top of page

Six Sigma Methodology at Verso

Updated: May 3

Six Sigma Article 18



Data Collection

In Article 17, we delved into the practical application of Operational Definitions. Now, it's time to explore Data Collection in the Measure Phase in this article. We'll cover the key steps, emphasize their importance, and examine the distinction between Continuous and Discrete Data.

Data Collection

Key Steps:

  1.  Develop a Data Collection Plan

  2.  Validate Measurement System

  3.  Collect Data


Why is this step important?

·       Establishing a data collection plan and validating the measurement system are crucial steps as they delineate a coherent strategy for efficiently gathering reliable data.

·       The data collection plan aids in guaranteeing optimal resource utilization by focusing solely on gathering data essential for project success.

·       Validating the measurement system is imperative as it guarantees that the collected data faithfully reflects the genuine characteristics of your process

Data Collection Plan:


Data Collection Plan

Continuous Vs. Discrete Data:

Continuous Data:

·       Continuous data encompasses information that can be measured along a continuum or scale.

·       It can possess nearly any numeric value and can be meaningfully divided into increasingly finer increments, depending on the precision of the measurement system.

·       Continuous data is infinitely divisible.

An example of continuous data is the height of students in a classroom. Heights can be measured along a scale and can take on any numeric value within a certain range. For instance, a student could be 150.5 centimeters tall, and another could be 155.2 centimeters tall. This data is continuous because it can be divided into finer and finer increments, depending on the precision of the measurement device.

Discrete / Attribute Data:

·       Discrete data comprises information that can be categorized into distinct classifications.

·       It relies on counts, and only a finite number of values is possible.

·       The values cannot be meaningfully subdivided.

An example of discrete/attribute data is the number of red apples in a basket. This data is discrete because it consists of distinct categories (red apples) and is based on counts. Each apple can be counted, and the number of red apples in the basket can only be whole numbers (e.g., 0, 1, 2, 3, etc.). The values cannot be further subdivided into smaller increments.

Now that we've delved into practical Data Collection in the Measure Phase, I encourage you to continue our journey with us. Join us in the next article where our focus will be on Sampling in the Measure Phase.

We invite you to engage with us by liking and sharing your thoughts in the comments section. Every comment is valuable to us, and we commit to responding as necessary.


bottom of page