In Experiments, researchers try to establish a Cause-Effect relationship between two sets of Variables.
Cause: event/stimulus that is changed/manipulated to cause an effect.
Effect: changes in behavior resulting due to the manipulation.
The concept of a Variable.
Any stimulus/event that varies in value and can be measured is called a Variable.
An object is not a variable, but its qualities/features are.
There are two types of variables: (i) Independent Variable, and (ii) Dependent Variable.
changes/alterations made by the researcher in this variable causes changes in other variables.
By making alterations to the independent variable, the researcher studies the effects of the changes made and records them in the study.
The effect of alterations made to independent variables occurs to the Dependent Variables.
It is expected that changes made to the independent variable cause changes to the dependent variable, hence the name “Dependent”.
Changes in the dependent variable may not always be a result of changes in the independent variable, because a specific behavior can be caused due to a lot of factors, But the researcher chose an independent variable to study just its effects on the behavior.
Factors other than the independent variable need to be controlled in an experiment so that it is easy for the researcher to easily experiment with the relationship between the independent and dependent variables.
Experiment and Control Groups.
The group which is exposed to or given the independent variable is the Experiment Group.
The group which is not exposed to the manipulated independent variable is the Control Group.
Both the groups are experimented with in similar ways except that in the control group setting the Independent Variable is absent. (Control Group = No Independent Variable)
The results of the Experiment Group and Control Group are then compared to check and make sure that it is the Independent Variable that is responsible for producing a specific behavior.
The distribution of participants in the experimental and control groups is done randomly to ensure that each person has an equal chance of getting into either of the groups.
Relevant variables that may affect the dependent variable must be controlled. These variables are of three types:
organismic: anxiety, personality, etc
situational/environmental: noise, temperature, etc
sequential: how the experiment is conducted when the participant is required to be tested in various conditions.
to control relevant variables, experimenters use several control techniques.
to minimize fluctuating variables and the best way to do this is to eliminate them from the experimental setting.
effort should be made to hold the extraneous variables constant so that their effect remains the same throughout the experiment if they cannot be eliminated.
matching is used for controlling organismic and background variables. The relevant variables in the two groups are held constant by taking matched pairs across conditions of the experiment.
The counter-balancing technique is used to minimize the sequence effect. The experimenter may interchange the order of the tasks.
Random assignment of participants to the groups also eliminates any potential systematic differences between groups.
An experiment is considered to be strong if it provides a piece of strong evidence of the cause-effect relationship between the variables.
Limitations of Experiments.
low-external validity: They provide only a demo of the outside world because they are mostly conducted in a controlled laboratory, that is why the experiments may produce results that do not apply to real situations.
Not all problems can be studied experimentally.
The third problem is that not all the relevant variables can be controlled.
Field Experiments and Quasi Experiments.
A Field Experiment is conducted when a particular study is not able to be conducted in a field or Natural Setting where the phenomenon exists. This results in high generalisability. In such types of experiments,
the control over relevant variables is less than in laboratory experiments.
it is more time-consuming and expensive.
In a Quasi Experiment, the independent variable is selected rather than altered or manipulated by the experimenter because not all variables can be manipulated in laboratory settings. The Latin word “Quasi” means “As if”. Thus, a quasi-experimenter uses naturally occurring groups to form experimental and control groups for manipulating independent variables in a natural setting.