This page explains key concepts that will be used in later pages. It introduces what data and variables are, and how to tell the difference between common types.
In brief, it covers the following:
Data refers to observations and measurements that have been obtained or collected, often through research. It can be recorded in different forms:
Quantitative data can be analysed using statistics, and so can qualitative data that is grouped into categories (for example, hair colour, country of birth, or marital status). However, qualitative data that records thoughts, feelings, and opinions is usually analysed in a different way.
In this module, you will work with quantitative data and categorical qualitative data. These types of data use specific statistical terms, which will be introduced shortly.
A variable is a characteristic or attribute that you observe, measure, or record. Some examples include height, weight, eye colour, dog breed, climate, electrical conductivity, customer service satisfaction and class attendance.
A variable can have different values for different subjects (a subject can be a person, place, or thing). For example:
These differences show how the value of a variable can change from one subject to another.
Choosing the correct statistic or statistical test depends on the type of data you have, and therefore the type of variable. For this reason, it is very important to be able to tell the difference between types of data.
Most of the time, you will classify your data (and variables) as either categorical or continuous. Each type can also be divided into smaller groups. These definitions and classifications are explained below.
Categorical data is data that is grouped into categories. For example, this includes variables such as gender or smoking status. It can be divided into two types:
Nominal data: The categories do not have an order. For example, marital status. If there are only two categories, the terms binary or dichotomous are sometimes used.
Ordinal data: The categories do have an order. For example, satisfaction level (such as low, medium, high).
Continuous data is measured on a continuous numerical scale and can take many possible values. For example, this includes variables such as weight or distance. It can be divided into two types:
Interval data: There is no true zero, and negative numbers have meaning. For example, temperature in degrees Celsius.
Ratio data: There is a true zero, and negative numbers do not have meaning. For example, height.
One other type of data is discrete data, which can be defined as follows:
Discrete data measures counts or the number of events. For example, class attendance. Although it is numerical, it is not measured on a continuous scale. Because of this, it does not fit neatly into either categorical or continuous data.
Instead, you can think of discrete data as a special type of data that can be treated as either categorical or continuous, depending on how many possible values there are. It is usually treated as continuous, but if there are only a small number of possible values (such as the number of units studied in a semester), it may be more useful to treat it as categorical.
It is also important to understand that continuous data can be turned into categorical data by creating categories from it. This can be useful if you want to use statistical tests that are designed for categorical data. For example, continuous data for a weight variable could be grouped into categories such as different weight ranges.
However, it is not possible to turn categorical data into continuous data. For this reason, if you have a choice, it is usually better to collect continuous data because it gives you more flexibility when analysing your data.
If you would like to practise classifying variables, try one or both of the following activities.
Activity: Decide whether you would treat each variable as categorical or continuous for the purpose of analysis and drag each variable into the correct box. Click on the ‘i’ symbol if you need a tip. Note that although you can always create categories from continuous data, you should place variables in the continuous box if it is possible to collect continuous data for them.
Activity: Decide whether the variables shown contain data that is nominal, ordinal, discrete or continuous and drag each variable into the correct box. Click on the ‘i’ symbol if you need a tip.
When you use bivariate analysis to test relationships between two variables, you will usually have one independent variable and one dependent variable. These are defined below.
The independent variable (also called the predictor variable) is the variable that may influence, affect, or predict another variable. For example, if you are investigating whether age influences income, then age is the independent variable.
The dependent variable (also called the outcome variable) is the variable that may be influenced, affected, or predicted. For example, if you are investigating whether income can be predicted by age, then income is the dependent variable.
It is important to be able to tell the difference between these two types of variables, because it determines where each variable is placed in tables and graphs and how it is used in statistical tests. However, it is also important to understand that the role of a variable depends on the context. Some variables (such as age) are always independent. Other variables (such as smoking status) can be either independent or dependent, depending on what you are trying to investigate.
If you would like to practise identifying independent and dependent variables, try the following activity.