Research Methods chapter 8

Question 1

Confounding variables

Answer 1

Variables that are not a part of your hypothesis test. They can influence the relationship between two other variables in a study. For example, if a researcher wants to study the relationship between coffee consumption and the risk of developing heart disease, there might be a confounding variable involved, such as smoking.

Question 2

Pretest

Answer 2

The measurement of the dependent variable prior to introduction of the treatment

Question 3

Posttest

Answer 3

The measurement of the dependent variable after the treatment has been introduced into the experimental situation

Question 4

Experimental group

Answer 4

The group that receives the treatment/the group in which the treatment is present. When the independent variable has several values, you can have more than one experimental group

Question 5

Control group

Answer 5

The group that does not receive the treatment

Question 6

Random assignment

Answer 6

Assign participants to groups to make comparisons. To compare between groups, you do not want the groups to differ with regard to variables that could be alternative explanations for a causal relationship.

Question 7

Treatment/independent variable

Answer 7

The treatment is the creation of a situation or entering into an ongoing situation and do something to modify it, coming from medical practice. You want the treatment to have an impact and produce specific reactions, feelings or behaviours.

Question 8

Dependent variable (in experimental research)

Answer 8

The physical conditions, social behaviours, attitudes, feelings, or beliefs of participants that change in response to a treatment. You can measure dependent variables by paper-and-pencil indicators, observations, interviews, or physiological responses (e.g., heartbeat or sweating palms)

Question 9

Classical experimental design

Answer 9

Composed of a random assignment, a pretest and posttest, experimental group, and a control group

Question 10

Pre-experimental designs

Answer 10

Some designs lack random assignment and are compromises or shortcuts

Question 11

One-shot case study design

Answer 11

Also called the one-group post test-only design. This type of study has only one group, a treatment and a posttest. Since there is only one group, there is no random assignment.

Question 12

One-group pretest-posttest design

Answer 12

This design has one group, a pretest, a treatment and a posttest. It lacks a control group and random assignment.

Question 13

Static group comparison

Answer 13

Also called the post-test-only nonequivalent group design. It has two groups, a posttest and a treatment. It lacks random assignment and a pretest.

Question 14

Quasi-experimental designs

Answer 14

Help test for causal relationships in situations in which the classic design is difficult or inappropriate. They are quasi because they are “weaker” compared to the classical experimental design. In general, you have less control over the independent variable compared to the classical design.

Question 15

Two-group post test-only design

Answer 15

Identical to the static group comparison, but with one exception: you randomly assign. It has all the parts of the classical design except for a pretest.

Question 16

Interrupted time-series design

Answer 16

An experimental design in which the dependent variable is measured periodically across many time points, and the treatment occurs in the midst of such measures, often only once˙

Question 17

Equivalent time series

Answer 17

This design is similar to the one-group design interrupted time series. It extends over a time period but instead of a single treatment, it has a treatment several times. Like the interrupted time-series design, you measure the dependent variable several times before and after the treatments.

Question 18

Latin square designs

Answer 18

Useful for finding out how several independent variables in different sequences or time orders influence the dependent variable. The Latin square design is created in this situation. The Latin square design is especially useful when the order or sequence in which the variables are presented could potentially influence the results (order effects).

Question 19

Solomon four-group design

Answer 19

Combines the classical experimental design with the two-group post test-only design. It randomly assigns participants to one of four groups, allowing for a more robust analysis of the effect of an intervention or treatment.

Question 20

Factorial design

Answer 20

In this design, the treatment is not each independent variable, but a combination of the variable categories instead. A two by three factorial design is written 2 * 3. This means that there are two treatments, with two categories in one and three categories in the other. An 2 * 3 * 3 design means that there are 3 independent variables, one with two categories and two with three categories each. Factorial designs allow you to measure and examine more of the world’s complexity than other designs.
This can be for example useful if a researcher wants to research 2 effects on participant’s memory performance, effect A and B, and wants to use different groups and create all possible combinations with these groups to see how the effects compare among different groups.

Question 21

Interaction effects

Answer 21

In a factorial designs, treatments can have main effects and interaction effects. Main effects are present in one-factor or single-treatment designs. You simply examine the impact of the treatment on the dependent variable here. In a factorial design, specific combinations of independent variable categories can have an effect beyond a single factor effect. They are interaction effects, as the categories in a combination interact to produce an effect beyond that of each variable alone.

Question 22

Design notation

Answer 22

Uses the following symbols: O (observation of the dependent variable), X (treatment, independent variable), R (random assignment). Pretests are O1, posttest O2

Question 23

Internal validity

Answer 23

When the independent variable, and nothing else, influences the dependent variable. Anything other than the independent variable influencing the dependent variable threatens internal validity

Question 24

Selection bias

Answer 24

Arises when you have more than one group of participants in an experiment.

Question 25

Which 3 types of comparing experiments do you have?

Answer 25

1. Within-participants: you compare the same person over multiple points in time (e.g., before and after completing a training course)
2. Within-groups: you compare one group of participants at two or more times (e.g., the group average of 15 people before and after a training course). You can also compare the group across a series of treatments.
3. Between-groups: you compare two different groups of participants, those who have and have not had the treatment (e.g., a group average of 15 who had to do the training course compared with 15 who did not). You can randomly assign participants to create similar groups.

Question 26

History effects

Answer 26

When an event unrelated to the treatment occurs during the experiment and influences the dependent variable. History effects are more likely in experiments that continue over a long time.

Question 27

Maturation

Answer 27

The threat that a biological, psychological, or emotional process within participants other than the treatment takes place during the experiment and influences the dependent variable. A maturation effect is more common in experiments over a long time. Designs with a pretest and control group help us determine whether maturation or history effects are present.

Question 28

Testing effects

Answer 28

When the pretest measure itself affects an experiment. This threatens internal validity, because more than the treatment alone is affecting the dependent variable. The Solomon four-group design helps you detect testing effects.

Question 29

Instrumentation

Answer 29

This threat is related to stability and reliability. It occurs when the instrument or dependent variable measure changes during the experiment.

Question 30

Experimental mortality

Answer 30

Experimental mortality, or attrition, arises when some participants do not continue throughout the entire experiment. It does not necessarily mean that they died, but if many participants leave partway through an experiment, you cannot know whether the results would have been different if they had stayed.

Question 31

Statistical regression

Answer 31

A problem of extreme values or a tendency for random errors to move group results toward the average. It can occur in two ways:
1. Diffusion of treatment or contamination: the threat that participants from different groups will communicate and learn about the other group’s treatment. You can avoid it by isolating groups or having them promise not to reveal anything to other participants.

2. Compensatory behaviour: Experiments that provide something of value to one group of participants but not to another, and the differences become known, is compensatory behaviour. The inequality between groups may create a desire to reduce differences, competitive rivalry between groups, or resentful demoralisation.

Question 32

What is experimenter expectancy and how can its effect be reduced?

Answer 32

Experimenter behaviour might threaten internal validity if the experimenter indirectly communicates a desired outcome. Even the most honest experimenter might unintentionally communicate desired findings. The double-blind experiment controls for experimenter expectancy: in it, the only people who have direct contact with the participants do not know the details of the hypothesis or the treatment. It is double blind because both the participants and those in contact with them are blind to details of the experiment.

Question 33

Demand characteristics

Answer 33

When a participant picks up clues about the hypothesis or an experiment’s purpose, then modify behaviour to what they believe the study demands of them. Participants often do this to please the researcher.

Question 34

Placebo effect

Answer 34

Threatens internal validity, I assume you know what it means

Question 35

External validity

Answer 35

Your ability to generalise experimental findings. If a study lacks external validity, the findings may hold true only for a specific experiment but little beyond that.

Question 36

Which three forms of generalisation does external validity involve?

Answer 36

1) Population generalisation: this form of external validity asks whether you can accurately generalise from what was learned with a specific collection of people in one study to a universe or population of people. To generalise the findings, you should specify the universe to which you wish to generalise.
2) Naturalistic generalisation: it asks whether you can generalise accurately from what you have learned in an artificially created setting to “real life” natural settings. Naturalistic generalisation involves two issues: mundane realism and reactivity, which I will ask you about later.
3) Theoretical generalisation: this asks whether you can accurately generalise from the concepts and relations in an abstract theory that we wish to a test to a set of measures and arrangements of activities in a specific experiment.

Question 37

Mundane realism

Answer 37

Considers the question ‘Is the experiment like the real world?’ For example, if you ask participants to memorise four-letter nonsense syllables, mundane realism would be stronger if you had them learn real-life factual information.

Question 38

Reactivity

Answer 38

The effect of people reacting because they are aware that they are in a study. Reactivity is most likely in which the research participants know an experimenter created the conditions and is observing their behaviours or responses. The Hawthorne effect is a specific kind of reactivity.

Question 39

Postexperiment interviews

Answer 39

At the end of an experiment, you should interview participants for 3 reasons. First, if you used deception, you must ethically debrief the research participants to explain the true purpose of the experiment and answer questions. Second, you can learn what participants thought and how their definitions of the situation affected their behaviour. Finally, you can explain the importance of not revealing the true nature of the experiment to other potential participants.