Unit 8: Group Experimental Research: Single-Factor Designs

Question 1

true experiment

Answer 1

A true experiment in which the researcher has complete control over the independent and extraneous variables, so that a cause-effect relationship can be established.

Question 2

quasi experiment

Answer 2

A true experiment in which the researcher has less than complete control (i.e. the independent variable is a participant characteristic)

Question 3

factor

Answer 3

the independent variable

Question 4

level

Answer 4

the particular value of the independent variable

Question 5

condition

Answer 5

a broad term used to discuss the independent variable(s)

Question 6

treatment

Answer 6

another word for condition

Question 7

between-subjects design

Answer 7

each subject is only exposed to one level of the treatment condition

Question 8

within-subjects design

Answer 8

each subject is exposed to every treatment condition

Question 9

order effect

Answer 9

within subjects: changes in behaviour resulting from the order of the conditions - ex. participants getting tired, bored, more experienced

Question 10

sequence effect

Answer 10

within subjects: effect that results from interaction between the conditions - they have different effects depending on what order they come in

Question 11

block randomization

Answer 11

control procedure in which the order of the conditions are randomized but with each presented once before any are presented a second time. Useful if you want to present conditions multiple times, and are using multiple sessions.

Question 12

Counterbalancing

Answer 12

conditions are presented in one order the first time, and the opposite the second time

Question 13

Define true experiment

Answer 13

A true experiment that shows a cause-effect relationship between the independent and dependent variables.

• researcher has complete control over the independent variable
• random assignment of P to control and experimental groups

Question 14

Describe the two basic elements of good experimental design.

Answer 14

1. presence of a control group or condition

2. random assignment of P. In single-subject, multiple conditions should be random or counterbalanced

Question 15

What are within-subject designs? What is the basic strategy for achieving control?

Answer 15

Subject acts as their own control (pretreatment baseline is the control condition).
Control of order effects and sequence effects within (ideally) or between subjects.
Better ability to detect true differences.

Question 16

How are order effects and sequence effects different?

Answer 16

Order effects are more general - the conditions can go in any order and the same influence will be exerted on them (things like fatigue, learning).
Sequence effects are interaction between the conditions themselves.

Question 17

How do you control for order and sequence effectswithin subjects?

Answer 17

Counterbalancing: ensuring that each condition appears in the ordinal position an equal number of times.
Randomization can be used when the sample is large enough that results of one subject’s sequence effects are unlikely to have an influence on the end outcome.

Question 18

When is reverse counterbalancing ineffective in controlling for order effect?

Answer 18

• when relatively few P will be tested
• when you have several conditions that can be presented only a few times
• works well when you think the confounding variables will act in a linear manner over conditions

Question 19

How do you control for order and sequence effects within groups?

Answer 19

1. counterbalance within the group by presenting each condition combination an equal number of times
   Problem: as the number of conditions increases, the number of combinations increases mathematically.
2. control for order effects but not sequence effects if you give up the condition that every condition follow every other an equal number of times.
   Latin square

Question 20

Latin Square

Answer 20

Each P gets a different order of conditions. Order is controlled for, but not sequence.
Permits smaller number of Pp.

Question 21

Balanced Latin Square

Answer 21

in each set, each condition is immediately preceded by a different condition

Question 22

What is complete counterbalancing? What does it control for? What is its greatest disadvantage?

Answer 22

Complete counterbalancing is a technique in single-factor design that controls for order and sequence effects.
It’s biggest disadvantage is that the more conditions, the exponentially more combinations or sets there are.

Question 23

What are between-subject designs? Explain the basic strategy for achieving control.

Answer 23

In between-subjects designs, each P only experiences one condition.
Control is achieved by using a control group.

Question 24

When are between-subjects designs preferred over within-subjects designs?

Answer 24

Between subject designs are preferred when P can’t be their own controls because of carry-over effects between conditions (experiencing one will effect experience of all of the others).

Question 25

Describe three designs to avoid in research, and give reasons for avoiding them.

Answer 25

1. One-group post-test design - measures one group, only after treatment. No control or baseline data=no comparison to demonstrate the effect of the treatment. Internally invalid, too many variable uncontrolled.
2. Post-test only design - using nonequivalent control/experimental groups (not randomly assigned) - too many potential confounding variables - results could be treatment or could be inherent differences.
3. One-group pre-test/post-test design - measures a single group before and after the treatment. too many variables uncontrolled for.