LEVEL OF MEASUREMENT GEOGRAPHY RESEARCH

1.1 Levels of Measurement

The mathematical and statistical operations that a researcher can perform on a given set of numbers are dependent on the level of measurement attained.  We will discuss the four principal levels of measurement  nominal, ordinal, interval, and ratio- and the rationale behind the operations permitted on each level.

1.2   Nominal Level

The lowest of measurement is the nominal level.  At this level, numbers or other symbols are used to classify objects or observations into a number of categories.  These numbers or symbols constitute a nominal, or classificatory, scale. Phenomenon in one classification category is equal to each other but not to phenomenon in any other category (i.e. the nominal level has the property of equivalence)

For example:  by means of the symbols 1 and 2, for instance, it is possible to classify a given population into males and females, with 1 representing males and 2 standing for females.  

1.3       Ordinal Level

When variables exhibit a relation to each other, they can be measured at ordinal level such relations can be designed by symbols > greater than. The ordinal level has properties of equivalent.

Social scientists study many variables that are not only classifiable but also exhibit some kind of relation.  Typical relations are higher, greater, more desired, more difficult, and so on.  Such relations may be designated by the symbols>or < Which means greater than or lesser than 

As an example of measurement at the ordinal level, consider the common practice of measuring attitudes.  Researchers measure attitudes by means of a series of questions whose alternative answers are ranked in ascending or descending order.

1.3   Interval Level

When exact distance between each of the observations is known as constant, measurement is carried out at interval level. Phenomenon of this level also display properties of equivalence and one observation can be greater than or smaller than another. For example, with interval measurement it is possible to say not only that Sue earns more than Mike, but also that Sue earns, say, $ 5,000 more than Mike. Examples of variables measured at the interval level are income, intelligence quotient (IQ), SAT scores, voter turnout, and crime rates.

1.4        Ration Level

Variables that have natural zero points (i.e. such as the point at which water freezes) can be measured on the ratio level of measurement.  Variables such as weight, time, length, and area have natural zero points and are measured at the ratio level.

At this level, the ratio of any two numbers is also independent of the unit of measurement.  The interval and the ratio levels are similar, and the rules by which numbers are assigned are the same, with one exception. A ration level of measurement, most commonly encountered in the physical sciences, is achieved only when it is possible to attain all four of these relations: (1) equivalence, (2) greater than, (3) known distance of any two intervals, and (4) a true zero point.