Pareto Analysis in Minitab – Tabtrainer® for Process Focus

By completing this Pareto Analysis training, you will learn to:

• Understand the principles of Pareto analysis and its significance in identifying improvement priorities.

• Analyze data sets for frequency and impact of causes in a process.

• Interpret and create Pareto charts to visualize key issues and improvement opportunities.

• Apply Pareto analysis in real-world scenarios, such as evaluating supplier performance and delivery reliability.

• Use data-driven insights to recommend actionable improvements for process optimization.

  Business Case Explanation:

  The business case revolves around Smartboard Company, a manufacturer of skateboards that has been facing unplanned production downtimes. These disruptions are caused by delayed deliveries of ball bearings, a critical component for skateboard assembly.

  To address this issue, Smartboard Company collaborates with two suppliers, identified as Supplier A and Supplier B. Despite placing orders in a timely manner, delivery delays from these suppliers have led to inefficiencies and financial losses due to halted production.

  The objective of this business case is to determine which supplier offers better delivery performance and reliability using Pareto analysis. This involves evaluating and comparing the delivery times of both suppliers to identify:

  1. Delivery Speed: How quickly each supplier fulfills orders.

  2. Delivery Reliability: The consistency of delivery times, ensuring predictability for production planning.

  3. Impact on Downtime: Analyzing how delays from each supplier affect overall production.

  By categorizing delivery times into predefined time intervals (e.g., less than 19 days, 19–21 days, etc.) and visualizing the data using a Pareto chart, the analysis identifies the key delivery performance trends and highlights areas for improvement.

  The outcome of this analysis provides a data-driven recommendation to the management of Smartboard Company on which supplier to prioritize. Selecting the more reliable supplier will enhance operational efficiency, reduce downtime, and ultimately improve profitability.

By the end of this lesson, participants will:

1. Understand how to structure and prepare a dataset for analysis.

2. Perform statistical evaluations of delivery performance.

3. Identify key delivery trends using Pareto charts and descriptive statistics.

4. Apply Minitab tools to derive actionable insights for supplier evaluation.

Lesson Content:

1. Dataset Overview and Preparation:

   • Introduction to the Smartboard Company’s dataset.

   • Importing data into Minitab and examining its structure: order number, order date, and delivery date.

   • Calculating delivery times as the difference between order and delivery dates.

2. Data Quality and Completeness Check:

   • Using Minitab’s worksheet information tool to assess data scope (e.g., missing values, column types).

3. Statistical Summary:

   • Calculating key metrics like mean, median, standard deviation, and range.

   • Interpreting delivery performance metrics for supplier evaluation.

4. Visualization:

   • Creating a simple chart to understand data distribution.

   • Identifying delivery trends and variability through statistical parameters.

5. Insights and Recommendations:

   • Leveraging descriptive statistics to compare suppliers’ performance.

   • Making data-driven recommendations to improve supplier selection and planning reliability.

This lesson provides hands-on training to effectively analyze supplier performance, combining statistical methods with practical applications in Minitab.

Lesson Content:

1. Visualizing Data with Histograms:

   • Purpose: Display frequency distributions of delivery times.

   • Steps in Minitab:

     1. Navigate to the Graphs tab and select Histogram.

     2. Choose the appropriate histogram type (e.g., simple histogram or histogram with fit).

     3. Customize bar intervals based on data range and sample size.

   • Example:

     • Data column: C4 Difference.

     • Observations: A right-skewed distribution indicating many shorter delivery times and fewer long delays.

     • Insights: Use the histogram to identify performance trends and variances.

2. Introduction to Pareto Analysis:

   • Purpose: Prioritize key contributors to delays using absolute and relative frequencies.

   • Steps in Minitab:

     1. Navigate to Statistics > Quality Tools > Pareto Chart.

     2. Select the dataset column (C4 Difference) as the input.

     3. Adjust settings to maximize differentiation (e.g., activate Do not combine).

   • Output:

     • Left vertical axis: Absolute frequencies (number of orders).

     • Right vertical axis: Cumulative relative frequencies (percentage).

     • Example: Orders with delays categorized into 26 value ranges based on data intervals.

3. Customizing Value Ranges:

   • Define specific intervals (e.g., <19 days, 19–21 days) provided by the Smartboard Company.

   • Assign and recode values using Minitab’s Recode to Text feature.

4. Insights from Pareto Charts:

   • Identify categories contributing to the majority of delays.

   • Use the cumulative curve to pinpoint critical improvement areas.

Outcome:
By the end of the session, participants will have mastered the basics of data visualization and Pareto analysis in Minitab, enabling them to identify key performance issues and make data-driven decisions for improvement.

Learning Objectives:
Participants will learn to:

1. Define specific value ranges for categorizing data.

2. Use Minitab’s recode function to assign continuous numeric data to categorical value ranges.

3. Handle missing data effectively by creating appropriate value categories.

Lesson Content:

1. Defining Value Ranges:

   • Objective: Categorize delivery times into meaningful ranges provided by Smartboard Company:

     • Less than 19 days

     • 19–21 days

     • 22–24 days

     • 25–28 days

     • 29–35 days

     • Over 35 days

     • Open (missing values)

2. Setting Up a New Column:

   • Steps:

     1. Create an empty column (C5: Delivery Days).

     2. Assign this column to store categorized data.

3. Recoding Values:

   • Methodology:

     • Access Data > Recode > To Text.

     • Select C4: Difference as the input column.

     • Use the Recode Ranges of Values option to assign continuous values into defined categories.

   • Implementation:

     • Enter lower and upper endpoints for each range.

     • Assign descriptive names (e.g., “Less than 19,” “19 to 21”).

     • Include an additional category for missing values using the * symbol for both endpoints, labeled as “Open Orders.”

4. Including Endpoints:

   • Ensure both lower and upper endpoints are included by selecting the Both endpoints option.

5. Validating Results:

   • Activate the Show Summary Table option for an overview of defined ranges and assigned categories.

   • Verify that the ranges are correctly assigned and comprehensive.

6. Insights from the Summary Table:

   • Example results:

     • 7 orders delivered in less than 19 days.

     • 471 orders delivered between 19–21 days.

     • 3 open orders with missing delivery dates.

7. Storing Recoded Data:

   • Specify C5: Delivery Days as the storage column.

   • Check the output to ensure the column contains text-coded categories (indicated by the T index in the column header).

Outcome:
By the end of this lesson, participants will be proficient in defining value ranges, recoding data, and handling missing values in Minitab. This skill enables clear categorization and prepares data for advanced analyses, such as Pareto charts.

Learning Objectives:
Participants will learn to:

1. Interpret Pareto charts with custom-defined value ranges.

2. Understand cumulative percentages and their implications for decision-making.

3. Evaluate delivery performance based on frequency distributions.

Lesson Content:

1. Setting Up the Pareto Chart:

   • Use Minitab’s Pareto chart tool under Statistics > Quality Tools > Pareto Chart.

   • Ensure no residual settings affect the analysis by pressing the F3 key to reset all prior entries.

   • Select the attribute data from C5: Delivery Days.

   • Key Setting: Activate the option Do Not Combine to display all defined value ranges without grouping smaller categories.

2. Custom Value Ranges on the X-Axis:

   • Verify that the X-axis of the chart reflects the user-defined value ranges:

     • Less than 19 days

     • 19–21 days

     • 22–24 days

     • 25–28 days

     • 29–35 days

     • Over 35 days

3. Analyzing the Pareto Chart:

   • Frequency Distribution:

     • Example insights:

       • 471 orders (47.1%) delivered in 19–21 days.

       • 230 orders (23.0%) delivered in 25–28 days.

     • Cumulative percentage for 19–28 days: 70.1%.

     • 216 orders (21.6%) delivered in 22–24 days, bringing the cumulative percentage to 91.7% for 19–28 days.

   • Identifying Key Ranges:

     • Interpretation: 91.7% of all deliveries occur between 19 and 28 days, highlighting this period as critical for analysis and improvement.

4. Handling Outliers and Missing Values:

   • Analyze remaining data:

     • 72 orders (7.2%) delivered in 29–35 days.

     • 7 orders (0.7%) delivered in less than 19 days.

     • 3 open orders with missing delivery dates.

   • Final Cumulative Insights:

     • 99.6% of deliveries arrive within 35 days.

     • Including open orders, 99.9% could meet this timeline.

5. Takeaways from the Pareto Chart:

   • Majority of deliveries fall within predictable timeframes.

   • Custom value ranges enable targeted analysis of performance trends.

   • Outliers and missing data are minimal but require attention for comprehensive performance improvement.

Outcome:
By the end of this lesson, participants will have the ability to customize Pareto charts with specific value ranges, interpret key data trends, and use cumulative percentages to make informed decisions. These skills are critical for effective performance monitoring and process optimization.

Learning Objectives:
Participants will:

1. Learn how to extract supplier identifiers from order numbers in Minitab.

2. Create a new column for supplier names to enable data segregation.

3. Prepare and analyze data for supplier-specific performance evaluation.

Lesson Content:

1. Objective:

   • Compare delivery performance of Supplier A and Supplier B to identify the more reliable supplier.

2. Preparation:

   • Recognize that the first character in the order number indicates the supplier (A or B).

3. Steps for Data Extraction:

   Step 1: Creating a New Column

   • Add a new column manually and name it Supplier.

   Step 2: Accessing Minitab’s Calculator Function

   • Go to Calculate > Calculator.

   • Reset previous settings by pressing F3 to avoid unintended configurations.

   Step 3: Defining the Storage Location

   • Specify column C6: Supplier as the destination for extraction results.

   Step 4: Using the Left Function

   • From the functions menu, double-click on Left to select the function for extracting text.

   • Input parameters in the formula:

     • Text Placeholder: Specify the source column (C1: Order Number).

     • Number of Characters Placeholder: Input the value 1 to extract only the first character.

   Step 5: Confirm and Review the Results

   • Click OK to apply the formula.

   • Verify that column C6: Supplier now contains either A or B for each order, reflecting the supplier.

Key Points to Note:

• The Left function extracts data based on position within the text.

• Always verify formula placeholders to avoid deleting essential syntax (e.g., brackets or semicolons).

• Resetting settings (F3) ensures no residual configurations interfere with current calculations.

Outcome:
Participants will understand how to extract and segregate supplier data using Minitab. This enables targeted analyses for comparing supplier-specific performance metrics, such as delivery times or reliability.

Learning Objectives:
Participants will:

1. Create and interpret supplier-specific Pareto charts in Minitab.

2. Use comparative tools like pie charts and box-plots to analyze delivery performance.

3. Develop actionable insights from visual data representation.

Lesson Content:

1. Objective:

   • Use Pareto analysis to evaluate and compare the delivery performance of Supplier A and Supplier B.

2. Steps for Pareto Analysis:

   Step 1: Preparing the Data for Analysis

   • Verify that supplier data is correctly structured in column C6: Supplier.

   • Ensure delivery performance data is available in column C5: Delivery Days.

   Step 2: Creating Pareto Charts

   • Click on Statistics > Quality Tools > Pareto Chart.

   • Reset previous entries by pressing F3.

   • Select C5: Delivery Days for attribute data and C6: Supplier for the variable field.

   • Enable One Group Per Graph, Same Ordering of Bars for consistent comparison.

   • Activate the Do Not Combine option to display all categories.

   • Confirm with OK to generate separate Pareto charts for each supplier.

3. Step 3: Interpreting Pareto Charts

   • Observe the left chart for Supplier A and the right chart for Supplier B.

   • Note key differences in delivery performance between the two suppliers.

4. Step 4: Using Pie Charts for Data Distribution

   • Go to Graphs > Pie Chart.

   • Select C6: Supplier as the categorical variable.

   • Enable Frequency and Percent options under Labels > Slice Label.

   • Confirm with OK to visualize the order distribution between suppliers.

5. Step 5: Adding Box-Plots for Performance Variability

   • Click on Graphs > Box-Plot and select One Y, With Groups.

   • Choose C4: Difference as the graphic variable and C6: Supplier as the group variable.

   • Confirm to view box-plots for both suppliers, highlighting delivery time variability and reliability.

Key Observations:

• Supplier A demonstrates significantly lower average delivery times compared to Supplier B.

• Supplier B shows greater variability in delivery performance, indicating lower planning reliability.

• 86% of Supplier A's deliveries occur within 19–21 days, while only 8.2% of Supplier B's deliveries fall within the same range.

Outcome:
Learners will gain practical experience in applying Pareto analysis to compare supplier performance. They will be equipped to derive meaningful insights and provide data-backed recommendations for supplier selection.

Summary of the Key Steps and Learnings:

1. Data Overview and Preparation:

   • Examined the completeness and structure of the dataset using worksheet information.

   • Gained insights into statistical center and scatter parameters through descriptive statistics.

   • Visualized the dataset distribution using a histogram.

2. Creating a Pareto Chart:

   • Learned to generate an initial Pareto chart to analyze overall delivery performance.

   • Defined specific Pareto value ranges to provide detailed insights.

3. Recode Function:

   • Applied the recode function to categorize delivery times into defined ranges.

   • Used recoded data to separate and analyze supplier-specific performance.

4. Supplier Comparison:

   • Generated individual Pareto charts for each supplier.

   • Created pie charts to visualize order quantities for both suppliers.

   • Used box-plots to compare variability and reliability in delivery performance.

5. Findings and Recommendations:

   • Supplier A demonstrated significantly better delivery performance and reliability than Supplier B.

   • Supplier A delivered 86% of orders within 19–21 days, compared to only 8.2% for Supplier B.

   • Supplier B exhibited greater variability in delivery times, making it less reliable.

   • A concrete recommendation was made to prefer Supplier A for future orders.

Outcome:
Participants successfully applied Pareto analysis and related tools to evaluate supplier performance. This training equipped learners to derive actionable insights and provide data-driven recommendations for operational decision-making.

Final Step:
The analysis results were saved under the project name "Pareto Analysis" to ensure data integrity and accessibility.