We measure physical objects as well as abstract concepts. The measurement means the process of assigning members to objects or observations, the level of measurement is simple, the researcher assigns numerals to objects, events or properties according to certain rules like percentages for e.g. Unemployment increases by 10%. Another example is the Richer scale, like say the earthquake measured 5.5 on the Richer scale. There are three central concepts in measurement.
(1) Numerals : A number is a symbol such as V, X, C or 5, 10, 100 ETC. a numeral has no implicit quantitative meaning. When it is given quantitative meaning, it becomes a number and can be used in the mathematical and statistical computation.
(2) Assignment : This is the designation of numerals or numbers to certain objects or events. For e.g. in a mass media research study, a simple measurement system might entail assigning numeral 1 to people who obtain most of their news from television, and numeral 2 to those who get most of their news from a newspaper, and numeral 3 to those who get most of their news from some other source.
(3) Rules : Rules specify the way that numerals and numbers are to be assigned. Rules are the base of any measurement system, if they are faulty, the entire system will be flawed. An example of rules is that in order to measure the speed of running, a stopwatch is used.
Scales/Levels of Measurement
Four different ways to measure things have been specified and they are known as the different levels of scale of measurement. This different os in the basis of rules that at used to assign numbers to objects or events. The different levels of measurements are as follows :
(1) Nominal Level/Scale : In this numerals or other symbols are assigned to events, persons, objects or characteristics in order to label them. The numbers assigned are just convenient labels for the particular class of events and they have no quantitative value. Nominal scales provide convenient ways of keeping track of people, object, and events.
(2) Ordinal Level/Scale : Here, the numbers used cannot be considered to be associated with an ordered scale, or their order is of no consequences. For e.g. In a study on political party affiliation, the coding could be as follows :
This is the weakness form of measurement.
This is the lowest level of the ordered scale that is commonly used. In this, events, objects or persons are placed in order, but no attempt is made to make the intervals of the scale equal in terms of some rules. Here objects are usually ranked along some dimension. For e.g. From the smallest to the largest. Rank orders represent ordinal scales and are frequently used in research related to quantitative phenomena. A student's rank in the class involves the use of ordinal scale. An example could be a measurement of the variable of a socioeconomic status of people in the country. The categorization could be according to class - lower class, lower middle class, middle class, upper middle class or upper class. Common examples of ordinal scales are rankings of football or basketball teams, military ranks, beauty pageant results, etc. Ordinal scales only permit the ranking of items from the highest to the lowest. They have no absolute value, and the real differences between adjacent ranks may not be equal. All that can be said is that one person is higher or lower on the scale than another, but more precise comparisons cannot be made. Therefore, it can imply something to be 'greater than' or 'lesser than' but will not be able to state how much greater or lesser.
(3) Interval Scale/Level : In interval scales, the interval between adjacent points are adjusted in terms of some rule that have been established as a basis for making the units equals. Interval scales can have an arbitrary zero, but it is not possible to determine for them what is an absolute zero or the unique origin. Interval scales lack a true zero point, and this is its disadvantage. An example of the interval scale is temperature. The same amount of heat is required to warm an object from 20 to 30 degree as to warm it from 40 to 50 degrees. Interval scales incorporate the formal property of equal differences. That is, numbers are assigned to the positions of objects in such a way that one may carry out arithmetic operations on the differences between them. Due to the absence of a true zero point, a researcher cannot make statements of a proportional nature.
(4) Ratio Scale/Level : Ratio levels of measurement have an absolute or true zero point of measurement. With this fixed zero point, ratio judgements can be made. Time and distance are ratio measures. An example would be, one can say that a car travelling at 50 miles per hour is going twice as fast as a car travelling at 25 miles per hour.
In mass media research, ratio levels of measurement are rarely used, although some variables like time spent watching television or number of words per story, etc. are ratio measurements.