• Skip to secondary menu
  • Skip to main content
  • Skip to primary sidebar
  • My Store
  • Glossary
  • Home
  • About Me
  • Contact Me

Statistics By Jim

Making statistics intuitive

  • Graphs
  • Basics
  • Hypothesis Testing
  • Regression
  • ANOVA
  • Probability
  • Time Series
  • Fun

Weibull Distribution: Uses, Parameters & Examples

By Jim Frost 6 Comments

What is a Weibull Distribution?

The Weibull distribution is a continuous probability distribution that can fit an extensive range of distribution shapes. Like the normal distribution, the Weibull distribution describes the probabilities associated with continuous data. However, unlike the normal distribution, it can also model skewed data. In fact, its extreme flexibility allows it to model both left- and right-skewed data.

Weibull probability distribution plot.This distribution is an unusually versatile probability density function because it can fit a variety of shapes. It can even approximate the normal distribution and other distributions. Because of its flexibility, analysts use it in a broad range of settings, such as quality control, capability analysis, medical studies, and engineering. It’s frequently used in life data, reliability analysis, and warranty analysis to assess time to failure for systems and parts.

The distribution is named after Swedish mathematician Waloddi Weibull, who presented it to the American Society of Mechanical Engineers (ASME) in 1951. However, Weibull didn’t discover this distribution. Indeed, other mathematicians had been using this probability distribution for decades. One early use for it was modeling particle sizes in 1933.

There are two versions of this distribution. The three-parameter Weibull distribution, unsurprisingly, has three parameters, shape, scale, and threshold. When analysts set the threshold parameter to zero, it is known as the two-parameter Weibull distribution.

Analysts use the Weibull distribution frequently because it is so adaptable to varying conditions. The nature of the distribution changes significantly based on the values of the parameters. In fact, with certain parameter values, the Weibull distribution is equivalent to other probability distributions. Let’s investigate how changing the parameters affects it!

Related posts: Understanding Probability Distributions and Skewed Distributions

Weibull Threshold Parameter (γ)

The threshold parameter defines the lowest possible value in a Weibull distribution. Some analysts refer to this parameter as the location. All values must be greater than the threshold. Consequently, negative threshold values let the distribution handle both negative and positive values. Zero allows it to contain only positive values. A two-parameter Weibull distribution simply has the threshold set to zero. Statisticians denote the threshold parameter with γ.

When you hold the shape and scale parameters constant, the threshold shifts the distribution left and right. In the probability distribution plot below, I show the threshold’s effect in action!

Graph the displays how the Weibull threshold parameter affects the distribution.

Weibull Shape Parameter (β, k)

Unsurprisingly, the shape parameter describes the shape of your data’s distribution. Statisticians also refer to it as the Weibull slope because its value equals the slope of the line on a probability plot. Statisticians denote the shape parameter using either beta (β) or k.

Keep in mind the following four key ranges of shape values for the Weibull distribution. In these probability distribution plots, I hold the scale and threshold parameters constant to highlight the impact of changing the shape.

Shape < 1: Steadily decreasing values

Graph of Weibull distribution with a shape parameter of less than 1.

When the shape parameter equals 1, the Weibull distribution is equivalent to a two-parameter exponential distribution.

Related post: Using the Exponential Distribution

Shape between 1 and 2.6: Right-skewed

Weibull probability distribution plot.

A Weibull distribution with a shape value of 2 is a Rayleigh distribution, which is equivalent to a Chi-square distribution with two degrees of freedom.

Shape near 3: Approximates a normal distribution.

Weibull distribution with a shape parameter of 3.

Related post: Normal Distribution

Shape > 3.7: Left-skewed

Probability distribution plot of a Weibull distribution with a shape of 5.

Weibull Shapes and Failure Rates

Additionally, if you’re studying failure rates, shape values provide critical information about how the failure rate changes over time. When the shape is:

  • < 1, the failure rate decreases over time (e.g., infant mortality failures).
  • = 1, the failure rate is constant over time.
  • > 1, the failure rate increases over time (e.g., wear-out failures).

Weibull Scale Parameter (η, λ)

The scale parameter represents the variability present in the distribution. Changing the scale parameter affects how far the probability distribution stretches out. As you increase the scale, the distribution stretches further right, and the height decreases. Decreasing the scale shrinks the distribution to the left and increases its peak, as shown below. Statisticians denote the scale parameter using either eta (η) or lambda (λ).

Graph that shows how changing the Weibull scale parameter affects the distribution.

The value of the scale parameter equals the 63.2 percentile in the distribution. 63.2% of the values in the distribution are less than the scale value.

Related posts: Measures of Variability and Percentiles: Interpretations and Calculations

Even though the Weibull distribution fits many shapes, it’s not always the best choice. Learn how to identify the probability distribution that best fits your data.

Share this:

  • Tweet

Related

Filed Under: Probability Tagged With: conceptual, distributions, graphs

Reader Interactions

Comments

  1. neaw says

    August 7, 2022 at 7:14 pm

    Thank you so much! Many of your articles help me a lot in my PhD dissertation

    Reply
  2. Gemechu Asfaw says

    March 8, 2022 at 12:34 pm

    Can we use at the same time Weibull, exponential, log-logistic and Gamma distributions at the same time in survival analysis

    Reply
  3. Gemechu Asfaw says

    March 8, 2022 at 11:14 am

    HI Dr. Jim I read on Weibull distribution and its application. But still now it is not clear for me. What is its special case from exponential and log-logistic in survival method

    Reply
  4. T Mallikarjunappa says

    August 13, 2021 at 2:47 am

    Dear Dr Jim

    I am happy to receive your updates on Weibull distribution. I am aware of this distribution but I had not used it. Now that you have kindled interest in this distribution, I would like to read this and check its applications. We normally tend to assume normal distribution and proceed. Your brief on Weibull application to skewed data is a good indicator for me. Let me read and see how best I can use this. Thank you for introducing me to this.

    Regards
    T Mallikarjunappa
    Central University of Kerala, India

    Reply
  5. JOAO JOSE DOS SANTOS says

    August 11, 2021 at 10:54 am

    Olá Professor! Como sempre suas aulas são bastantes esclarecedoras. A cada aula eu amplio ainda mais os meus curtos conhecimentos em Estatística. Parabéns! Um abraço do brasileiro do Estado de Pernambuco.

    Hello teacher! As always, your classes are very enlightening. With each class I expand even more my short knowledge in Statistics. Congratulations! A hug from the Brazilian from the State of Pernambuco.

    Reply
    • Jim Frost says

      August 11, 2021 at 5:48 pm

      Olá Joao! Your kind comments make my day! I’m so happy to hear that my website has been helpful and that I’ve been a part of your statistical journey!

      Reply

Comments and Questions Cancel reply

Primary Sidebar

Meet Jim

I’ll help you intuitively understand statistics by focusing on concepts and using plain English so you can concentrate on understanding your results.

Read More...

Buy My Introduction to Statistics Book!

Cover of my Introduction to Statistics: An Intuitive Guide ebook.

Buy My Hypothesis Testing Book!

Cover image of my Hypothesis Testing: An Intuitive Guide ebook.

Buy My Regression Book!

Cover for my ebook, Regression Analysis: An Intuitive Guide for Using and Interpreting Linear Models.

Subscribe by Email

Enter your email address to receive notifications of new posts by email.

    I won't send you spam. Unsubscribe at any time.

    Follow Me

    • FacebookFacebook
    • RSS FeedRSS Feed
    • TwitterTwitter

    Top Posts

    • How to Interpret P-values and Coefficients in Regression Analysis
    • How To Interpret R-squared in Regression Analysis
    • Z-table
    • How to do t-Tests in Excel
    • Multicollinearity in Regression Analysis: Problems, Detection, and Solutions
    • How to Find the P value: Process and Calculations
    • Mean, Median, and Mode: Measures of Central Tendency
    • How to Interpret the F-test of Overall Significance in Regression Analysis
    • Understanding Interaction Effects in Statistics
    • One-Tailed and Two-Tailed Hypothesis Tests Explained

    Recent Posts

    • Probability Mass Function: Definition, Uses & Example
    • Using Scientific Notation
    • Selection Bias: Definition & Examples
    • ANCOVA: Uses, Assumptions & Example
    • Fibonacci Sequence: Formula & Uses
    • Undercoverage Bias: Definition & Examples

    Recent Comments

    • Morris on Validity in Research and Psychology: Types & Examples
    • Jim Frost on What are Robust Statistics?
    • Allan Fraser on What are Robust Statistics?
    • Steve on Survivorship Bias: Definition, Examples & Avoiding
    • Jim Frost on Using Post Hoc Tests with ANOVA

    Copyright © 2023 · Jim Frost · Privacy Policy