4_R

Levels of Measurement

Level of measurement is a classification which describes the nature of information within the values assigned to variables [6]. Also, it can be defined as the way a set of data is measured.

There are four levels of measurement [1-7]:

1. Nominal. Here, the values in the variable are used only to classify the data. The variables are usually organized into non-numeric categories (but can be numerica, for example, IDs etc) that cannot be ranked or compared quantitatively. In other words, the variables are categorized, where categories have no order and are mutually exclusive (i.e each case can only fit into one category) and exhaustive (i.e there is a category for each possible case). For example, gender, ethnicity, car brands etc.

2. Ordinal. These variables are also classified into categories, but these categories can be ordered and there is no equivalent distance between the categories. So basically the data is categorized and ranked in defined relative order. But there is no equivalent distance or boundaries between these categories. The categories still must be mutually exclusive and exhaustive, but ​also​ have a logical order that allows them to be ranked. For example, language ability (e.g., beginner, intermediate, fluent), class level (freshman, sophomore, junior, senior) etc.

3. Interval. This level of measurement not only classifies and orders the measurements, but it also specifies that the distances between each interval on the scale are equivalent along the scale from low interval to high interval. Thus, the variables can be directily compared, because the difference between any two sequential data points is exactly the same as the difference between any other two sequential data points. Also, zero point is just another data point along the scale, it does not mean the absence of something. For example, temperature in Celsius, IQ test, shoe size etc.

4. Ratio. Ratio variables have all of the characteristics of nominal, ordinal and interval variables and have a meaningful zero point. So the zero point means there is absence of something. So it allows to compare and add, subtract, divide and multiply the two ratio level variables. For example, weight, age, height etc.

Knowing the level of measurement helps to decide how to interpret the data from that variable. Also, determining the level of measurement of a variable helps to find an appropriate statistical test or analysis for this case [3].

---

References

1. https://www.questionpro.com/blog/nominal-ordinal-interval-ratio/

2. https://www.statisticssolutions.com/data-levels-of-measurement/

3. https://conjointly.com/kb/levels-of-measurement/

4. https://ncu.libguides.com/statsresources/measurement

5. https://www.kdnuggets.com/2015/08/statistics-understanding-levels-measurement.html

6. https://en.wikipedia.org/wiki/Level_of_measurement

7. https://www.scribbr.com/statistics/levels-of-measurement/