Variables, Aims & Hypotheses

Genrally, the aim of research is to test a hypothesis about the relationship between 2+ variables. In correlations, we hope to test the relationship between two co-variables. In other research methods we hope to test a causal relationship between the IV & the DV. The validity of research can sometimes be reduced by confounding variables.

Independent Variable: The aspect of a study changed or controlled by the experimenter. Each different condition in a piece of research is referred to as a ‘level’ of the IV. 

Dependent Variable: Something the researchers hope to measure precisely, to find out if it has changed under different levels of the IV. 

Co-variable: Those characteristics which will be measured in a correlation.

Confounding Variable: Anything other than the IV which may have had an impact on the DV. This could be every day problems such as noise, temperature etc, but can also include anything which reduces internal validity such as experimenter bias etc.

Extraneous Variable: Factors which we recognise as potential confounding variables. Efforts should be taken to control all confounding variables.

To increase internal validity, it is important that we clearly explain how the levels of the IV will be different and that we establish a way to measure the DV as precisely as we can.

Operationalising Variables - ensuring that all variables are in a form that can be easily measured, e.g. for the DV you need to explain the units that will be used to record the results. For the IV you need to explain the different conditions/levels of the IV.

The aim of most research is either to test the difference between two levels of the IV or to test the relationship between two co-variables. A simple way to write aims is to use one of the following templates:

• To investigate the effect of [independent variable] on [dependentvariable]
• To investigate the relationship between [co-variable 1] and [co-variable 2]

An aim states what the research hopes to investigate, whereas a hypothesis is a prediction about what will happen. There are three types of hypothesis used in science; directional, non-directional and null.

Directional Hypothesis (one tailed): A prediction which specifies the direction of the effect (i.e. one level of the IV will increase the DV)

Non-directional Hypothesis (two tailed): A prediction which does not specify the direction of the effect (i.e. the IV will effect the DV)

Null: A prediction that the IV will have no effect on the DV. 

We only make a directional prediction if we have a good reason to be sure it is right. In effect, this means we only choose a directional hypothesis if previous research clearly suggests this outcome.

REMEMBER: Only choose directional if previous research is mentioned in the example of research.

As with aims, we can often make this easier for ourselves by following a template.

Directional - [IV] will increase / decrease [DV}
As [Co-variable 1] increases, [co-variable 2] will increase / decrease

Non-directional - [IV] will effect [DV]
There will be a relationship between[co-variable 1] and [co-variable 2]

Null  - [IV] will have no effect on [DV]
There will be no relationship between [co-variable 1] and [co-variable 2]