Types of Variable

• Non-experimental research: In non-experimental research, the researcher does not manipulate the independent variable(s). This is not to say that it is impossible to do so, but it will either be impractical or unethical to do so. For example, a researcher may be interested in the effect of illegal, recreational drug use (the dependent variable(s)) on certain types of behaviour (the independent variable(s)). However, whilst possible, it would be unethical to ask individuals to take illegal drugs in order to study what effect this had on certain behaviours. As such, a researcher could ask both drug and non-drug users to complete a questionnaire that had been constructed to indicate the extent to which they exhibited certain behaviours. Whilst it is not possible to identify the cause and effect between the variables, we can still examine the association or relationship between them.

In addition to understanding the difference between dependent and independent variables, and experimental and non-experimental research, it is also important to understand the different characteristics amongst variables. This is discussed next.

Dichotomous, Discrete and Continuous Variables

Variables can be characterised as dichotomous (or nominal), discrete (or qualitative/categorical/ordinal), and continuous (or quantitative/interval/ratio).

• Dichotomous variables, also known as nominal variables, are variables that have two levels; they are “either/or”. For example, if we were looking at gender, we would probably categorise somebody as either “male” or “female”. Alternately, if we were interested in mobile phone usage, we might start by asking a person: Do you own a mobile phone? Here, we may categorise mobile phone ownership as either “Yes” or “No”.
  
• Discrete variables, also known as qualitative, categorical, or ordinal variables, have more than two levels of measurement. For example, if we were looking at where people live, we may categorise this by US state, which would mean that we had 50 different levels. Similarly, in examining what political party an individual voted for, we may categorise this as “Democratic Party”, “Republican Party”, “None”, and “Other”. We may even ask the question: Do you like the Democratic Party? If we gave people the choice of stating “Not very much”, “They are OK”, and “Yes, a lot”, we can also rank the people’s opinions. Indeed, we could rank these opinions from the most positive (Yes, a lot), to our middle response (They are OK), to the least positive (Not very much). However, whilst we can rank the levels of measurement for discrete variables, we cannot place a “value” to them.
  
• Continuous variables, also known as quantitative, interval or ratio variables have a number of facets. However, their central characteristic is that continuous data can be measured along a continuum and has a numerical value (for example, continuous variables include income, height, age, time, temperature, etc…). As such, the time could be 10:43, 10:44, 10:45 and so forth. Here, the accuracy of the measurement is determined by the precision of the measurement instrument. For example, the time recorded is as accurate as the precision of the recording device. Therefore, we may not only be able to record time in minutes, but also seconds, milliseconds, and so forth. In some cases, the measurement scale for data is ordinal but the variable is treated as continuous. For example, a Likert scale that contains five values – strongly agree, agree, neither agree nor disagree, disagree, and strongly disagree – is ordinal. However, where a Likert scale contains seven or more value – strongly agree, moderately agree, agree, neither agree nor disagree, disagree, moderately disagree, and strongly disagree – the underlying scale is sometimes treated as continuous.

It is worth noting that how we categorise variables is somewhat of a choice. Whilst we categorised gender as a dichotomous variable (you are either male or female), social scientists may disagree with this, arguing that gender is a more complex variable involving more than two distinctions, but also including measurement levels like genderqueer, intersex, and transgender. At the same time, some researchers would argue that a Likert scale, even with seven values, should never be treated as a continuous variable.

To find out more about setting up experiments and evaluating their output, see the statistical guide, Hypothesis Testing. However, if you are relatively new to statistics, we would first recommend that you work through the other statistical guides in our Essentials series. In the next guide in the series, we talk about Measures of Central Tendency.