WinSPC.comWinSPC.com
Global leaders in real-time SPC software solutions
  • Software
    • WinSPC
      • WinSPC
      • Capture Data
      • Monitoring & Alarming
      • Analysis & Reporting
      • Supply Chain Quality
      • Industries Using WinSPC
      • How to Buy WinSPC
      • WinSPC System Requirements
      • Download WinSPC Trial
    • WinSPC Cloud
      • WinSPC Cloud
      • Retain Local System Flexibility
      • Gain These Cloud Benefits
      • Go Beyond Traditional SaaS
      • Data Protection & Security
    • WinSPC Envision
      • WinSPC Envision
      • Visibility
      • Mobility
      • Interactivity
      • How to Buy WinSPC Envision
      • Envision System Requirements
  • Services
    • Implementation Assistance
    • System Integration
    • Customer-Specific Solutions
    • Software Validation
    • SPC & Software Training
      • SPC & Software Courses
      • Course Delivery Options
      • Directions & Lodging
  • Resources
    • Contact Support
    • Activate WinSPC Licenses
    • Customer Downloads (PRIV)
    • WinSPC Knowledgebase
    • Ask The Expert (BLOG)
    • DataNet News (BLOG)
    • What is SPC?
      • What is SPC
      • SPC Tools
      • SPC FAQ
      • SPC Glossary
Home » » Ask The Expert » How do I test my data normality?

How do I test my data normality?

Before applying statistical methods that assume normality, it is necessary to perform a normality test on the data.


Figure 1: Histogram depicting a normal (bell-shaped) distribution in WinSPC

For example, all of the following statistical tests, statistics, or methods assume that data is normally distributed:

• Hypothesis tests such as t tests, Chi-Square tests, F tests
• Analysis of Variance (ANOVA)
• Least Squares Regression
• Control Charts of Individuals with 3-sigma limits
• Common formulas for process capability indices such as Cp and Cpk

Before applying statistical methods that assume normality, it is necessary to perform a normality test on the data (with some of the above methods we check residuals for normality). We hypothesize that our data follows a normal distribution, and only reject this hypothesis if we have strong evidence to the contrary.

While it may be tempting to judge the normality of the data by simply creating a histogram of the data, this is not an objective method to test for normality – especially with sample sizes that are not very large. With small sample sizes, discerning the shape of the histogram is difficult. Furthermore, the shape of the histogram can change significantly by simply changing the interval width of the histogram bars.

Normal probability plotting may be used to objectively assess whether data comes from a normal distribution, even with small sample sizes. On a normal probability plot, data that follows a normal distribution will appear linear (a straight line). For example, a random sample of 30 data points from a normal distribution results in the first normal probability plot (Figure 2). Here, the data points fall close to the straight line. The second normal probability plot (Figure 3) illustrates data that does not come from a normal distribution.


Figure 2: Normal probability plot illustrating normal distribution


Figure 3: Normal probability plot illustrating non-normal distribution

Many methods are available to handle non-normal data and these should be utilized when necessary. Applying methods which assume the normal distribution when this assumption is not valid often results in incorrect conclusions.

 

Steven Wachs, Principal Statistician
Integral Concepts, Inc.

Integral Concepts provides consulting services and training in the application of quantitative methods to understand, predict, and optimize product designs, manufacturing operations, and product reliability. www.integral-concepts.com


Download the white paper on how to jump-start a “mini” Six Sigma Quality program on a budget

October 8, 2018 Administrator WinSPC

Related Posts

  • What is the Difference Between Specification Limits and Control Limits? | Ask the Expert
    What is the Difference Between Specification Limits and Control Limits? | Ask the ExpertJanuary 24, 2019
  • Quality Automation: Benefits, Pitfalls Part 1 of 2 | Quality Insight
    Quality Automation: Benefits, Pitfalls Part 1 of 2 | Quality InsightJanuary 2, 2019
  • Fluid Tank Supplier Delivers Critical Temp Change Alerts to Line Operators | WinSPC News
    Fluid Tank Supplier Delivers Critical Temp Change Alerts to Line Operators | WinSPC NewsDecember 13, 2018

Popular Posts

  • Nestle Purina PetCare Delivers Full Value with Help from WinSPC | WinSPC News
    Nestle Purina PetCare Delivers Full Value with Help from WinSPC | WinSPC NewsJuly 9, 1998
  • Consilium® Selects DataNet’s WinSPC® C/S Statistical Process Control Software for Use With Its FAB300™ Manufacturing Automation Software System | WinSPC News
    Consilium® Selects DataNet’s WinSPC® C/S Statistical Process Control Software for Use With Its FAB300™ Manufacturing Automation Software System | WinSPC NewsJuly 17, 1998
  • DataNet Quality Systems Introduces WinSPC v1.2 at ISA Expo98 | WinSPC News
    DataNet Quality Systems Introduces WinSPC v1.2 at ISA Expo98 | WinSPC NewsOctober 19, 1998

Leave a Reply Cancel reply

You must be logged in to post a comment

Search WinSPC.com

Evaluate WinSPC

  • View Video Tour
  • Talk to an Expert
  • Download Trial

Follow Us On

Follow Us On FacebookFollow Us On LinkedInFollow Us On TwitterFollow Us On YouTube

Find it on WinSPC.com

Follow Us on

Follow Us on FacebookFollow Us on LinkedInFollow Us on TwitterFollow Us on YouTube

Contact Us

866-4WINSPC

248-357-2200

248-357-4933

info*dqs.com

Southfield

Michigan USA

my_location Find Us - Map

Helpful Links

  • Knowledgebase Site
  • Ask The Expert – BLOG
  • What is SPC?
  • SPC Tools
  • SPC FAQ
  • SPC Glossary
  • Docs & Downloads

About Us

  • About DataNet
  • DataNet News
  • Job Postings
  • Find A Reseller
  • Contact Support
  • Industries Using WinSPC
  • Customers Using WinSPC
DataNet Quality Systems - 29200 Northwestern Hwy - Southfield, MI 48034 -- Copyright © 1995-2019 -- All Rights Reserved