Types of data measurement scales are fundamental to understand well for researchers. Types of data measurement scales in statistics consist of nominal, ordinal, interval, and ratio scales. This article will discuss the different types of data measurement scales.
We can use the types of data measurement scale to determine the analytical tools used in research. The selection of analytical tools cannot be determined according to the researcher’s wishes but must follow statistical rules.
In determining the data processing method, we need to know in advance what analytical tools will be used. When we draft a research proposal, there is a research methods chapter. In the research methods chapter, one sub-chapter will convey the plan of analysis methods and data processing methods.
Determine the analytical tool to be used depends on the scale of measurement of the data in the study. Types of data measurement scales consisting of nominal and ordinal scales can be grouped into non-parametric statistics.
Meanwhile, for types of data measurement scales consisting of interval and ratio scales, we can group them in parametric statistics.
In general, researchers often see associative relationships between variables. The associative relationship consists of an effect test, correlation, and comparative test.
In selecting this associative test, the analytical tools will be different for variables with nominal, ordinal, interval, and ratio scales. Therefore, when choosing associative tests, we must understand the differences in the nominal, ordinal, interval, and ratio data scales.
Nominal Scale Data
Nominal scale data is the lowest data scale in Types of data measurement. On a nominal scale, data is measured by categorizing the data. There is no ranking or level of data in the categorization of data on a nominal scale.
We can say that the nominal scale is only used to distinguish the data. An example of a nominal data scale is gender. Gender consists of males and females.
Based on the categorization of this data, it is only to distinguish a person’s gender, whether male or female. There is no measure that men are better than women and vice versa.
Another example of a nominal data scale is the type of work. The types of work consist of government employees, private employees, entrepreneurs, farmers, etc. The size of this type of work only distinguishes between types of work. No job A measure is higher than job B, and vice versa.
Ordinal Scale Data
Ordinal scale data is a higher data measurement scale than nominal scale data. On the ordinal data scale, data categorization is not only to differentiate but also to rank.
An example of an ordinal data scale is the level of education. The education level consists of elementary school, junior high school, high school, and college.
Based on the difference in education level, there are differences and any levels. Respondents with elementary school education levels will be lower than high school, and vice versa.
In measuring the ordinal data scale, many researchers measure it using a Likert scale. The Likert scale is widely used to measure qualitative variables, for example, competence, behavior, performance, etc.
Interval Scale Data
The data scale interval is higher than the nominal and ordinal scales. The interval data scale has also been grouped in parametric statistics.
On the interval scale, the data measurement has obtained a numerical value. In contrast to the nominal and ordinal scales, the data are qualitative. A scoring technique is needed so that quantitative analysis can be carried out.
The numerical data obtained has a distance on the interval data scale, and this data does not yet have absolute zero. Interval data can be measured on a particular scale.
An example of an interval data scale is temperature. The temperature has a specific interval of 1-100 degrees Celsius. This temperature data does not have absolute zero.
Ratio Scale Data
The data scale ratio is at the top of the data measurement scale. The data scale ratio is almost the same as the data scale interval. The difference is that the data already has absolute zero in the scale ratio.
In addition to having absolute zero, another characteristic of the ratio data scale is that it has the same distance. Examples of ratio data scales are height, weight, income, consumption, etc.
Ratio data scale data has many data analysis options. The ratio data scale already has lower data scale characteristics (nominal, ordinal, interval).
Selection of Analysis Tools
The selection of analytical tools must be adjusted to the scale of data measurement. For example, variables with nominal and ordinal data scales, then use analytical tools included in the non-parametric statistical group.
If the variables analyzed use interval and ratio scales, then select an analytical tool that belongs to the parametric statistics group.
In parametric statistics, some assumptions must be met. The assumption test is more complex in the analytical tools included in parametric statistics than those using non-parametric statistics.
Today, we have learned about the types of data measurement scales. See you in the following article! I hope it will be beneficial for all of us.
[…] In a previous article, I have stated that the type of data measurement scale consists of 4 scales, namely nominal, ordinal, interval, and ratio data scales. For those who haven’t read it yet, please visit Kanda Data’s article entitled: “Nominal, Ordinal, Interval, and Ratio Scales | Types Of Data Measurement.” […]
[…] Variables with nominal and ordinal scales can be grouped as non-parametric variables. The interval and ratio scales are grouped in parametric variables. For more details, you can read the article entitled: “Nominal, Ordinal, Interval, And Ratio Scales | Types Of Data Measurement.” […]
[…] For those who want to get a more in-depth explanation of the difference between the ordinal scale and other data measurement scales, you can read the previously written article entitled “Nominal, Ordinal, Interval, And Ratio Scales | Types Of Data Measurement.” […]
[…] For more complete information, you can read the article entitled: “Nominal, Ordinal, Interval, And Ratio Scales | Types Of Data Measurement“ […]
[…] In the paired sample t-test, we test for differences in mean values. Therefore, the data measurement scale should have an interval/ratio data scale. How to distinguish nominal, ordinal, interval, and ratio data measurement scales can read my previous article entitled: “Nominal, Ordinal, Interval, and Ratio Scales | Types of Data Measurement“ […]
[…] of correlation analysis technique depends on the data measurement scale used. As I wrote in the previous article, the data measurement scale is divided into nominal, ordinal, interval, and ratio […]
[…] I answered, yes! Linear Regression with the OLS method can add independent variables with nominal scale measurements. Variables that are measured on a nominal scale are called dummy variables. The difference between the interval/ratio scale and the nominal scale can be seen in my previous article entitled: “Nominal, Ordinal, Interval, And Ratio Scales | Types Of Data Measurement“ […]
[…] Therefore, researchers who observe variables measured by nominal or ordinal scales should not need to force themselves to choose the OLS method of regression analysis. Researchers can choose other analytical approaches following the characteristics of the observed data. To find out the differences in the nominal, ordinal, interval, and ratio data scales, you can read the previous article entitled: “Nominal, ordinal, interval and ratio scales | Types of Data Measurement.” […]
[…] if the measurement scale of the variable is ordinal, or if the researcher uses an interval/ratio scale but it is not normally distributed, the […]
[…] Parametric variables are typically measured using interval and ratio scales. On the other hand, non-parametric variables are measured using nominal and ordinal scales. […]
[…] the importance of this matter, in this discussion, we will explore the differences between nominal, ordinal, interval, and ratio scales along with […]