Nominal Data:

In business & Social Science, nominal data are more widely collected than any other. When nominal data is collected, you partition a set into categories that are mutually exclusive & collectively exhaustive.

The counting of numbers in each category is the only possible arithmetic operation, when nominal scale is employed. If we use numbers to identify categories, they are recognized as labels only & have no quantitative value. Nominal scales are the least powerful of the four data types. They suggest no order or distance relationship & have no arithmetic origin. Researcher is restricted to use 'Mode' as the measure of central tendency. There is no generally used measure of dispersion for nominal scales. This data is widely used in survey & other ex-post facto research when data are classified by major sub groups. Of population. e.g. gender, marital status.

Ordinal Data:

It includes characteristics of nominal scale plus indicator of order. The use of ordinal scale implies a statement of "greater than" or "less than" without stating how much greater or less. Example of ordinal data include opinion & preference scale. Widely used paired-comparison technique uses ordinal data. Because number of this scale have only a rank meaning, the appropriate measure of central tendency is the 'Median'. A percentile or quartile reveals the dispersion.

Interval Data:

It has the power of nominal data and ordinal data plus it incorporates the concept of equality of interval. ( distance between 1 & 2 is equal to distance between 2 & 3.) Calendar time is such a scale. 3 A.M. - 6 A.M. is equal to 4 A.M. - 7 A.M. When a scale is interval scale, you use 'arithmetic mean' as a measure of central tendency. The 'standard deviation' is the measure of dispersion.

Ratio Data:

It incorporates all of the powers of previous data types plus the provision for absolute zero origin. Ratio data represents actual amounts of a variable. e.g. weight, height, distance, area .etc. 'Geometric & Harmonic means' are measure of central tendency & co-efficient of variation may be calculated.

Measurement Scales:

The distinction between nominal, ordinal, interval, and ratio data is important for the nature of a set of data may suggest the use of particular statistical techniques. Researcher has to be quite alert about this aspect while measuring properties of objects or of abstract concepts.

When data can be measured in units which are interchangeable e.g. weights ( by ration scale ) or temperature ( interval scale ) that data is said to be parametric and can be subjected to most kinds of statistical and mathematical or statistical process.

When data can be measured in units which are not interchangeable, e.g. product preferences, the data is said to be non-parametric and is susceptible only to a limited extent to mathematical and statistical treatment.