Research methods in psychology by B. Morling (third edition) – Chapter 10 summary

Experiments are the only way to investigate causal issues.

EXPERIMENTAL VARIABLES
An experiment means that the researchers manipulated at least one variable and measures another. A manipulated variable is a variable that is controlled. Measured variables take the forms of records of behaviour or attitudes. The manipulated variable is the independent variable. The conditions are the different levels of the independent variable. The measured variable is the dependent variable. Control variables are variables that are also controlled. These variables are controlled by holding all other factors constant. Any variable that an experimenter holds constant on purpose is called a control variable.

WHY EXPERIMENTS SUPPORT CAUSAL CLAIMS
There are three rules for something to be causal:

1. Covariance
2. Temporal precedence
3. Internal validity

If independent variables did not vary, a study could not establish covariance, because you need a comparison group to establish covariance. It is impossible to establish internal validity if there are confounds, or alternative explanations. A design confound is an experimenter’s mistake in designing the independent variable. It is a second variable that happens to vary systematically along with the intended independent variable. Something is only a design confound if it shows systematic variability with the independent variable. It would not be a design confound if it shows unsystematic variability. If individual differences are distributed evenly in both groups, the are not a confound.

Selection effects are effects that are the result of two groups being systematically different from those in the other. This can also happen when the experimenters let participants choose in which group they want to be. The selection effects can be avoided by using random assignment, when assigning people to the conditions. Selection effects can also be avoided by using matched groups.

INDEPENDENT GROUP DESIGNS
In an independent group design both groups of participants are placed into different levels of the independent variable. This type of design is also called a between-subjects design or between-groups design. In a within-groups design or within-subjects design, there is only one group of participants and each person is pretended with all levels of the independent variable.

In the posttest-only design, also known as equivalent groups, participants are randomly assigned to independent variable groups. In a pretest/posttest design, participants are randomly assigned to at least two different groups and are tested on the key dependent variable twice, before and after exposure to the independent variable.

WITHIN-GROUPS DESIGNS
There are two basic types of within-groups design:

1. Repeated-measures design
   In this design participants are measured on the dependent variable every time they are exposed to another level of the independent variable.
2. Concurrent-measures design
   In this design participants are exposed to all the levels of an independent variable at roughly the same time.

The main advantage of a within-group design is that it ensures that participants in the two groups will be equivalent. The term power refers to the probability that a study will show a statistically significant result when a n independent variable truly has an effect in the population. A within-groups design also requires less participants, because they are all exposed to the same conditions.

Sometimes, being exposed to one condition changes how participants react to the other condition. These responses are called order effects and they happen when exposure to one level of the independent variable influences responses to the next level. An order effect is a confound. Order effects can include the following effects:

1. Practice effects
   Participants can get better at a task after a while.
2. Fatigue effects
   Participants can get tired or bored of the task towards the end.
3. Carryover effects
   Some form of contamination carries over from one condition to the next (e.g: sipping orange juice right after brushing your teeth. The first taste contaminates our experience of the second one).

Order effects are potential internal validity problems. They can be avoided by using counterbalancing, they present the levels of the independent variable to the participants in different sequences. When using counterbalancing, the researchers have to split the participants into groups, each group receives one of the condition sequences.

There is a difference between full counterbalancing and partial counterbalancing. In full counterbalancing, all possible condition orders are represented. In partial counterbalancing, only some of the possible condition orders are represented. For partial counterbalancing, a Latin square can be used, to make sure that every condition appears in every position at least once.

There are three main disadvantages to within-groups designs:

1. Repeated-measures designs have the potential for order effects
2. Within-groups design might not be possible or practical
3. Participants might change the way they normally act when they see all the levels of the independent variable

If there is a demand characteristics, when participants guess what the researchers expected them to do and act accordingly, it is not possible to give a causal conclusion, because there is a confound.

INTERROGATING CAUSAL CLAIMS WITH THE FOUR VALIDITIES
If you want to interrogate causal claims with the four validities, you need to check the face validity first: how well were the dependent variables measured and how well were the independent variables manipulated? A manipulation check is an extra dependent variable that researchers can insert into an experiment to convince them that their experimental manipulation worked.

A pilot study is a simple study, using a separate group of participants, that is completed before (or sometimes after) conducting the study of primary interest.