Skip to main content

Quantitative Methods Using R

2 Basic Statistical Concepts

2.1 Data Types

Data types idea in computer science and program shares similar nomenclature in case of statistics. Data is broadly classified into constant and variables in terms of its nature during the execution of the analysis or the statistical program.

Constant are those kind of data types which are not changed during the program or during analysis. For eg, the value of alpha (alpha) is always kept constant.

Variables are those data types which are changed or have multiple values in the program.

2.2 Types of variable

2.2.1 Quantitative Variables (Continuous and Discrete):

  • Continuous Variables: Variables that can take any value within a range, typically measured on a continuous scale. Example: Height, weight, or temperature.

  • Discrete Variables: Variables that can only take specific values, usually whole numbers or counts. Example: Number of students in a class, or number of books in a library.

    Qualitative Variables (Nominal and Ordinal):

  • Nominal Variables: Variables that represent categories without any inherent order. Example: Gender (male or female), or types of food (vegetarian or non-vegetarian).

  • Ordinal Variables: Variables that represent categories with a natural order or ranking. Example: Education level (elementary, high school, or college), or customer satisfaction ratings (poor, average, or excellent).

                       VARIABLES
                       |
            +----------+-----------+
            |                      |
      Quantitative           Qualitative
            |                      |
     +------+-------+      +-------+-------+
     |              |      |               |
Continuous    Discrete   Nominal      Ordinal

2.3 Types of scales of measurement of variables

Four different types of scales of measurement are presented in the table below.

Scale of Measurement Description Example
Nominal Categorical data without any inherent order or ranking. Each value represents a distinct category. Gender (male or female), colors, or religion.
Ordinal Categorical data with a natural order or ranking, but without a specific numerical value. Education level, Likert scale, or age group.
Interval Numeric data with a constant difference between values, but no true zero point. Temperature (Celsius or Fahrenheit), or calendar years.
Ratio Numeric data with a constant difference between values and a true zero point. Age, height, weight, or income.

Understanding the scales of measurement is important because it helps determine the appropriate statistical techniques and interpretations for the data.