Tutorial 3: Variables

Think of independent and dependent variables in terms of cause and effect. Your independent variable(s) is the variable that you believe is causing the change in the dependent variable—the effect.

In the image below, the amount of water/amount of fertiliser represents your independent variables, while the height of the plant is your dependent variable.

Your implicit assumption is that a greater amount of water/fertilizer increases the height of the plant.

In short, the independent variable (A) affects the dependent variable (B).

When analysing your data, you may want to control for or keep a specific set of variables constant. Your independent and dependent variables may change, but your control variables are held constant (e.g. water levels stay the same despite changes to the independent and dependent variables).

Control variables are not of primary interest to the research question but are controlled because they could affect the dependent variable, thus confounding the results. By controlling these variables, researchers aim to isolate the relationship between the independent variable (the cause) and the dependent variable (the effect), ensuring that the observed effects are due to the manipulation of the independent variable alone.

For example, if a researcher is studying the effect of a new teaching method on student performance (the dependent variable), they might control for variables like age, prior knowledge, and study time, because these could also affect performance. By doing so, they can be more confident that changes in student performance are indeed due to the teaching method rather than other factors.

These variables are those that are divided into one unique group for each unique value of the grouping variable. In the example below, Gender is the grouping variable, which separates your data into two groups, one for Males and one for Females. Each group will have their own mean, median, standard deviation, etc.   

Grouping variables can be employed to gauge the differences between these groups. For example, what is the difference between 'Males' and 'Females'?

These are variables that are made by combining multiple variables into one. You do this at the analysis stage. How to do this will be covered later.  In the example below, a series of questions about attitudes are combined into a new variable that measures Extremism. 

Composite Variables:

Composite variables, also known as composite scores, are derived by combining two or more individual variables into a single variable. This is typically done to represent a multidimensional concept that cannot be captured by a single variable alone, often to simplify analysis or enhance the reliability and validity of measurements of complex traits or concepts.

Confounding Variables

This type of variable, known as a confounding variable, is associated with both the independent and dependent variables, yet it is not the primary focus of the study. Such variables can distort or conceal the actual effects of other variables on the outcome. 

Essentially, confounding variables influence the variables under examination, potentially leading to results that do not accurately represent the true relationship between the independent and dependent variables. Controlling for confounding variables effectively requires a robust research design, coupled with a thorough knowledge and understanding of the research area.

Covariates: 

A Covariate can be an independent variable, which may be of direct interest to your study or is an unwanted confounding variable. Adding covariates can increase the accuracy of your models.  In studies on extremism, for example, Household income can be an additional covariate to Age. Household income could also be considered a confounding variable. 

For a more in-depth discussion read this article.