Levels of Measurement and Scales of Measure are expressions that typically refer to the theory of scale types developed by the psychologist Stanley Smith Stevens. Nominal levels of measurement only allow for the placing of the subjects into categories, like female and male. Ordinal levels of measurement allow the researcher to rank respondents, eg: strongly agree and agree. In quantitative social science, concepts are measured in order to provide a frequency count for each value of a variable.

In the quantification of people, perceptions, and events, there are 4 main levels of measurement. Not all measurements have the same qualities and some statistical tests require particular levels of measurement. There are four levels of measurement: nominal, ordinal, interval and ratio. A ratio level of measurement allows the researcher to express various scores as ratios and this requires an absolute zero.

For example, Mary has twice as many siblings as does John. Complex statistical tests require interval or ratio measurements. It is important for the researcher to understand the different levels of measurement, as these levels of measurement play a part in determining the arithmetic and the statistical operations that are carried out on the data. Interval measurement allow the researcher to specify the distance between respondents, John has 10 less units of intelligence than does Mary.

It should be noted that among these levels of measurement, the nominal level is simply used to classify data, whereas the levels of measurement described by the interval level and the ratio level are much more exact. The four levels of measurement have an important impact on how you collect data and how you analyze them later. If you collect at the wrong level, you will end up having to adjust your research, your design, and your analyses.

**
Level of Measurement -
Once Over Again**

Edgar F. Borgatta, Graduate Center, George W.
Bohrnstedt.

The distinctions between nominal, ordinal, interval, and ratio measurement were
popularized by S. S. Stevens. Unfortunately, positions taken by Stevens have often been
disseminated without criticism. One problem is the common assumption that
"ordinal" statistics are the best statistics to use for presumed noninterval
continuous social variables, when, in fact, they use addition, subtraction, and division,
which make the measurements interval by definition.