Is a percent value considered attribute/discrete?
Six Sigma – iSixSigma › Forums › Old Forums › General › Is a percent value considered attribute/discrete?
 This topic has 3 replies, 3 voices, and was last updated 14 years, 10 months ago by Adrian P. Smith.

AuthorPosts

June 14, 2007 at 7:41 pm #47271
Per the posted article on Discrete Data, “Discrete data is information that can be categorized into a classification. Discrete data is based on counts. Only a finite number of values is possible, and the values cannot be subdivided meaningfully. For example, the number of parts damaged in shipment”.
Is a percent value considered attribute/discrete? It meets the category of finite number of values (i.e. ranges only from 0% to 100%) but it can be subdivided meaningfully (i.e. 50.123%).0June 14, 2007 at 7:59 pm #157447Discrete Data cannot be associated with a continuum of values but rather assume specific values along the number line, with gaps between them. The most common form of discrete data is a count of some observable occurrence. i.e. count data include the number of blemishs on an automobile surface, or the monthly number of dissatisfied customers, or the number of defective units in a batch. Count data can be expressed in terms o whole numbers or percentages.
Short answer, Yes
Chad Taylor0June 28, 2007 at 9:55 pm #158042Thanks for your response. Does it depend on how the percentage was calculated? For example, if we have continous data for both numerator and denominator, does it automatically make the percent value attribute or does it remain continous because both numerators and denominators were continous? Or, are we saying that the percent value itself, regardess of the values, is always attribute.
0June 28, 2007 at 10:26 pm #158043
Adrian P. SmithParticipant@AdrianP.Smith Include @AdrianP.Smith in your post and this person will
be notified via email.Hi Wicho
You are correct.
If both are continuous the percentage is continuous.
If both are discrete the percentage is discrete.
And of course, if you have 1 continuous variable and calculate what percentage of individual data points are above a certain value, that is also discrete (since each one is either above or not).
In general, discrete percentages are more common in transactional projects and if you are lucky enough to have continuous data it is usually better to analyse them separately as you do lose some information by converting it to a percentage.
Hope this helps.
Rgds,Adrian0 
AuthorPosts
The forum ‘General’ is closed to new topics and replies.