Types of Variables

#RefreshingStatistics Day 1

Variable — any characteristics, number, or quantity that can be measured or counted; also called data item or observation in terms of data samples.

Variables can be:

a) numeric (quantitative) — variables whose values reflect a notion of magnitude; can take any numbers

• discrete — the values that are obtained by counting and have a finite number of possibilities; the values are often (but not always) integers

Example: number of people living in Tallinn, number of weeks since certain event

• continuous — the values that are not countable, are obtained by measuring, and have an infinite number of potential values

Example: age, weight, height

b) categorical (qualitative)

• ordinal — observations that can be logically ranked

Example: students grades scale, accident severity measures, risk assessment measures (low, medium, high)

• nominal — a qualitative variable that cannot be ranked, represents an individual category

Example: gender (male, female), color, customer type (home or business)

Variable transformations:

a) from continuous to discrete

Example: converting the age to amount of weeks since the date of birth

b) from numeric to categorical

Example: let’s say we have a list of customers and the frequency of web visits per week; we can define ranking of customers by creating intervals from web visits frequency — < 10 times a week, > 10 times a week, and label customers that fall under these intervals as “hibernating” and “active” accordingly