left of where the line crosses is your "vital few"
Techniques 04 & 05

Correlation & Scatter Plot Analysis

Quantify and visualise the relationship between two variables — as a starting point for root cause investigation.

Correlation analysis produces a correlation coefficient (r) between −1 and +1. It measures both the strength and direction of a linear relationship between two numeric variables.

r valueStrengthDirectionBusiness interpretation
+0.9 to +1.0Very strongPositiveAs X increases, Y almost always increases too. Very strong association worth investigating.
+0.6 to +0.9StrongPositiveA clear positive pattern — X is likely a meaningful driver of Y.
+0.3 to +0.6ModeratePositiveSome relationship, but other factors also matter.
−0.3 to +0.3Weak / NoneMixedLittle evidence of a linear relationship.
−0.6 to −0.3ModerateNegativeAs X increases, Y tends to decrease.
−1.0 to −0.6StrongNegativeStrong inverse relationship.
⚠ The golden rule — Correlation ≠ Causation

Ice cream sales and drowning rates are strongly correlated. Both increase in summer — because of the heat, not because ice cream causes drowning. A correlation tells you two variables move together. It does not tell you why, or which causes which. Always ask: is there a third variable (confounder) that explains both?

Scatter Plot — what to look for

Pattern: Upward slope

Positive correlation

More training hours → higher performance scores. Points cluster around an upward-sloping line.

Pattern: Downward slope

Negative correlation

More machine age → fewer units produced. Points cluster around a downward-sloping line.

Pattern: No pattern

No relationship

Shoe size and sales performance. Points scattered randomly with no discernible slope.

Pattern: Curved

Non-linear relationship

Correlation coefficient will understate the relationship. A linear model is inappropriate. Consider log transformation or polynomial regression.

Techniques 06 · 07 · 08

Process Mapping, C&E Matrix & FMEA

Three structured tools for systematic failure investigation in complex processes.

Process Mapping

A process map documents a workflow as a sequence of steps, decisions, and handoffs. It makes invisible waste and failure points visible. The most common format is a swim lane diagram — each lane represents a team or role, showing who does what and where handoffs occur.

In root cause analysis, the process map is used to identify: where in the process the defect could be introduced · which steps have no quality check · where delays accumulate · which handoffs create communication failures.

Cause-and-Effect Matrix (C&E Matrix)

The C&E Matrix scores potential causes against output requirements, weighting each by importance. It bridges the fishbone's brainstorming phase with quantitative prioritisation.

Potential CauseOutput 1 (weight: 9)Output 2 (weight: 6)Output 3 (weight: 3)Total Score
Insufficient training39181
Equipment malfunction931108
Supplier variability13954

Score = Σ(Rating × Weight). Higher score = higher priority cause to investigate.

FMEA — Failure Mode and Effects Analysis

FMEA identifies potential failure modes in a process, their effects, and calculates a Risk Priority Number (RPN):

RPN = Severity (1–10) × Occurrence (1–10) × Detection (1–10)
FactorWhat it measuresScore 1 = Score 10 =
SeverityImpact on the customer if the failure occursMinor annoyanceSafety hazard / complete failure
OccurrenceHow often the failure mode happensAlmost neverHappens nearly every cycle
DetectionHow unlikely it is to catch before reaching the customerAlways detectedNever detected

Failure modes with the highest RPN scores are addressed first. An RPN above 100–120 typically triggers immediate corrective action.

Tool Guide 🟢 Start Here

Microsoft Excel

Pareto charts, correlation, scatter plots, and FMEA templates — all without add-ins.

🟢 Start HerePareto Chart
01
Prepare your data
Two columns: Category (text) and Count (number). Do not sort yet — Excel's Pareto chart sorts automatically.
02
Select data and insert
Select both columns → Insert → Charts → Insert Statistic Chart → Pareto
03
Read the chart
Bars (left axis) = frequency per category, sorted highest to lowest. Orange line (right axis) = cumulative percentage. Where the line crosses 80% — everything to the left is your "vital few."
What to tell stakeholders
"Two complaint types — late delivery and wrong items — account for 63% of all complaints. Resolving these two issues will have more than 3× the impact of fixing all remaining categories combined."
04
Manual cumulative % (if needed)
In column C: =B2/SUM($B$2:$B$10) for %. In column D: =D1+C2 for cumulative %. This gives you the data to build a custom chart if you need more control.
🟢 Start HereCorrelation & Scatter Plot
01
Correlation coefficient (single pair)
Formula: =CORREL(A2:A100, B2:B100) — returns r between −1 and +1. Interpret using the table in the Correlation tab.
02
Correlation matrix (multiple variables)
Data → Data Analysis → Correlation → select all numeric columns as Input Range → tick "Labels in First Row" → choose output location → OK. Produces a full correlation matrix.
03
Scatter plot
Select two numeric columns → Insert → Charts → Scatter (X,Y) → choose first option (dots only).
04
Add trendline and R²
Right-click any dot on the scatter chart → Add Trendline → tick Display Equation on chart and Display R-squared value. R² = r² — tells you what % of variance in Y is explained by X.
🟢 Start HereFMEA Template

Excel is the most common tool for FMEA. Build a table with these columns:

ColumnContentFormula (if any)
Process StepName of the stepText
Potential Failure ModeWhat could go wrongText
Potential EffectImpact on output/customerText
Severity (S)1–10 ratingNumber
Potential CauseRoot cause of failureText
Occurrence (O)1–10 ratingNumber
Current ControlsExisting detection methodsText
Detection (D)1–10 ratingNumber
RPNRisk Priority Number=S*O*D
Recommended ActionWhat to do for high RPNsText

Sort by RPN column descending to prioritise. Apply conditional formatting: Home → Conditional Formatting → Color Scales to the RPN column for instant heat-map effect.

Tool Guide 🟡 Go Deeper

Minitab & IBM SPSS

Purpose-built statistical tools with dedicated quality and diagnostic procedures.

🟡 Go DeeperMinitab — Pareto Chart & Fishbone

Minitab is the industry standard for quality analysis (Six Sigma, Lean). Its quality tools menu makes Pareto and fishbone creation faster than Excel.

01
Pareto Chart
Stat → Quality Tools → Pareto Chart → enter the column containing defect/complaint categories in "Defects or attribute data in" → click OK. Minitab automatically sorts, calculates cumulative %, and draws both bars and the cumulative line.
02
Cause-and-Effect (Fishbone) Diagram
Stat → Quality Tools → Cause-and-Effect → enter your effect (problem) in "Effect" → enter causes in the six category branches (Machines, Methods, Materials, Measurements, People, Environment) → OK. Minitab generates the diagram automatically.
03
Reading Minitab output
Minitab's Pareto output shows the exact cumulative % line and annotates which categories cross the 80% threshold. The Session Window also shows a table with counts and percentages.
🟡 Go DeeperSPSS — Correlation Analysis
01
Bivariate Correlation (Pearson)
Analyze → Correlate → Bivariate → move all numeric variables to the Variables box → ensure Pearson is ticked → tick Flag significant correlations → OK.
02
Reading the correlation matrix
SPSS produces a symmetric matrix. Each cell shows the Pearson r value and a two-tailed p-value. Cells marked with ** are significant at p<.01; those with * at p<.05. Focus on cells where |r| > 0.3 AND marked significant.
Output includes
Pearson r value · Sig. (2-tailed) p-value · N (sample size) · ** and * significance flags
03
Spearman (non-parametric) alternative
If your data is ordinal or not normally distributed: Analyze → Correlate → Bivariate → tick Spearman instead of (or in addition to) Pearson.
04
Scatter Plot in SPSS
Graphs → Chart Builder → Scatter/Dot → Simple Scatter → drag variables to X and Y axes → OK. Double-click the chart in Output to open the Chart Editor and add a regression line.
Tool Guide 🔵 Full Power

Python — Diagnostic Analysis

Automate Pareto charts, correlation matrices, scatter plots, and FMEA scoring at scale.

🔵 Full PowerPareto Chart
# Pareto chart import pandas as pd import matplotlib.pyplot as plt data = {'Complaint': ['Late Delivery','Wrong Item','Damaged','Billing','Other'], 'Count': [342, 218, 165, 124, 55]} df = pd.DataFrame(data).sort_values('Count', ascending=False) df['CumPct'] = df['Count'].cumsum() / df['Count'].sum() * 100 fig, ax1 = plt.subplots() ax2 = ax1.twinx() ax1.bar(df['Complaint'], df['Count'], color='steelblue', alpha=0.8) ax2.plot(df['Complaint'], df['CumPct'], color='orange', marker='o', linewidth=2) ax2.axhline(80, color='red', linestyle='--', alpha=0.7, label='80% line') ax2.set_ylim(0, 110) ax1.set_ylabel('Frequency') ax2.set_ylabel('Cumulative %') plt.title('Pareto Chart — Customer Complaints') plt.tight_layout() plt.show()
🔵 Full PowerCorrelation Matrix & Scatter Matrix
# Correlation matrix with heatmap import seaborn as sns corr = df.select_dtypes(include='number').corr() sns.heatmap(corr, annot=True, fmt='.2f', cmap='RdYlGn', center=0, vmin=-1, vmax=1, square=True) plt.title('Correlation Matrix') plt.show() # Scatter matrix (all pairs at once) pd.plotting.scatter_matrix(df.select_dtypes(include='number'), figsize=(10,10), diagonal='hist', alpha=0.5) plt.suptitle('Scatter Matrix — All Variable Pairs') plt.show() # Single scatter with regression line from scipy import stats slope, intercept, r, p, se = stats.linregress(df['x_var'], df['y_var']) print(f"r = {r:.3f}, r² = {r**2:.3f}, p = {p:.4f}") sns.regplot(data=df, x='x_var', y='y_var', ci=95) plt.show()
🔵 Full PowerFMEA RPN Calculator
# FMEA from Excel/CSV df_fmea = pd.read_excel('fmea_data.xlsx') df_fmea['RPN'] = df_fmea['Severity'] * df_fmea['Occurrence'] * df_fmea['Detection'] df_fmea = df_fmea.sort_values('RPN', ascending=False) # Highlight critical failures (RPN > 100) critical = df_fmea[df_fmea['RPN'] > 100] print(f"Critical failure modes requiring immediate action: {len(critical)}") print(critical[['FailureMode','Severity','Occurrence','Detection','RPN']])
Interactive Practice

Three Simulators

Practice the three core diagnostic tools before applying them to real work.

Simulator 1 · Pareto Analyser

Eight complaint types are listed with their frequencies. Identify which categories form the "vital few" — the ones that cross the 80% cumulative threshold. Click each bar to select/deselect it as a vital-few category.

Click bars to mark as vital few · Total complaints: 1,240
Select the bars that form the 80% vital few, then check.

Simulator 2 · 5 Whys Walk-Through

Follow a 5 Whys analysis for a real business problem. At each step, select the most analytically sound "why" answer to progress toward the root cause.

Problem: "Customer churn rate increased by 18% in Q3."
Click the best answer for Why 1 to begin.

Simulator 3 · Root Cause Classifier

Classify each potential cause into the correct fishbone category by clicking the cause, then clicking the category it belongs to.

Click a cause to select it (it will highlight), then click the category where it belongs.
Best Practice

Common Mistakes

These are the errors that turn root cause analysis into a political exercise instead of an analytical one.

Mistake 01

Stopping at the first cause found

The first explanation is almost always a symptom, not a root cause. If you stop after one "why," you will solve the fuse (symptom) not the missing maintenance schedule (root cause). Always drill deeper.

Mistake 02

Confusing correlation with causation

Two variables that move together are not necessarily connected. Before acting on a correlation, ask: is there a plausible mechanism? Could a third variable explain both? Run the analysis but state the limitation explicitly.

Mistake 03

Fishbone sessions dominated by one voice

The fishbone diagram is a brainstorming tool. Its value comes from diverse perspectives filling in the branches. If one person dominates, critical causes in other categories (often Environment or Measurement) will be missed.

Mistake 04

Treating all FMEA RPNs as equally reliable

RPN scores depend entirely on the quality of the ratings. Inconsistent raters (one person rates Severity 3, another rates the same failure 7) make the RPN meaningless. Always calibrate raters before scoring.

Mistake 05

Using Pareto to ignore the "trivial many"

The 80/20 rule says act on the vital few first — not ignore everything else forever. After resolving the top 20%, the next tier becomes the new top 20%. Pareto analysis drives prioritisation, not permanent neglect.

Mistake 06

Skipping the verification step

Root cause analysis produces a hypothesis, not a proven cause. After identifying the likely root cause, you must verify it — check if the problem disappears when the cause is removed. Without verification, you are still guessing.

Set 02 · Key Takeaway
The goal is not to find a cause — it is to find the cause that, when addressed, prevents the problem from recurring.
Assessment

Knowledge Check

Five questions across all techniques in Set 02.

Q1 — A machine stops working. The investigation reveals: overload → poor lubrication → faulty pump → worn shaft → no maintenance schedule. What is the root cause?
A
The overload that blew the fuse
B
The faulty lubrication pump
C
No maintenance schedule or filter — the deepest correctable cause
D
The worn pump shaft
The 5 Whys drills through symptoms to find the root cause — the systemic issue that, when fixed, prevents recurrence. The fuse, lubrication, pump, and shaft are all symptoms of the real problem: no preventive maintenance system. Replacing the fuse without fixing the maintenance gap guarantees the problem returns.
Q2 — A Pareto analysis of 500 defects shows five categories: A=190, B=145, C=85, D=55, E=25. Which categories form the "vital few" (cross the 80% threshold)?
A
Category A only (38%)
B
Categories A and B (38% + 29% = 67% — wait, plus C: 67%+17%=84%) — A, B, and C cross 80%
C
All five categories
D
Categories A, B, C, and D
Cumulative %: A=38%, A+B=67%, A+B+C=84%. Categories A, B, and C together account for 84% of defects — crossing the 80% threshold. These three are the "vital few." Resolving them eliminates most of the problem. D and E (the "trivial many") account for only 16% combined.
Q3 — A correlation analysis shows r = +0.82 between employee training hours and customer satisfaction scores. What can you correctly conclude?
A
Training causes higher customer satisfaction — invest in more training immediately
B
There is a strong positive association — employees with more training tend to have higher satisfaction scores, but causation requires further investigation
C
Training explains 82% of the variance in customer satisfaction
D
The relationship is moderate and not worth acting on
r=0.82 is a strong positive correlation — but correlation never proves causation. It is possible that better-performing branches both train more AND serve more satisfied customers (a confounder). The correct conclusion is "strong association — worth investigating further with regression and controlled analysis." Note: r²=0.67 means training explains 67% of variance (not 82%).
Q4 — An FMEA rates a failure mode as: Severity=8, Occurrence=3, Detection=9. What is the RPN and what does it indicate?
A
RPN = 20. Low risk — no action needed.
B
RPN = 80. Moderate risk — monitor.
C
RPN = 216. High risk — the failure is severe when it occurs and very hard to detect. Requires immediate action.
D
RPN = 216. Low risk — occurrence is only 3.
RPN = 8 × 3 × 9 = 216. Despite infrequent occurrence (3), the combination of high severity (8) and very difficult detection (9) produces a high RPN. The failure is rare but catastrophic when it occurs — and your quality system almost never catches it before reaching the customer. This demands immediate corrective action to improve detection controls.
Q5 — Which tool is most appropriate for identifying WHERE in a multi-step service process failures and delays are being introduced?
A
Pareto Analysis — to rank failure frequencies
B
Fishbone Diagram — to categorise causes by type
C
Process Mapping — to visualise the workflow and identify failure and delay points step by step
D
5 Whys — to drill into a specific known failure
Process mapping is the tool for understanding where in a sequence of steps failures occur. The fishbone identifies what categories of causes exist. The Pareto ranks them by frequency. The 5 Whys drills into a specific known failure. Process mapping is used when you need to see the full workflow first — before you can even know where to focus.