The Experiment Flashcards

0
Q

Quasi-Experiment

A

Cannot randomly assign people to the levels of the IV.
•Cannot control something of interest.
Ex: Drug exposure on a fetus.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
1
Q

True Experiments

A

Can randomly assign individuals to levels of the IV. (Random Assignment: every participant has an equal chance for being in the levels of the experiment.)
•Control everything
Ex: Alcohol and reaction time.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Independent Variable

A

The one we believe is causing the change. (The group your in)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Levels of the Independent Varaible

A

The different values of an independent variable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Types of Experiments

A
  • Between Subjects Design

* Within Subjects Design

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Between Subjects Design

A

Groups of participants only receive one level of the IV.
•Different groups receive the different levels of the IV.
EX: Group 1: Alcohol
EX: Group 2: No Alcohol

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Within Subjects Design

A

(aka: Pretest-Posttest or Repeated Measures Design)
Subjects receive all the levels of the IV.
EX: Alcohol and reaction time
EX: No Alcohol and reaction time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Goal of the Experiment

A

Internal Validity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Internal Validity

A

The point of a true experiment.
•Ability to say that the manipulation of the IV caused the changes in the DV.
•Rule out extraneous (confounding) variables: something else that could be causing the changes noted.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Threats to Internal Validity in Between Subjects Designs (aka: Pretest-Posttest or Repeat Measures Design)

A
  1. Selection
  2. Selection by Maturation
  3. Mortality
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Threats to Internal Validity in Between Subject Designs due to Selection

A

Where the groups are equivalent before the study began. Self-selection threat.
Ex: Age and Political Views: How people feel about a topic comparing older and younger people.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Threats to Internal Validity in Between Subjects Design due to Selection by Maturation

A

(Maturation: the individual is developing and changing.)
Asking whether your two groups would have naturally grown apart even without the treatment.
•Weren’t equal to begin with and they would have grown apart anyway.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Threats to Internal Validity in Between Subjects Designs due to Mortality

A

Dropout rates or death.

More people dropout of one group than another.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Controlling Threats to Internal Validity in Between Subjects Designs

A
  • Random assignment

* Matching

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Random Assignment

A

every person has an equal chance.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Matching

A

Make samples equivalent in some way on important variables.

EX: Income or Age

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Threats to Internal Validity in Within Subjects Designs

A
  1. Maturation
  2. History
  3. Instrumentation
  4. Mortality
  5. Regression to the Mean
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Threats to Internal Validity in Within Subjects Designs due to Maturation

A

Growing up or changing.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Threats to Internal Validity in Within Subjects Designs due to History

A

Could other events in the participants lives have caused the pretest-posttest difference.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Threats to Internal Validity in Within Subjects Designs due to Instrumentation

A

Was the same instrument used in the pretest as in the posttest.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Threats to Internal Validity in Within Subjects Designs due to Mortality

A

Die or Dropout. Start and end with the same amount of participants.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Threats to Internal Validity in Within Subjects Designs due to Regression to the Mean

A

Statistical phenomenon that extreme scores are unlikely to occur repeatedly.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Additional Threats to Internal Validity in Within Subjects Design due to Carryover Effects

A

The effect of one treatment persists to influence the participants response to the next treatment.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Additional Threats to Internal Validity in Within Subjects Design due to Practice Effects

A

Similar to Maturation = Growing up or changing.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Additional Threats to Internal Validity in Within Subjects Design due to Order Effects
The position of a treatment in a series determines in part the participants response. EX: Brush teeth then drink orange juice versus drinking orange juice then brushing teeth.
25
Counterbalancing in Repeated Measures/Within Subjects Design
Presenting different treatment sequences.
26
Within Subject Counterbalancing (Participants)
The presentation of different treatment sequences to the same participant (subject). Ex: Coke before Pepsi than Pepsi before Coke: Do you like Coke or Pepsi better?
27
Within Subject Counterbalancing
1. Obtrusive Observation 2. Resentful Demoralization 3. Compensatory Rivalry 4. Treatment Contamination
28
Within-Subject Counterbalancing: | Obtrusive Observation
(Observable, reactance) | Participants react differently because of the presence of the researcher.
29
Within-Subjects Counterbalancing: | Resentful Demoralization
If control groups are given boring experiences they may perform extremely low. Ex: Gate classes versus regular classes.
30
Within-Subjects Counterbalancing: | Compensatory Rivalry
Sometimes control groups work extra hard to compensate for weaker treatment. Underdog Ex: Bell shaped curve, there are few extremes.
31
Within-Subjects Counterbalancing: | Treatment Contamination
Participants in different groups talk to each other and mess up the manipulation of the IV.
32
Participant as Extraneous Variable
1. Characteristics of the Experimenter 2. Good Subject Effect 3. Screw-You Effect 4. Evaluation Apprehension (Social Desirability) 5. Test Sophistication 6. Research Sophistication
33
Participant as Extraneous Variable: | Characteristics of the Experimenter
Sometimes participants react differently due to the way people look or act. Ex: Wearing a Uniform
34
Participants as Extraneous Variable: | Good Subject Effect
Participants try to figure out what they think they are suppose to do and then do it.
35
Participants as Extraneous Varaible: | Screw-You Effect
Subjects deliberately undermine the study. | EX: Sex: Male or Female? __A lot!
36
``` Participants as Extraneous Variable: Evaluation Apprehension (Social Desirability) ```
Participants are uncomfortable answering certain questions so they use social desirability response set.
37
Participants as Extraneous Variable: | Test Sophistication
Some people learn to be good test takers.
38
Participants as Extraneous Variable: | Research Socphistication
When participants guess the nature of deception or guess at the hypotheses.
39
Participants as Extraneous Variable: | How Do I Fix It?
Demand Characteristics | Obtrusive Observation
40
Demand Characteristics
Blind or double-blind or placebo: where the researchers, or the participants, or both don't know what level of the IV they are experiencing.
41
Participant as Extraneous Variable: | Obtrusive Observation
Unobtrusive observation: If we are changing peoples' behavior because they know they are being watched. The others? You do your best.
42
Experimenter as an Extraneous Variable
1. Observer Differences Effect 2. Interpreter Effects 3. Intentional Effects 4. Biosocial Effect 5. Psychosocial Effect 6. Situational Effect 7. Modeling Effect
43
Experimenter as an Extraneous Variable: | Observer Differences Effect
Systematic observation errors. Experimenter themselves become a confounding error. Ex: One experimenter starts the stop watch.
44
Experimenter as an Extraneous Variable: | Interpreter Effect
Systematic interpretive errors. | Ex: Aggression in apes: one experimenter calls things aggressive.
45
Experimenter as an Extraneous Variable: | Intentional Effect
Deliberate dishonesty or sloppiness in data collectors.
46
Experimenter as an Extraneous Variable: | Biosocial Effect
Demographic or biological characteristics of the data collectors (researchers) the effect the participants responses or vice versa.
47
Experimenter as an Extraneous Variable: | Psychosocial Effect
Data collector's interpersonal styles affect participant responses. Ex: Anxiety study: by highly anxious collector.
48
Experimenter as an Extraneous Variable: | Situational Effect
Results are unique to the situation under which the data are collected.
49
Experimenter as an Extraneous Variable: | Modeling Effect
Researchers offer sample answers or demonstrate a procedure and are then repeated by the participants.
50
Counterbalancing in Repeated Measures (Within Subjects) Design: Within-Group Counterbalancing
•Split up the sequences across the participants in our groups. Different because: Not everyone sees all the treatments. •Randomly assign half to have Coke-Pepsi. •Half to have Pepsi-Coke.
52
Complete Counterbalancing (Best Way) Controls for All
* n! (n factorial) * 3 levels * (3)(2)(1) = 6 need at least 6 participants or more in sixes.
53
Incomplete Counterbalancing
Some but not all sequences | •Randomly chose the first sequence and then rotate.
54
Requirements for Complete Counterbalancing
•Each Treatment must be: •Presented to each participant an equal # of times. •Occur an equal # of times at each testing or practice 1 time. •Precede and follow each of the other treatments an equal # of times. Ex: # of times Coke before Pepsi after Select, etc.
55
Internal Validity - Experimenters and Participants
* Demand Characteristics | * Experimenter Drift
56
Participant as Extraneous Variable: | Demand Characteristics
Participants themselves become extraneous, overt or subtle cues to participants on how they should behave. Ex: Predictive Horse
57
Participant as Extraneous Variable: | Experimenter Drift
There's a gradual change in how the subjects are treated over the course of the study.
58
Participant as Extraneous Variable: | How do I fix it?
* Observer and Interpreter Effect | * The others
59
Participant as Extraneous Variable: How do I fix it? | Observer and Interpreter Effect
Inter-Rater Reliability
60
Participant as Extraneous Variable: How do I fix it? | The Others
Blinding, standardization of instructions and procedures, and training.
61
Experimenter as an Extraneous Variable
Rosenthal Effect •Maze "Bright" vs. Maze "dull" •Intellectual Bloomers
62
Rosenthal Effects
The experimenter's preconceived idea of appropriate responding influences the treatment of participants and their behavior (experimenter expectancies)
63
Rosenthal Effect: | Maze vs Maze
Maze "Bright" vs. Maze "Dull": | Heterogeneous rats, randomly assign to two boxes.
64
Rosenthal Effects: | Intellectual Bloomers
•Intellectual Bloomers: Go into public school and randomly select 7 students, lie to teachers that they will have an intellectual growth spurt. End of year they bloom.