Measurement Scales

Measurement scales refer to the types of information provided by numbers. Each scale (i.e., nominal, ordinal, interval, and ratio) provides a different type of information. Knowing which scale applies in a particular situation is necessary to accurately interpret numbers assigned to people, objects, or events. Ignorance of scales’ distinguishing characteristics can lead to improper treatment of the numbers (e.g., computing incorrect statistics) and inappropriate actions toward and decisions about people.

Nominal Scales

Numbers are used to name or identify people, objects, or events—for example, a social security number or driver’s license number. Gender is an example of a nominal measurement in which a number (e.g., 1) is used to label one gender, such as males, and a different number (e.g., 2) is used for the other gender, females. Numbers do not mean that one gender is better or worse than the other; they simply are used to classify persons. In fact, any other numbers could be used because they do not represent an amount or quality. It is impossible to use word names with certain statistical techniques (e.g., Pearson product-moment correlation or linear multiple regression), but numerals can be used in a coding system. For example, fire departments may wish to examine the relationship between gender (where male = 1, female = 2) and performance on physical ability tests (with numerical scores indicating ability).

Other examples of nominal scales used to classify people are race (e.g., Caucasian, African American, Asian) and political party affiliation (e.g., Democrats and Republicans). Examples of nominal measurements that can be used to classify objects are test items (e.g., multiple choice, short answer, and essay) and type of physical injury suffered on the job (e.g., slip, trip, or fall). Examples of nominal measurement of events are charges of discrimination (e.g., racial, gender, age, and disability) and selection procedures (e.g., interview, paper-and-pencil test, and assessment center exercise).

Ordinal Scales

Numbers are used to represent rank order and indicate the order of quality or quantity, but they do not provide an amount of quantity or degree of quality. Usually, the number 1 means that the person (or object or event) is better than the person labeled 2; person 2 is better than person 3, and so forth. For example, to rank order persons in terms of potential for promotion, May might be 1, Joe might be 2, and Wong might be 3. The 1 rating assigned to May indicates that she has more potential but does not indicate how much more potential than Joe. There may be very little difference between May and Joe, but Wong may be extremely inferior to Joe. Academic journals (objects) have been rank ordered in terms of prestige. When ordinal measurement is used (rather than interval measurement), certain statistical techniques are applicable (e.g., Spearman’s rank correlation).

Interval Scales

Numbers form a continuum and provide information about the amount of difference, but the scale lacks a true zero. The differences between adjacent numbers are equal or known. If zero is used, it simply serves as a reference point on the scale but does not indicate the complete absence of the characteristic being measured. For example, if an individual obtains a score of 0 on the extroversion scale of the Revised NEO Personality Inventory, the 0 score does not mean that he or she is completely unsociable. The Fahrenheit and Celsius scales are examples of interval measurement. It takes the same amount of heat to raise the temperature from 50 degrees to 60 degrees as it does to raise the temperature from 60 degrees to 70 degrees. The most powerful statistical techniques are appropriate with interval measurement.

Most measures of psychological constructs are not true interval scales, according to the strict definition. They provide information about order, but whole numbers on such a scale are not precisely equidistant from adjacent whole numbers. Moreover, the amount of difference (of the construct or trait) between numbers may be unknown. For example, the work scale of the Job Descriptive Index measures satisfaction with the work itself, separate from other aspects of the job (e.g., pay or promotion). The 18 items constituting the scale are scored 3 for favorable responses, 2 for unfavorable responses, and 0 if the respondent is undecided whether the item accurately describes the job. Although a score of 54 is three points higher than a score of 51, which is three points higher than 48, increases in the degree of satisfaction may actually be different from 48 to 51 than from 51 to 54. Although they do not adhere to the strict definition of interval scales, psychological tests (in the broad sense of the word) that have been carefully constructed can be treated as interval scales.

Before numbers can be assigned to people (reflecting a level or degree of some psychological characteristic), items (such as those on an application blank, mental ability test, or performance appraisal form) must be assigned numbers to reflect some quality, such as relevance, difficulty, or importance. Using the method of equal appearing intervals, subject-matters experts may be instructed to indicate their opinion of items by rating them on an interval scale. For example, subject-matter experts constructing a job knowledge test for firefighters may be asked to rate the importance of knowing how to use certain pieces of equipment (e.g., the Jaws of Life) from 1 (not important at all) to 5 (extremely important). An importance index can then be computed by averaging item ratings.

Ratio Scales

Ratio scales have all of the characteristics of interval scales as well as a true zero, which refers to complete absence of the characteristic being measured. Physical characteristics of persons and objects can be measured with ratio scales, but most psychological characteristics (e.g., intelligence, conscientiousness, and interests) cannot. Consequently, most measures of employees’ and applicants’ optimal and typical performance do not use true ratio scales. Height and weight are examples of ratio measurement. A score of 0 means there is complete absence of height or weight. Ratios can also be created such that a person who is 4 feet tall is two thirds (4 divided by 6) as tall as a 6-foot-tall person; a 100-pound person is two thirds as heavy as a 150-pound person.


Measurement refers to the assignment of numbers in a meaningful way. Understanding scales of measurement is important to interpreting the numbers assigned to people, objects, and events. For the most part, numbers used in the work world are nominal, ordinal, or approach interval measurements. Assuming interval measurement permits the use of statistical techniques (parametric statistics) that are more powerful than other techniques (nonparametric statistics).


  1. Allen, M. J., & Yen, W. M. (1979). Introduction to measurement theory. Monterey, CA: Brooks/Cole.
  2. Crocker, L., & Algina, J. (1986). Introduction to classical and modern testtheory. New York: Harcourt Brace Jovanovich.
  3. Murphy, K. R., & Davidshofer, C. O. (2005). Psychological testing: Principles and applications (6th ed.). Upper Saddle River, NJ: Prentice Hall.
  4. Nunnally, J., & Bernstein, I. (1994). Psychometric theory (3rd ed.). New York: McGraw-Hill.
  5. Society for Industrial and Organizational Psychology. (2003). Principles for the validation and use of personnel selection procedures (4th ed.). Bowling Green, OH: Author.