Introduction to Dummy Variables
• N/B Ratio scale are interval level (Given X then x2-x1 makes se
𝑥2
but not example is temperature. Ordinal level Given X then x2 >
𝑥1
makes sense e.g ranking footballers. Ratio scale is where other t
𝑥2
characteristics of interval and ordinal scales, also make sense.
𝑥1
• A variable where non of interval, ordinal and ratio scale do not hol
nominal scale. Such variables are also known as indicator variab
categorical variables, qualitative variables, or dummy variables
• In the previous discussions, we encountered only ratio scale variab
i.e Quantitative variables as the explanatory variables.
, Introduction to Dummy Variables…
• In this topic, we consider models that may involve not only ratio s
variables but also nominal scale variables.
• THE NATURE OF DUMMY VARIABLES
• In regression analysis the dependent variable is frequently influen
not only by ratio scale variables (e.g., income, output, prices, co
height, temperature) but also by variables that are essenti
qualitative, or nominal scale, in nature, such as sex, race, co
religion, nationality, geographical region and party affiliation.
• For example, holding all other factors constant, female workers
found to earn less than their male counterparts or nonwhite work
are found to earn less than whites.
• N/B Ratio scale are interval level (Given X then x2-x1 makes se
𝑥2
but not example is temperature. Ordinal level Given X then x2 >
𝑥1
makes sense e.g ranking footballers. Ratio scale is where other t
𝑥2
characteristics of interval and ordinal scales, also make sense.
𝑥1
• A variable where non of interval, ordinal and ratio scale do not hol
nominal scale. Such variables are also known as indicator variab
categorical variables, qualitative variables, or dummy variables
• In the previous discussions, we encountered only ratio scale variab
i.e Quantitative variables as the explanatory variables.
, Introduction to Dummy Variables…
• In this topic, we consider models that may involve not only ratio s
variables but also nominal scale variables.
• THE NATURE OF DUMMY VARIABLES
• In regression analysis the dependent variable is frequently influen
not only by ratio scale variables (e.g., income, output, prices, co
height, temperature) but also by variables that are essenti
qualitative, or nominal scale, in nature, such as sex, race, co
religion, nationality, geographical region and party affiliation.
• For example, holding all other factors constant, female workers
found to earn less than their male counterparts or nonwhite work
are found to earn less than whites.
