Single Factor Designs Unit 8

Question 1

What is the purpose of a true experiment?

Answer 1

To test whether the independent variable is the cause of any change in the dependent variable

Question 2

In a TRUE experiment has COMPLETE control. What dose that mean? (entail)

Answer 2

1. The experimenter can manipulate the independent variables
2. Extraneous variables are controlled so that any observed effects can be attributed to the independent variable

–> this is done by randomly assigning research subjects to different experimental groups

Question 3

What is it called when the experimenter does NOT have complete control?

Answer 3

Quasi-experiment

Question 4

What is a single-factor design?

Answer 4

When only one independent variable is manipulated

Question 5

What is an advantage of between-subject designs?

What is a disadvantage of between-subject designs?

How to overcome?

Answer 5

A: One treatment will not contaminate the other because each subject receives only one treatment

DA: Lower ability to detect real differences between the groups because of the variability among individuals

Overcome: Matching can be used to match subjects on scores of variables that are likely to effect the dependent variable

Question 6

What are 2 types of single-factor designs?

Answer 6

1. Between-subjects factorial design: subject is exposed to one treatment condition
2. Within-subjects factorial design: subject is exposed to every treatment condition
   * *Preferred over between-subjects!! because of its ability to detect any real differences

Question 7

What are 2 basic types of between-subjects? And define them.

Answer 7

1. After-only design: the dependent measures of a experimental group are compared with a control group only after the TREATMENT has been given
2. Before-after design: subjects that are randomly assigned are measured on the dependent variable both BEFORE and AFTER treatment has been given

Question 8

What is an advantage of within-subject designs?

Answer 8

It requires only a small number of subjects and each subject serves as his/her own control - the ability to detect small differences increases

Question 9

2 types of carryover effects with within-subject designs?

Answer 9

1. Order effect: refers to subjects getting better with practice or bored with the task (changes in the subjects performance)

Solution: Counterbalancing

2. Sequence effect: effect of one treatment on another treatment differs depending on which treatment comes first (changes in the subjects performance as a result of interactions among the condition is repeated)

**counterbalancing cannot fix this solution

Question 10

Define and distinguish the terms FACTOR, LEVEL and CONDITION

Answer 10

Factor - independent variable
ex) new medication

Level - particular value of an independent variable
ex) 3 pills taken a day

Condition - a group or treatment in an experiment
ex) 4 pills a day experimental condition

Question 11

What is the basic strategy for achieving control in WITHIN-SUBJECTS

Answer 11

Counterbalancing - this is done by arranging that subjects experience the various conditions in different orders

Question 12

What is counterbalancing? What does it control for? Disadvantage?

Answer 12

Counterbalancing within a group occurs when each condition occurs an equal number of times in each rank order position AND follows every other condition an equal amount of times (ABBA or ABCCBA)

You control for ordering sequence within a group of subjects

Disadvantage - as the number of conditions increases the number of orders required increases geometrically

Question 13

What is the basic strategy for achieving control in BETWEEN-SUBJECTS

Answer 13

The conclusion of a control group(s) that are not exposed to the independent variable of the independent variables

Question 14

When are between-subjects preferred over within-subjects?

Answer 14

Sometimes carryover effects will make a between-subjects more necessary

Question 15

What are 3 designs to avoid in research?

Answer 15

1. One group post-test only design - research design that measures the behavior of a single group after they are given treatment
2. Post-test only design with non-equivalent control groups - where subjects are not randomly selected from the same population
3. One group pretest post-test design - design that measures the behavior of a single group before and after treatment

Question 16

Latin Square Technique

Answer 16

Subjects S1–S4 together constitute a balanced Latin square, because each condition occurs once in each ordinal position and follows every other condition once

ex) JKLM –> KLMJ –> LMJK –> MJKL

Question 17

What is a mixed factorial design

Answer 17

• Designs containing at least one variable that is presented in a within-subjects fashion and one other variable that is presented in a between-subjects fashion
• A factorial design offers an opportunity for design not available in single- factor experiments, namely combining within-subject variables and between- subject variables in a single experiment.
• Mixed designs are also used when using the same participants in all conditions is possible but not desirable.

Question 18

Difference between true experiment and quasi-experiment?

Answer 18

True experiments, in which all the important factors that might affect the phenomena of interest are completely controlled, are the preferred design. Often, however, it is not possible or practical to control all the key factors, so it becomes necessary to implement a quasi-experimental research design.

In a true experiment, participants are randomly assigned to either the treatment or the control group, whereas they are not assigned randomly in a quasi-experiment