# Deciding the Level of Measurement is the Initial Step in Operationalizing A Construct

[Image Source](https://geneticliteracyproject.org)

Levels of measurement, normally called rating scales, allude to the values that a pointer can take. For instance, male and female are two levels of the marker gender. In his original article titled published in Science in 1946 title “On The theory of Scales of Measurement,” psychologist Stanley Smith Stevens characterized four bland kinds of rating scales for scientific measurements.

**Generic Type of Scales**

* Nominal Scales

* Ordinal Scales

* Interval Scales

* Ratio Scales

**Nominal Scales**

It is additionally alluded as categorical scales, measure categorical information. These scales are utilized for variables that have fundamentally unrelated traits. Illustrations incorporate industry, gender, and religious association. Regardless of whether we allot exceptional numbers to each value, for example 1 for male and 2 for female, the numbers don’t generally mean anything and could have been effectively been spoken to nonnumerically, for example, M for male and F for female. Nominal scales only offer names for various characteristic values. The proper measure of focal propensity of a nominal scale is mode, and neither the mean nor the median can be characterized.

[Image Source](http://www.appysphere.com)

**Ordinal Scales**

These are those that measure rank ordered information like the ranking of students in a class as first, second, third, et cetera, in view of their average grade. Be that as it may, the real values of characteristics or contrast in trait values can’t be surveyed. For example, ranking of students in class says nothing in regards to the genuine GPA of the students, or how they all around performed in respect to each other. A great case in the natural sciences is Moh’s scale of mineral hardness, which describes the hardness of different minerals by their capacity to scratch different minerals.

For example, diamonds can scratch all other naturally happening minerals on earth, and consequently precious stone is the hardest mineral. In any case, the scale does not demonstrate the real hardness of these minerals or even gives a relative appraisal of their hardness. The focal inclination measure of an ordinal scale can be its median or mode, and means are uninterpretable. Henceforth, measurable investigations may include percentiles and nonparametric examination, yet more modern procedures, for example, relationship, relapse, and examination of variance, are not proper.

**Interval Scales**

Interval scales are those where the values measured are rank-ordered, as well as equidistant from nearby traits. For instance, the temperature scale, where the contrast in the vicinity of 30 and 40 degree Fahrenheit is the same as that in the vicinity of 80 and 90 degree Fahrenheit. In like manner, on the off chance that you have a scale that asks respondents’ annual salary utilizing the accompanying characteristics: $0 to 10,000, $10,000 to 20,000, $20,000 to 30,000, et cetera, this is likewise an interval scale, in light of the fact that the midpoint of each range are equidistant from each other.

[Image Source](https://www.proprofs.com)

The intelligence quotient scale is additionally an interval scale, in light of the fact that the scale is planned with the end goal that the distinction between IQ scores 100 and 110 should be the same as in the vicinity of 110 and 120. Interval scale enables us to look at the amount more is one ascribe when contrasted with another, which isn’t conceivable with nominal or ordinal scales. Permitted focal propensity measures incorporate mean, median, or mode, as are measures of scattering, for example, range and standard deviation.

**Ratio Scales**

Ratio scales are those that have every one of the characteristics of nominal, ordinal, and interval scales, and moreover, likewise have a truezero point. Most measurement in the natural sciences and engineering utilize ratio scales, similar to some social science variables, for example, age, residency in an association, and firm size. For instance, a firm of size zero means that it has no workers or incomes.

The Kelvin temperature scale is likewise a ratio scale, as opposed to the Fahrenheit or Celsius scales, on the grounds that the zero point on this scale isn’t an arbitrary value however speaks to a state where the particles of matter at this temperature have zero kinetic energy. These scales are called ratio scales in light of the fact that the ratios of two points on these measures are meaningful and interpretable.

[Image Source](http://www.silkyquote.com)

References:

Construct Validity

Measuring Constructs

Operationalization

Types of Data Measurement Scales

Level of Measurement

The Four Scales of Measurement