What is the key difference between the Variable and Attribute Control Chart?

 

The difference between you and God is that You have forgotten that YOU are divine: Unknown

Introduction

There is a difference between a fact and a story. Many times, we entangle ourselves so much into the story that we fail to see the real issue. Like during COVID Pandemic, we are so much enamored by social media that even if we have mild symptoms, we start making many stories around it and feel sicker than the actual problem. We must understand the difference between the fact and the story to enjoy life fully.   

Objective

In the statistical studies, Walter Shewhart and W Edward Deming have done tremendous work to understand the variation in the process and its causes through statistical studies. The understanding of these variations is important to improve quality, increase productivity and reduce cost (QCD).

There are 2 types of control charts (Variable data and Attribute Data) to understand the variation in the process. There are different types of control charts that are plotted based on the type of data and criticality of the problem (mean, range, I chart, MR Chart, p, np, c, u). By understanding these charts and taking suitable actions, the process can be brought under statistical control.

Definitions:

Variable Chart: It explains the process data in terms of its process variation, piece to piece variation, and its process average.  

Attribute Chart: They have discrete values and can be counted for recording and analysis.

Detailed Information

Control charts can be used to monitor or evaluate the process. There are two types of control charts: Variable data and Attribute data.

The process itself will dictate which type of control chart needs to be used. While introducing the control chart, it is important to prioritize the problem area and use it where it is most needed.

Where possible variable control charts are always preferred over attribute control charts as they provide much more information with the same efforts.

Before Control charts are used, several preparatory steps are needed like

  • Establish an environment suitable for action
  • Define the process
  • Define the characteristic
  • Define the measurement system
  • Minimize unnecessary variation
  • Ensure the measurement is capable of detecting special causes
  • Define characteristics for the control chart like customer needs, current/potential problem areas, the correlation between characteristics

How to decide which control chart has to be used?

Variable control chart:

  • I and MR Chart: Sample Size is 1
  • Xbar (mean) and Range Chart: Sample size is more but less than 8
  • Xbar (9mean) and S Chart: Sample Size is more than 8

Attribute control chart:

  • p, np: Number of defective items
  • c, u: Number of defects/unit

Dr. Walter Shewhart developed the first control chart in the 1920s to describe common and special causes for Detection (tolerates waste) and Prevention (avoid waste)

Following are some of the key difference between Variable and Attribute Control Chart:

S.No. Variable Control Chart Attribute Control Chart
1 Measured Data Counted Data
2 Data is continuous like diameter, width, length, etc. Data is discrete like go-no-go, good-not good, etc.
3 X bar and Range Chart, I (Individual) chart, MR (Moving Range) Chart, etc. p, np, c, u Chart
4 Quantitative value (Example: Diameter: 10.15 mm) Qualitative Value (number of defects)
5 More costly Less costly
6 Quick decision with small sample size The decision takes time as the sample size is bigger
7 The time delay between the ‘out of control’ signal to corrective action is shorter The time delay between ‘out of control’ signal to corrective action is longer
8 Improvement can be quantified Improvement can not be quantified
9 Process data in terms of its process variation, piece to piece variation, and its process average  
10 Analyzed in pair in the form of Mean (Process Average) and Range (Process Variation)  

 

Present Challenges:

  1. How often control charts are selected (variable or attribute) based on the requirement and not based on the convenience of the available software!
  2. How often the organization is clear about the difference between p, np, c, u charts?
  3. Why the majority of the organization use only variable control charts and not attribute control charts?

References:

IATF 16949: 2016

SPC Manual (AIAG) 2nd Edition

Industry Experts

 

This is the 108th article of this Quality Management series. Every weekend, you will find useful information that will make your Management System journey Productive. Please share it with your colleagues too.

Your genuine feedback and response are extremely valuable. Please suggest topics for the coming weeks.

Leave a Reply

avatar
  Subscribe  
Notify of