• When numbers are purposefully assigned to data that have a sense of rank or order, but the magnitude of difference between those numbers is not known or cannot be measured.

• Ordinal scale data can be in specific order
• Unlike with nominal data, the assigned numbers are not arbitrary
• This type of data scale does not allow for the calculation of an average or mean since the magnitude of difference between each assigned number is not the same.
• Example:  An average of the degree of heart failure a group of patients have cannot be described with a mean.  A patient cannot have Class 2.5 heart failure, because we do not really know what that means clinically.

• In both of the following examples there is a sense or ranking to condition of the patient. However, the magnitude of difference between each assigned level is not the same.
• New York Heart Association (NYHA) Heart Failure Classification:
• There are 4 classifications (Class I, II, III, & IV)
• There is a sense of order or rank, where a patient with NYHA Class III heart failure has more symptoms and complications than a patient with NYHA Class I heart failure.
• Glasgow Coma Scale:
• Score can range from as low as 3 and as high as 15.
  
• A trauma patient with a score of 8 is considered more unstable than a trauma patient whose GCS is 14.

• Nonparametric Statistical Analysis
• Parametric Statistical Analysis
• Nominal Data
• Continuous Data
  

1. Gaddis ML et al. Introduction to biostatistics: part 1, basic concepts. Ann Emerg Med 1990;19:86-89.

Editors:

• Anthony J. Busti, MD, PharmD, FNLA, FAHA
  

Last Reviewed: July 2015