Discussion & Conclusions

32
1 Dr. McKirnan; Foundations of Research Discussion & Conclusions Methods & data Phenomenon Theory Hypothesis Results Basic research designs. Dr. David J. McKirnan, University of Illinois at Chicago, Psychology; [email protected] This is a PowerPoint show. Click through it by pressing any key. Focus & think about each point; do not just passively click. Note key words and phrases

description

Basic research designs. Phenomenon. This is a PowerPoint show. Click through it by pressing any key. Focus & think about each point; do not just passively click. Note key words and phrases. Theory. Hypothesis. Methods & data. Results. Discussion & Conclusions. - PowerPoint PPT Presentation

Transcript of Discussion & Conclusions

Page 1: Discussion & Conclusions

1Dr. McKirnan; Foundations of

Research

Discussion &Conclusions

Methods & data

Phenomenon

Theory

Hypothesis

Results

Basic research designs.

Dr. David J. McKirnan, University of Illinois at Chicago, Psychology; [email protected]

This is a PowerPoint show.

Click through it by pressing any key.

Focus & think about each point; do not just passively click.

Note key words and phrases

Page 2: Discussion & Conclusions

2Dr. McKirnan; Foundations of

Research

Discussion &Conclusions

Methods & data

Phenomenon

Theory

Hypothesis

Results

Basic research designs.

Want to print this file for taking notes? This file is now in your downloads folder in "show" format

(ppsx). To convert it to a printing format (pptx):

Click 'esc' to leave this file Open PowerPoint Under “file” click “open”, browse to this file, click “open” In the open file click “save as” and save as pptx.

To print in notes format: Go to “file” “print’. In the dialogue box click “print what?”. Click “Handouts (3 slides per page)”

Then, come back and re-run the show

Page 3: Discussion & Conclusions

3Dr. McKirnan; Foundations of

Research

Discussion &Conclusions

Methods & data

Phenomenon

Theory

Hypothesis

Results

Basic research designs.

This module addresses:Designs without a

control group

Variations on control group designs

The overall structure of an experiment

Page 4: Discussion & Conclusions

4Dr. McKirnan; Foundations of

Research

Psychology 242, Dr. McKirnan

Week 3; Experimental designs

Basic experimental designs

This module overviews the core elements of an experimental research design.

We will discuss “pre-experimental” designs

These typically have no control group or may use existing groups

They are often used in preliminary or exploratory research

“True” experiments have several key characteristics:

A control group

Random assignment of participants to groups

Standardized or uniform procedures for each group

Page 5: Discussion & Conclusions

5Dr. McKirnan; Foundations of

Research Experimental designs and validity

We will discuss internal and external validity.

Internal validity In experiments we manipulate (induce…) the Independent Variable.

We then measure the Dependent Variable.

Experimental hypothesis: the outcome (the level of the Dependent Variable) is caused by – and only by – the Independent Variable.

Internal validity: How confident are we that the outcome was due only to the Independent Variable.

Confound: A variable other than the IV that caused or influenced the result.

Did the participants in the experimental v. control groups differ on something other than the IV?

Were the procedures biased in some way…?Confound

Page 6: Discussion & Conclusions

6Dr. McKirnan; Foundations of

ResearchExperimental designs and validity

We will discuss internal and external validity.

External validity Experimental participants are a sample of the larger population.

The experimental manipulation attempts to accurately induce the Independent Variable.

The outcome measure represents the Dependent Variable.

The experiment is conducted in a specific physical or cultural setting.

External validity:

Does the research sample accurately represent the larger population?

Do the exp. manipulation and outcome measures accurately represent the concepts underlying the Independent & Dependent Variables?

Is the experimental setting representative of how these processes work in nature?

Page 7: Discussion & Conclusions

7Dr. McKirnan; Foundations of

Research External validity: summary

The study structure & context

The research

Setting:

The Dependent

Variable

The research Sample:

Is the sample representative of the larger population?

Is this typical of the natural

settings where the phenomenon

occurs?

Does the outcome measure represent

what we are trying to explain?

Does the experimental manipulation actually create the phenomenon you

are interested in?

The Independent

Variable

Page 8: Discussion & Conclusions

8Dr. McKirnan; Foundations of

Research Overview: Basic Designs “Pre-experimental” designs: no control group

Post-Test Only Design Pre- Post- Test Design

Group assignment

Pre-test Experimental manipulation

Outcome

Experimental Observe2TreatmentObserve1

Page 9: Discussion & Conclusions

9Dr. McKirnan; Foundations of

Research Basic Designs

“Pre-experimental” designs: no control groupPost-Test Only Design Pre- Post- Test Design

Group assignment

Pre-test Experimental manipulation

Outcome

Experimental Observe2TreatmentObserve1

True (or Quasi-)experimental designs with a control group

“After only” Control group design

Pre- Post- Group Comparisons

Control Observe2ControlObserve1

Page 10: Discussion & Conclusions

10Dr. McKirnan; Foundations of

Research Basic Designs

“Pre-experimental” designs: no control groupPost-Test Only Design Pre- Post- Test Design

Group assignment

Pre-test Experimental manipulation

Outcome

True (or Quasi-)experimental designs with a control group

“After only” Control group design

Pre- Post- Group Comparisons

Multiple group comparison

Experimental Observe1 Observe2

Experimental

Control

Observe1

Observe1

Treatment 2 Observe2

Observe2

Treatment 1

Control

Page 11: Discussion & Conclusions

11Dr. McKirnan; Foundations of

Research

“Pre-experimental” designsPost-Test Only Design

Treatment MeasureGroup

Only 1 group - typically an existing group: no selection or assignment occurs.

Experimental intervention (“Treatment”) may or may not be controlled by the researcher.

Use for naturally occurring or system-wide events (e.g., group trauma, government policy change, etc.).

Measurement may or may not be controlled by the researcher.

Measure1Treatment Measure1

Group

Only one group;• only group

available?• naturally

occurring intervention?

Measurements given to all participants at baseline & follow-up

All participants get the same treatment, which may or may not be controlled by the researcher.

Pre- Post- Test Design

Page 12: Discussion & Conclusions

12Dr. McKirnan; Foundations of

Research “Pre-experimental” Designs (2)

Allow us to study naturally occurring interventions.

Advantage of “Post-” & “Pre- Post-” Designs:

e.g., test scores before and after some school change,

Crime rates after a policy change, etc.

Having both Pre- and Post measures allows us to examine change.

Page 13: Discussion & Conclusions

13Dr. McKirnan; Foundations of

Research “Pre-experimental” Designs (2)

Disadvantage of “Post-” & “Pre- Post-” Designs:

Maturation: Participants may be older / wiser by the post-test

History; Cultural or historical events may occur between pre- and post-test that change the participants

Mortality: Participants may non-randomly drop out of the study

Regression to baseline: Participants who are more extreme at baseline look less extreme over time as a statistical confound.

Reactive Measurement: Scores may change simply due to being measured twice, not the experimental manipulation.

No control group = many threats to internal validity.

Page 14: Discussion & Conclusions

14Dr. McKirnan; Foundations of

Research

Experiments“After only” Control group design

Adds a control group. Either…

Observed Groups: Naturally occurring (e.g., Class 1. v. Class 2) or Self-selected (sought therapy v. did not…).

Assigned Groups:

Randomly assign participants to experimental v. control group, or

Match participants to create equivalent groups.

Measure Dependent Variable(s) only at follow-up.

Use experimental or standard measures (e.g., grades, census data, crime reports).

Experimental

Control

Treatment 2 Observe2

Observe2Control

Page 15: Discussion & Conclusions

15Dr. McKirnan; Foundations of

Research Advantages of experimental design

“After only” Control group design

Advantage: Lessens the likelihood of confounds or threats to internal validity.

Control group Random assignment

Disadvantage: Existing or self-selected groups may have confounds.

No baseline or pre- measure available: We cannot assess change over time. We cannot assess whether the groups are

equivalent at baseline.

Experimental

Control

Treatment 2 Observe2

Observe2Control

Page 16: Discussion & Conclusions

16Dr. McKirnan; Foundations of

Research Basic Designs: True experiments (2)

Pre- Post- Group Comparisons (most common study design)

Two groups:

Observed (quasi-experiment)

orAssigned

(true experiment).

Baseline (“pre-test”) measure of study variables and possible confounds.

Group 1

Group 2

Measure 1

Measure 1

Page 17: Discussion & Conclusions

17Dr. McKirnan; Foundations of

Research Basic Designs: True experiments (2)

Pre- Post- Group Comparisons (most common study design)

The group getting the experimental condition is contrasted with a control group..

Group 1

Group 2

Measure 1

Measure 1

Treatment Measure 2

Measure2

“Post-test” follow-up of dependent variable(s);

Simple outcome Change from

baseline.

Control

Page 18: Discussion & Conclusions

18Dr. McKirnan; Foundations of

Research Basic Designs: True experiments (2)

Pre- Post- Group Comparisons (most common study design)

Group 1

Group 2

Measure 1

Measure 1

Treatment Measure 2

Measure2

Advantages: Pre-measure assesses baseline level of Dependent Variable

Allows researcher to assess change

Can find matched pairs of participants and assign each to different groups (rather than random assignment).

Can assess whether groups are equivalent at baseline.

Disadvantage: Highly susceptible to confounds if using observed or self-selected groups.

Control

Page 19: Discussion & Conclusions

19Dr. McKirnan; Foundations of

Research

More Complex Experimental Designs

Multiple group comparison

3 (or more) groups

Typically formed by Random assignment.

Multiple experimental groups, e.g. Low drug dose, High drug dose, Placebo.

or Male therapist, Female therapist, Wait list control.

Group 1

Group 2

Group 3

Measure1

Measure1

Measure1

Treatment #2

Treatment #1

Control

Page 20: Discussion & Conclusions

20Dr. McKirnan; Foundations of

Research More Complex Experimental Designs

Multiple group comparison

Measure2Group 1

Group 2

Group 3

Measure1

Measure1

Measure1

Treatment #2 Measure2

Measure2

Treatment #1

Compare: Level 1 of independent

variable from Level 2 Either / both experimental

groups from control grp.

Control

Page 21: Discussion & Conclusions

21Dr. McKirnan; Foundations of

Research More Complex Experimental Designs

Multiple group comparison

Measure2Group 1

Group 2

Group 3

Measure1

Measure1

Measure1

Treatment #2 Measure2

Measure2

Treatment #1

Advantages: Test dose or context effects:

Drug doses, amounts of psychotherapy, levels of anxiety, etc. Increasing dose effect can be tested against no dose.

Diverse conditions to test 2nd hypotheses or confounds, e.g., therapy delivered by same sex v. opposite sex therapist.

Disadvantage:

More costly and complex.

Potential ethical problem with a “no dose” (or very high dose) condition.

Control

Page 22: Discussion & Conclusions

22Dr. McKirnan; Foundations of

Research

Core components of a research study

Participant Selection

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

We will use this framework to think about the basic elements of an experiment.

Who is in our research study?

How did we recruit or sample them?

We will have at least one Experimental Group and a Control Group.

How do we assign participants to be in one or the other?

What instructions do we give?

What experimental tasks will participants be performing?

What measures might we be taking?

Experimental & control groups get different conditions.

We hypothesize that this manipulation “causes” the outcome.

What outcomes are we measuring?

What is the experiment trying to explain?

Page 23: Discussion & Conclusions

23Dr. McKirnan; Foundations of

Research Experimental design overview

Participant Selection

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure Treatment Outcome

Group B Procedure Control Outcome

(Group C) (Procedure ) (Alternate Treatment?) (Outcome)

We recruit a sample of participants from the larger population.

We randomly assign them to groups to ensure the groups are equivalent at baseline.

Procedures for all groups should be exactly the same…

…except the experimental manipulation, i.e., the Independent variable.

Hypothesis: The outcome or Dependent Variable varies only by group.

Page 24: Discussion & Conclusions

24Dr. McKirnan; Foundations of

Research

Overview of true experimental designs

Participant Selection

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure Treatment Outcome

Group B Procedure Control Outcome

(Group C) (Procedure ) (Alternate Treatment?) (Outcome)

Experimental group

Control group

Page 25: Discussion & Conclusions

25Dr. McKirnan; Foundations of

Research

Overview: experimental designs

Participant Recruitment

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure A Treatment Outcome

Group B Procedure A Control Outcome

Group C Procedure A Alternate Treatment (?) Outcome

Does the sample well represent

the population?

External validity

• Was recruitment biased?

• Is the sample size large enough?

What form of validity is threatened by sample

bias?

What can we do to avoid that threat?

Random selection

Page 26: Discussion & Conclusions

26Dr. McKirnan; Foundations of

Research

Overview: experimental designs

Participant Recruitment

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure A Treatment Outcome

Group B Procedure A Control Outcome

Group C Procedure A Alternate Treatment (?) Outcome

Does the sample well

represent the population?

External validity

Random selection

Are the groups equal at

baseline?

Internal validity

Random Assignment

• Did participants Self-select (in or out) of the study?

• Did we use existing groups?

Validity Threat?

Solution?

Page 27: Discussion & Conclusions

27Dr. McKirnan; Foundations of

Research

Overview: experimental designs

Participant Recruitment

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure A Treatment Outcome

Group B Procedure A Control Outcome

Group C Procedure A Alternate Treatment (?) Outcome

Does the sample well

represent the population?

External validity

Random selection

Are the groups equal at baseline?

Internal validity

Random Assignment

Procedures the same for all groups?

Internal validity:

Lack of confounds

• Do both groups have the same expectations?

• Are participants (and researchers) really blind?

• Do we treat both groups the same?

Validity Threat?

Solution?

Page 28: Discussion & Conclusions

28Dr. McKirnan; Foundations of

Research

Overview: experimental designs

Participant Recruitment

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure A Treatment Outcome

Group B Procedure A Control Outcome

Group C Procedure A Alternate Treatment (?) Outcome

Does the sample well

represent the population?

External validity

Random selection

Are the groups equal at baseline?

Internal validity

Random Assignment

Procedures the same for all groups?

Internal validity:

Lack of confounds

Independent variable faithfully

reflects the construct?

External Validity

Correct IV?

• Does the operational definition really express the construct we are interested in?

• Have we given the correct dose of the IV?

Validity Threat?

Solution?

Page 29: Discussion & Conclusions

29Dr. McKirnan; Foundations of

Research

Overview: experimental designs

Participant Recruitment

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure A Treatment Outcome

Group B Procedure A Control Outcome

Group C Procedure A Alternate Treatment (?) Outcome

Does the sample well

represent the population?

External validity

Random selection

Are the groups equal at baseline?

Internal validity

Random Assignment

Procedures the same for all groups?

Internal validity:

Lack of confounds

Independent variable faithfully

reflects the construct?

External Validity

Correct IV?

Internal Validity:

Statistical testing

Groups really

different at outcome?

• Is any difference we see actually statistically significant (reliable & meaningful)?

• …or it is due to chance alone..

Validity Threat?

Solution?

Page 30: Discussion & Conclusions

30Dr. McKirnan; Foundations of

Research

Overview: experimental designs

Participant Recruitment

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Sample

Group A Procedure A Treatment Outcome

Group B Procedure A Control Outcome

Group C Procedure A Alternate Treatment (?) Outcome

Does the sample well

represent the population?

External validity

Random selection

Are the groups equal at baseline?

Internal validity

Random Assignment

Procedures the same for all groups?

Internal validity:

Lack of confounds

Independent variable faithfully

reflects the construct?

External Validity

Correct IV?

Internal Validity:

Statistical testing

Groups really different at outcome?

Page 31: Discussion & Conclusions

31Dr. McKirnan; Foundations of

Research

Experimental design key elements Control group v. non-controlled designs Threats to internal validity:

Maturation History Mortality Regression to baseline Reactive Measurement

“Pre-experimental” designs Pre-post designs Multiple group comparisons

Overview: key terms

Page 32: Discussion & Conclusions

32Dr. McKirnan; Foundations of

Research

Overview: experimental designs

Participant Recruitment

Participant Assignment

Experimental Procedures

Experimental Treatment or Manipulation

Results

Does the sample well

represent the population?

External validity

Are the groups equal at baseline?

Internal validity

Procedures the same for all groups?

Independent variable faithfully

reflects the construct?

Groups really different at outcome?

External validity

Internal validity

Internal validity