Interval Scale: Definition
The interval scale is defined as a quantitative measurement scale where the difference between 2 variables is meaningful. Interval scale is the 3rd level of measurement. In other words, the variables are measured in actuals and not as a relative manner, where the presence of zero is arbitrary. This means that the difference between two variables on a scale is an actual and equal distance. For example, difference between 68 degrees F and 58 degrees F is the exact same as 101 degrees F and 91 degrees F. In this example, you can not say that 98 degrees F is double the temperature in terms of “heat” or “cold” of 49 degrees F. This is because there is no absolute zero on the Fahrenheit scale – that is at zero temperature doesn’t exist.
It is easy to remember the objective of this scale as “interval” equates to the interval or distance between 2 variables. Another easy way to remember interval scale is that subtraction is defined between the two variables. This is unlike the ratio scale where division is defined between two variables.
Interval data can be discrete – with whole numbers like 8 degrees, 4 years, 2 months etc. or continuous – with fractional numbers like 12.2 degrees, 3.5 weeks or 4.2 miles.
This statistical method is also known as scale, quantitative or parametric.
Learn more: Interval Data- Definition and Example
Characteristics of interval scale
The characteristics of interval scale are as follows:
- The interval scale is preferred to nominal scale or ordinal scale because the latter two are qualitative scales; and the interval scale is quantitative in the sense that it can quantify the difference between values.
- You can subtract values between two variables that helps understand the difference between 2 variables.
- The interval scale allows to calculate the mean and median of variables.
- This is a preferred scale in statistics because you can assign a numerical value to any arbitrary assessment such as feelings or different calendar types like Gregorian, Aztecan, or Buddhist calendars where the variable inputs are the same metrics.
Interval scale examples
The interval scale is the most commonly used question types in a research study. To get any answer type, it is imperative that the question asked requires the respondents to answer on a numerical scale where the difference between the two numbers is equal.
You have probably seen the following scales used in a research study – agreement, satisfaction levels, likelihood or want. In the interval scale, the survey is required to be designed in such a way that the dimension too be measured is scaled appropriately and this can be anchored ideographically, numerically or verbally.
The question types for interval scales are:
One of the most commonly used interval scale question, the question is arranged in a 5 point Likert Scale question where the each emotion is denoted with a number and the variables range from extremely dissatisfied to extremely satisfied.
Net Promoter Score (NPS)
In this interval question, the question is asked using a Net Promoter Score (NPS) question where the respondents reply on a scale of 1-10 how likely they are to refer a company/product/service to a peer and in aids in calculating how happy a customer is or not.
Bipolar Matrix Table
Another interval question is where an object is assessed by the respondent on a bipolar matrix table (using 5-point rating scale):
The interval scale gives the ability to quantify and differentiate between options. This is better than the nominal scale and the ordinal scale as they do not account for quantitative insights. The interval scale consists of variables that exist along a common scale at equal intervals. The scientific measures used to calculate the distance between the variables is highly reliable.
Although in an interval scale, since there is an absence of the absolute 0 and it works on the principal of an arbitrary 0, the division of variables is not possible. So whilst interval scale allows for a lot of data to be analysed from a question, it doesn’t have the ability to calculate ratios.