Interval Data and Ratio Data
Aside from qualitative data (Nominal and Ordinal), there is also numeric data that belongs to as quantitative or metric data. Quantitative data is a kind of data obtained from measurement which can has decimal.
Examples of metric data are height, age, purchase, and others. For instance, height can be 170 cm or 178,45 cm (decimal), and age can be 30 years or 29,5 years.
Practically, metric data is divided into Interval and Ratio Data. Both are resemble, however the existence of absolute data in ratio data becomes the difference. The most popular interval data is room temperature which is represented by (Celsius, Fahrenheit, and Reamur) degree.
Here, there is no absolute temperature, they all depend on the measurement used. For instance, what is the temperature of frozen water?
Unlike interval data, ratio data has a real zero point or absolute. Many data in our daily life is based on the ratio data. For example height, if someone is weighing and having 40 kg, it means that he / she is 40 kg. Without any weight unit, it can be considered the weight is 0 kilograms.
It is better if statistically the data which is going to processed is ratio data, data that reflects such real situation will be easier interpreted than categorized nominal or ordinal data only.
Many statistic procedures are developed to process data with ratio or interval data, like t test or Anova. It is called as parametric statistics. There is also multivariate statistical technique such as double regression analysis, factor analysis, and others which require ratio data. Approach and special interpretation will be used for non ratio data.
