Accendo Reliability

Your Reliability Engineering Professional Development Site

  • Home
  • About
    • Contributors
  • Reliability.fm
    • Speaking Of Reliability
    • Rooted in Reliability: The Plant Performance Podcast
    • Quality during Design
    • Way of the Quality Warrior
    • Critical Talks
    • Dare to Know
    • Maintenance Disrupted
    • Metal Conversations
    • The Leadership Connection
    • Practical Reliability Podcast
    • Reliability Matters
    • Reliability it Matters
    • Maintenance Mavericks Podcast
    • Women in Maintenance
    • Accendo Reliability Webinar Series
  • Articles
    • CRE Preparation Notes
    • on Leadership & Career
      • Advanced Engineering Culture
      • Engineering Leadership
      • Managing in the 2000s
      • Product Development and Process Improvement
    • on Maintenance Reliability
      • Aasan Asset Management
      • AI & Predictive Maintenance
      • Asset Management in the Mining Industry
      • CMMS and Reliability
      • Conscious Asset
      • EAM & CMMS
      • Everyday RCM
      • History of Maintenance Management
      • Life Cycle Asset Management
      • Maintenance and Reliability
      • Maintenance Management
      • Plant Maintenance
      • Process Plant Reliability Engineering
      • ReliabilityXperience
      • RCM Blitz®
      • Rob’s Reliability Project
      • The Intelligent Transformer Blog
      • The People Side of Maintenance
      • The Reliability Mindset
    • on Product Reliability
      • Accelerated Reliability
      • Achieving the Benefits of Reliability
      • Apex Ridge
      • Metals Engineering and Product Reliability
      • Musings on Reliability and Maintenance Topics
      • Product Validation
      • Reliability Engineering Insights
      • Reliability in Emerging Technology
    • on Risk & Safety
      • CERM® Risk Insights
      • Equipment Risk and Reliability in Downhole Applications
      • Operational Risk Process Safety
    • on Systems Thinking
      • Communicating with FINESSE
      • The RCA
    • on Tools & Techniques
      • Big Data & Analytics
      • Experimental Design for NPD
      • Innovative Thinking in Reliability and Durability
      • Inside and Beyond HALT
      • Inside FMEA
      • Integral Concepts
      • Learning from Failures
      • Progress in Field Reliability?
      • R for Engineering
      • Reliability Engineering Using Python
      • Reliability Reflections
      • Testing 1 2 3
      • The Manufacturing Academy
  • eBooks
  • Resources
    • Accendo Authors
    • FMEA Resources
    • Feed Forward Publications
    • Openings
    • Books
    • Webinars
    • Journals
    • Higher Education
    • Podcasts
  • Courses
    • 14 Ways to Acquire Reliability Engineering Knowledge
    • Reliability Analysis Methods online course
    • Measurement System Assessment
    • SPC-Process Capability Course
    • Design of Experiments
    • Foundations of RCM online course
    • Quality during Design Journey
    • Reliability Engineering Statistics
    • Quality Engineering Statistics
    • An Introduction to Reliability Engineering
    • Reliability Engineering for Heavy Industry
    • An Introduction to Quality Engineering
    • Process Capability Analysis course
    • Root Cause Analysis and the 8D Corrective Action Process course
    • Return on Investment online course
    • CRE Preparation Online Course
    • Quondam Courses
  • Webinars
    • Upcoming Live Events
  • Calendar
    • Call for Papers Listing
    • Upcoming Webinars
    • Webinar Calendar
  • Login
    • Member Home

by Dianna Deeney 2 Comments

QDD 107 QDD Redux Ep. 3: When it’s Not Normal: How to Choose from a Library of Distributions

QDD Redux Ep. 3: When it’s Not Normal: How to Choose from a Library of Distributions

When trying to fit a probability distribution to quantitative results, sometimes the normal probability doesn’t fit. Minitab has a wealth of distributions to pick from. Do you just pick whichever one Minitab tells you fits the best? Maybe not. Just because the distribution fits your data doesn’t mean it’s a good one to use. We review my top 3 distributions for product testing and some other ones that come up but may not be appropriate to use.

We’ll also share what you need to think about when picking a distribution:

  1. think about your purpose of test
  2. consider your failure mode and how you’re expecting your product to perform – does the typical use case of a distribution fit?
  3. when you have options, the simpler the distribution the  better (i.e. choose a 2-parameter over a 3-parameter)

 

 

View the Episode Transcript


If not normal, try lognormal and a 2-parameter Weibull distribution first. If your analysis is really complicated and the stakes are high, ask a reliability engineer for some help fitting an accurate model.


Minitab has a help guide on distribution fit for reliability analysis. It lists the available distributions in Minitab, and you can read more about them. Bookmark the page as a starting point to help you. https://support.minitab.com/en-us/minitab/19/help-and-how-to/statistical-modeling/reliability/supporting-topics/distribution-models/distribution-fit/

Reliability engineers also use Gamma, Beta, and Log-Logistics distributions. Here is a link that explains them if you really want to know about these distributions.  https://www.weibull.com/hotwire/issue56/relbasics56.htm

 


Episode Transcript

We’re doing verification testing and getting quantitative results, or data and numbers. We’re trying to plot a data set to fit a probability distribution, and it doesn’t quite fit a normal distribution. You know, that’s the one that looks like a bell curve and the one everyone really wants to have because it’s the gateway to lots of other statistical tools, but it doesn’t fit it. Then we run the distribution fit function in Minitab and get this weird distribution we’ve never heard of. But it’s got the right fit. Do we use that one? Maybe not. Let’s review after this brief introduction.

Hello and welcome to Quality during Design, the place to use quality thinking to create products, others love for less. My name is Dianna. I’m a senior level quality professional and engineer with over 20 years of experience in manufacturing and design. Listen in and then join the conversation at qualityduringdesign.com.

In this episode we’re talking about choices of distributions of a data set. I’m glad to be able to talk with you about this today because it’s something that comes up quite often.

First, the basic takeaway is going to be just because the distribution fits doesn’t mean it’s a good one to use. Our discussion today is going to be high concept. We’re not going to get into nitty gritty details about math and statistical theory. Doing that in a podcast isn’t something I want to do, and not likely something you want to listen to either.

Secondly, let’s get on the same page with some terminology. Probability density function is a plot of a function over a random variable. If we look at a probability density function of a normal distribution, it’s going to look like it’s famous bell curve.

Third thing I’m going to talk about is continuous data sets. Continuous data sets are those that take on fractions of a whole. It’s not discrete data. In other words, it’s not data that’s countable. Time, force, pressure: these are examples of continuous data.

Back to our problem at hand: fitting a distribution. Now, Minitab has lots of probability distributions to choose from. So it’s built to fit the need of many different industries. Its options are to fit everyone. Some of those distributions have applications that just don’t match up with product performance testing. So, in other words, just because you found a probability distribution that Minitab says fits our data best overall others we need to follow through ourselves on a couple of things before we use that distribution to make decisions.

Now distributions, when picking there’s some things that we need to consider.

First, what is our purpose of test? What are we trying to do with our data? For example, are we trying to show that our device is stronger than a minimum requirement? Is the minimum requirement of 5N and all of our data is over 5000 N? If we don’t need to calculate a performance with a certain reliability and confidence level, then let’s move on. The product is performing way above what we needed to at any probability distribution is going to be far away from our requirement. It doesn’t make practical sense to spend a lot of time on it. However, if we decided that we needed an accurate model then we need to take care on which distribution we choose. Maybe we need an accurate model because our data set doesn’t have a huge factor of safety. Maybe we need an accurate model because we want to report life data or we’re using values to make a decision about different design features.

When choosing a distribution, the second thing to consider is what type of failures are we testing? What is failing and how is it failing? How are we expecting it to perform? The importance of failure modes comes into effect here.

Let’s talk about some common distributions that are not normal. We’re going to review some use cases, their probability density functions (or what they look like on a graph), and generally what we use them for.

First is the exponential distribution. Let’s say that our test is of a product that would likely last forever if it weren’t for an external force. Like electronic parts that fail because of surges or time until a light bulb burns out. An exponential distribution is a model of something that has constant failure rate. Its unit under test doesn’t degrade or wear out overtime. Its probability density function looks like a slide starting from near zero and trailing off with a long right tail. So, if our test is of cycles to failure or wear out, then we don’t choose this one. We may be able to manipulate it to fit, but it wouldn’t be appropriate to do so.

If our failure mode is wear-out, I have two top contenders that I work with after the normal probability: the two parameter Weibull and the Lognormal.

A Weibull distribution is loved by many reliability engineers for its capability to be manipulated and yet still be accurate. An example of this love is a well-known reliability website, called weibull.com. I also had a professor in a college course that loved Weibull. The probability density function of a Weibull distribution can mimic other distributions. It’s a shapeshifter. The three parameter Weibull has a shape, scale, and threshold parameter which gives it its copycat-type behavior. It can model failure rates that are increasing, decreasing, or constant. So, the Weibull is a good model to try if all others are just not fitting. I always pick a 2-parameter Weibull in my top three distributions to test against. For some reliability folks, is their go to distribution.

A Lognormal distribution is used if a failure mode is a wear-out function, like degradation or corrosion. Its probability density function looks like a normal distribution but is always positive or to the right of the zero and has a long extended right tail. What’s special about the Lognormal distribution is if our data fits it, then we can transform our data to make it follow a normal distribution. That then allows us to do all those fun statistical tests that need the assumption of a normal distribution, like confidence intervals and hypothesis tests.

Now, Extreme Value, either smallest or largest, seems to come up quite a lot. In product design verification, I haven’t really found a use case where it fits well. The use case for the extreme value distributions is for extreme phenomena. Meteorologists, safety engineers working in a dam, and insurance companies, finance, economics, and material sciences are more likely to use it than engineers for product design performance testing. The probability density functions of these distributions also have a bell-shaped curve but with extended tails: the smallest extreme value has a long tail to the left and the largest has a long tail to the right. For product design testing, there are other distributions that fit better than an extreme value. Use Weibull instead. These are used for reliability engineering, so if you really think your case fits then get some help from your favorite reliability engineer. Reliability engineers also use gamma, beta, log logistics; and I’ll include a link in the podcast blog if you really want to know about these distributions.

So what do we do with what we’ve been talking about today? Before settling on a probability distribution, we understand the underlying type of failure it’s modeling and we consider the typical use cases of that distribution. Does what we’re testing makes sense to what that model is typically used for? Does the behavior of our design failure match the idea behind the model? And we pick the simplest model that we can, which means choosing a 2-parameter model over 3-parameter model.

Now some insight to action: If our data is not normal, try lognormal and two parameter Weibull distributions first. If your analysis is really complicated and the stakes are high, ask a reliability engineer for some help fitting an accurate model. On this podcast blog, I will post a link to the Minitab Help guides on distribution fit for reliability analysis. It lists the available distributions in Minitab and you can read more about them. Bookmark the page as a starting point to help.

Please visit this podcast blog and others at qualityduringdesign.com. Subscribe to the weekly newsletter to keep in touch. If you like this podcast or have a suggestion for an upcoming episode, let me know. You can find me at qualityduringdesign.com, on Linked-In, or you can leave me a voicemail at 484-341-0238. This has been a production of Deeney Enterprises. Thanks for listening.

Filed Under: Quality during Design

About Dianna Deeney

Dianna is a senior-level Quality Professional and an experienced engineer. She has worked over 20 years in product manufacturing and design and is active in learning about the latest techniques in business.

Dianna promotes strategic use of quality tools and techniques throughout the design process.

Comments

  1. Carl DuPoldt says

    May 7, 2023 at 2:02 PM

    not normal distributions – https://www.statisticshowto.com/probability-and-statistics/non-normal-distributions/
    —————-
    tips and tricks for analyzing not normal distributions – https://www.qualitymag.com/ext/resources/files/white_papers/minitab/Tips-and-Tricks-for-Analyzing-Non-Normal-Data-002.pdf
    —————-
    dealing with not normal distributions – https://onlinelibrary.wiley.com/doi/pdf/10.1016/j.pmrj.2012.10.013
    ————–

    Reply
    • Dianna Deeney says

      June 6, 2023 at 11:40 AM

      Thanks for sharing your go-to resources!

      Reply

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Quality during Design podcast logo

Tips for using quality tools and methods to help you design products others love, for less.


by Dianna Deeney
Quality during Design,
Hosted on Buzzsprout.com
Subscribe and enjoy every episode
Google
Apple
Spotify

Recent Episodes

QDD 128 Leveraging Proven Frameworks or Concept Development

QDD 127 Understanding Cross-Functional Collaboration

QDD 126 Exploring the Problem Space: A Key Principle for Robust Product Design and Project Success

QDD 125 Exploring Product Development and AI Through Literature

QDD 124 Design for User Tasks using an Urgent/Important Matrix

QDD 123 Information Development in Design, with Scott Abel – Part 2 (A Chat with Cross-Functional Experts)

QDD 122 Information Development in Design, with Scott Abel – Part 1 (A Chat with Cross-Functional Experts)

QDD 121 Crafting Effective Technical Documents for the Engineering Field

QDD 120 How to use FMEA for Complaint Investigation

QDD 119 Results-Driven Decisions, Faster: Accelerated Stress Testing as a Reliability Life Test

QDD 118 Journey from Production to Consumption: Enhancing Product Reliability

QDD 117 QDD Redux: Choose Reliability Goals for Modules

QDD 116 Reliability Engineering during Design, with Adam Bahret (A Chat with Cross-Functional Experts)

QDD 115 QDD Redux: 5 Options to Manage Risks during Product Engineering

QDD 114 The Instant Glory of Projects

QDD 113 What to do about Virtual Meetings

QDD 112 QDD Redux: How to self-advocate for more customer face time (and why it’s important)

QDD 111 Engineering with Receptivity, with Sol Rosenbaum (A Chat with Cross-Functional Experts)

QDD 110 Don’t Wish for Cross-Functional Buy-in on Product Designs – Plan to Get It!

QDD 109 Before You Start Engineering Solutions, Do This

QDD 108 QDD Redux Ep. 4: Statistical vs. Practical Significance

QDD 107 QDD Redux Ep. 3: When it’s Not Normal: How to Choose from a Library of Distributions

QDD 106 QDD Redux Ep. 2: How to Handle Competing Failure Modes

QDD 105 QDD Redux Ep. 1: How Many Do We Need to Test?

QDD 104 The Fundamental Thing to Know from Statistics for Design Engineering

QDD 103 What to do for Effective and Efficient Working Meetings

QDD 102 Get Design Inputs with Flowcharts

QDD 101 Quality Tools are Legos of Development (and Their 7 Uses)

QDD 100 Lessons Learned from Coffee Pod Stories

QDD 099 Crucial Conversations in Engineering, with Shere Tuckey (A Chat with Cross-Functional Experts)

QDD 098 Challenges Getting Team Input in Concept Development

QDD 097 Brainstorming within Design Sprints

QDD 096 After the ‘Storm: Compare and Prioritize Ideas

QDD 095 After the ‘Storm: Pareto Voting and Screening Methods

QDD 094 After the ‘Storm: Group and Explore Ideas

QDD 093 Product Design with Brainstorming, with Emily Haidemenos (A Chat with Cross Functional Experts)

QDD 092 Ways to Gather Ideas with a Team

QDD 091 The Spirits of Technical Writing Past, Present, and Future

QDD 090 The Gifts Others Bring

QDD 089 Next Steps after Surprising Test Results

QDD 088 Choose Reliability Goals for Modules

QDD 087 Start a System Architecture Diagram Early

QDD 086 Why Yield Quality in the Front-End of Product Development

QDD 085 Book Cast

QDD 084 Engineering in the Color Economy

QDD 083 Getting to Great Designs

QDD 082 Get Clarity on Goals with a Continuum

QDD 081 Variable Relationships: Correlation and Causation

QDD 080 Use Meetings to Add Productivity

QDD 079 Ways to Partner with Test Engineers

QDD 078 What do We do with FMEA Early in Design Concept?

QDD 077 A Severity Scale based on Quality Dimensions

QDD 076 Use Force Field Analysis to Understand Nuances

QDD 075 Getting Use Information without a Prototype

QDD 074 Finite Element Analysis (FEA) Supplements Test

QDD 073 2 Lessons about Remote Work for Design Engineers

QDD 072 Always Plot the Data

QDD 071 Supplier Control Plans and Design Specs

QDD 070 Use FMEA to Design for In-Process Testing

QDD 069 Use FMEA to Choose Critical Design Features

QDD 068 Get Unstuck: Expand and Contract Our Problem

QDD 067 Get Unstuck: Reframe our Problem

QDD 066 5 Options to Manage Risks during Product Engineering

QDD 065 Prioritizing Technical Requirements with a House of Quality

QDD 064 Gemba for Product Design Engineering

QDD 063 Product Design from a Data Professional Viewpoint, with Gabor Szabo (A Chat with Cross Functional Experts)

QDD 062 How Does Reliability Engineering Affect (Not Just Assess) Design?

QDD 061 How to use FMEA for Complaint Investigation

QDD 060 3 Tips for Planning Design Reviews

QDD 059 Product Design from a Marketing Viewpoint, with Laura Krick (A Chat with Cross Functional Experts)

QDD 058 UFMEA vs. DFMEA

QDD 057 Design Input & Specs vs. Test & Measure Capability

QDD 056 ALT vs. HALT

QDD 055 Quality as a Strategic Asset vs. Quality as a Control

QDD 054 Design Specs vs. Process Control, Capability, and SPC

QDD 053 Internal Customers vs. External Customers

QDD 052 Discrete Data vs. Continuous Data

QDD 051 Prevention Controls vs. Detection Controls

QDD 050 Try this Method to Help with Complex Decisions (DMRCS)

QDD 049 Overlapping Ideas: Quality, Reliability, and Safety

QDD 048 Using SIPOC to Get Started

QDD 047 Risk Barriers as Swiss Cheese?

QDD 046 Environmental Stress Testing for Robust Designs

QDD 045 Choosing a Confidence Level for Test using FMEA

QDD 044 Getting Started with FMEA – It All Begins with a Plan

QDD 043 How can 8D help Solve my Recurring Problem?

QDD 042 Mistake-Proofing – The Poka-Yoke of Usability

QDD 041 Getting Comfortable with using Reliability Results

QDD 040 How to Self-Advocate for More Customer Face Time (and why it’s important)

QDD 039 Choosing Quality Tools (Mind Map vs. Flowchart vs. Spaghetti Diagram)

QDD 038 The DFE Part of DFX (Design For Environment and eXcellence)

QDD 037 Results-Driven Decisions, Faster: Accelerated Stress Testing as a Reliability Life Test

QDD 036 When to use DOE (Design of Experiments)?

QDD 035 Design for User Tasks using an Urgent/Important Matrix

QDD 034 Statistical vs. Practical Significance

QDD 033 How Many Do We Need To Test?

QDD 032 Life Cycle Costing for Product Design Choices

QDD 031 5 Aspects of Good Reliability Goals and Requirements

QDD 030 Using Failure Rate Functions to Drive Early Design Decisions

QDD 029 Types of Design Analyses possible with User Process Flowcharts

QDD 028 Design Tolerances Based on Economics (Using the Taguchi Loss Function)

QDD 027 How Many Controls do we Need to Reduce Risk?

QDD 026 Solving Symptoms Instead of Causes?

QDD 025 Do you have SMART ACORN objectives?

QDD 024 Why Look to Standards

QDD 023 Getting the Voice of the Customer

QDD 022 The Way We Test Matters

QDD 021 Designing Specs for QA

QDD 020 Every Failure is a Gift

QDD 019 Understanding the Purposes behind Kaizen

QDD 018 Fishbone Diagram: A Supertool to Understand Problems, Potential Solutions, and Goals

QDD 017 What is ‘Production Equivalent’ and Why Does it Matter?

QDD 016 About Visual Quality Standards

QDD 015 Using the Pareto Principle and Avoiding Common Pitfalls

QDD 014 The Who’s Who of your Quality Team

QDD 013 When it’s Not Normal: How to Choose from a Library of Distributions

QDD 012 What are TQM, QFD, Six Sigma, and Lean?

QDD 011 The Designer’s Important Influence on Monitoring After Launch

QDD 010 How to Handle Competing Failure Modes

QDD 009 About Using Slide Decks for Technical Design Reviews

QDD 008 Remaking Risk-Based Decisions: Allowing Ourselves to Change our Minds.

QDD 007 Need to innovate? Stop brainstorming and try a systematic approach.

QDD 006 HALT! Watch out for that weakest link

QDD 005 The Designer’s Risk Analysis affects Business, Projects, and Suppliers

QDD 004 A big failure and too many causes? Try this analysis.

QDD 003 Why Your Design Inputs Need to Include Quality & Reliability

QDD 002 My product works. Why don’t they want it?

QDD 001 How to Choose the Right Improvement Model

Join Accendo

Receive information and updates about articles and many other resources offered by Accendo Reliability by becoming a member.

It’s free and only takes a minute.

Join Today

© 2025 FMS Reliability · Privacy Policy · Terms of Service · Cookies Policy