Top Banner
Designing Designs for Research
43

Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

Dec 21, 2015

Download

Documents

temporal precedence

designs cause u

measurement slide

argument slide

maturationthreat slide

research slide

threats u

outcome u

Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

Designing Designs for Research

Page 2: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

Designing Designs

How do you establish causecause? How do you minimize threats minimize threats to

validity? How do you construct construct a design? What is a goodgood design?

Page 3: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal PrecedenceTemporal Precedence

Page 4: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

CauseCause EffectEffectthenthen

Time

Page 5: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

CauseCause EffectEffectthenthen

Time

Why is this important?Why is this important?

Page 6: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

CauseCause EffectEffectthenthen

Time

Why is this important?Why is this important?

Cyclical functionsCyclical functions

Inflation

Unemployment

Page 7: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal PrecedenceTemporal Precedence

Covariation of Cause and EffectCovariation of Cause and Effect

CauseCause EffectEffectthenthen

TimeTime

Page 8: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

Covariation of cause and effectCovariation of cause and effect

CauseCause EffectEffectthenthen

timetime

If X, then Y.If X, then Y.If If notnot X, then X, then notnot Y. Y.

Page 9: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

Covariation of cause and effectCovariation of cause and effect

CauseCause EffectEffectthenthen

timetime

If X, then Y.If X, then Y.If If notnot X, then X, then notnot Y. Y.

If program given, then outcome observed.If program not given, then outcome not observed.

Page 10: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

Covariation of cause and effectCovariation of cause and effect

CauseCause EffectEffectthenthen

timetime

If X, then Y.If X, then Y.If If notnot X, then X, then notnot Y. Y.

If program given, then outcome observed.If program not given, then outcome not observed.

If more of program, then more of outcome observed.If less of program given, then less of outcome observed.

Page 11: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

Covariation of cause and effectCovariation of cause and effect

No alternative explanationsNo alternative explanations

CauseCause EffectEffectthenthen

timetime

If X, then Y.If X, then Y.If If notnot X, then X, then notnot Y. Y.

Page 12: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

Covariation of cause and effectCovariation of cause and effect

No alternative explanationsNo alternative explanations

CauseCause EffectEffectthenthen

timetime

If X, then Y.If X, then Y.If If notnot X, then X, then notnot Y. Y.

ProgramProgram OutcomeOutcomecauses?

Page 13: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Establish Cause?

Temporal precedenceTemporal precedence

Covariation of cause and effectCovariation of cause and effect

No alternative explanationsNo alternative explanations

CauseCause EffectEffectthenthen

timetime

If X, then Y.If X, then Y.If If notnot X, then X, then notnot Y. Y.

ProgramProgram OutcomeOutcomeCauses?

Alternativecause

Alternativecause

Alternativecause

Alternativecause

Page 14: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

In Typical Outcome Evaluation

Is taken care of because you intervene before you measure outcome

Is taken care of because you control the intervention

Is the central issue of internal validity -- usually taken care of through your design

Temporal Precedence

Covariation of Cause and Effect

No Alternative Explanations

Page 15: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By argument By measurement or observation By design By analysis By preventive action

Page 16: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By argumentBy argument

Page 17: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By argumentBy argument

Simply say the threat isn’t reasonable.

Page 18: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By measurementBy measurement

Page 19: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By measurementBy measurement

Measure that the threat didn’t happen.

Page 20: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By designBy design

R O X OR O X O

MaturationMaturationthreat?threat?

Page 21: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By designBy design

Add a group to control for the threat.

R O X OR O OR O X OR O O

To address aTo address amaturationmaturation

threatthreat

Page 22: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By analysisBy analysis

Mortality threat : Are your dropoutsMortality threat : Are your dropoutsdifferent from those retained indifferent from those retained in

your study?your study?

Page 23: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By analysisBy analysis

Show through analysis that the threat isn’t plausible.

Retained Drop-Out05

1015202530

Retained Drop-Out

PretestPretestPretestmeansmeans

Page 24: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By preventive actionBy preventive action

Rivalry?

Page 25: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Minimize Threats to Validity?

By preventive actionBy preventive action

Don’t allow the threat to happen in the first place.

Rivalry

Get programGet programnext semesternext semester

Page 26: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Across time Across programs Across observations Across groups

Expand...

Page 27: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Start with the simplest design.

Page 28: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

X OX O

Start with the simplest design.

Page 29: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across timetime..

Page 30: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across timetime..

O O X OO O X O

O X O O OO X O O O

Page 31: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across programsprograms..

Page 32: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across programsprograms..

O X1 OO X2 OO X3 O

O X1 OO X2 OO X3 O

ProgramProgramvariationsvariations

Page 33: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across observationsobservations..

Page 34: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across observationsobservations..

O1 X O1,2,3

O1 O1,2,3

O1 X O1,2,3

O1 O1,2,3

MeasurementMeasurementvariationsvariations

Page 35: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across groupsgroups..

R O X OR O OR O X OR O O

Page 36: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across groupsgroups..

R O X OR O OR O X OR O O

R O X OR O OR O X OR O OAdd aAdd a

replicate.replicate.

Page 37: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across groups and timegroups and time..

R O X OR O O

N O

R O X OR O O

N O

Page 38: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across groups and timegroups and time..

R O X OR O O

N O

R O X OR O O

N O

Page 39: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

Expand across groups and timegroups and time..

R O X OR O O

N O

R O X OR O O

N O

TimeTime

GroupsGroups

Page 40: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

X OStart

Page 41: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

X OStart

Expand

R O X O O

R O O X O

N O X O

N O O

Page 42: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

How Do You Construct a Design?

X OStart

Expand

R O X O O

R O O X O

N O X O

N O O

R O X O

R O O

N O OContract

Page 43: Designing Designs for Research. Designing Designs cause u How do you establish cause? minimize threats u How do you minimize threats to validity? construct.

What Is a Good Design?

Theory-grounded Situational (adapted) Feasible Redundant Efficient


Related Documents
Standardizing Security Processes to Minimize Mobile Threatsa248.e.akamai.net/f/248/3214/1d/ · There are also new threats that are focused on attacking via Bluetooth on mobile devices.

Standardizing Security Processes to Minimize Mobile...

Category: Documents
Threat Modeling and Analysis - KAMM...Threat Modeling and Analysis ... • Point Threats • Systems Threats • Distal Threats • Proximal Threats • Terminal Threats • Pathways

Threat Modeling and Analysis - KAMM...Threat Modeling and...

Category: Documents
ANOMALI AND SIXGILL DARKFEED: NEXT-GEN THREAT … · threats in advance, prevent incidents, and minimize attack surface. Security-centric approach: We treat the security of data with

ANOMALI AND SIXGILL DARKFEED: NEXT-GEN THREAT … ·...

Category: Documents
CONVENCIÓN SOBRE EL COMERCIO INTERNACIONAL DE … · threats for these species and development of a national Action Plan with proposals on how to avoid or minimize these threats.

CONVENCIÓN SOBRE EL COMERCIO INTERNACIONAL DE … ·...

Category: Documents
MDM Review 2009 12.14.09 Jason Sanders. Outline Measures of frequency Measures of association Study designs INTERMISSION Threats to study validity Defining.

MDM Review 2009 12.14.09 Jason Sanders. Outline Measures of....

Category: Documents
Fractional Factorial Experiment Designs To Minimize ...

Fractional Factorial Experiment Designs To Minimize ...

Category: Documents
Topology optimization process for new designs of ......topology optimization problem. The topology optimization problem was defined to minimize the compliance of the structure with

Topology optimization process for new designs of...

Category: Documents
Assessment of Malingering with Simulation Designs: Threats to External Validity

Assessment of Malingering with Simulation Designs: Threats.....

Category: Documents
CHAPTER 2 CONTROVERSIAL ISSUES IN GENE RESEARCH · equal vigor, to minimize the threats such developments pose.” DNA testing: Advantages and Disadvantages The ongoing project to

CHAPTER 2 CONTROVERSIAL ISSUES IN GENE RESEARCH · equal...

Category: Documents
10 Steps for Securing Your Digital Identity...1. Identify 10 digital security risks. 2. List tools and best practices to minimize security threats. Identify your vulnerabilities –within

10 Steps for Securing Your Digital Identity...1. Identify 10...

Category: Documents
A Bestiary of Experimental and Sampling Designs. REMINDERS The goal of experimental design is to minimize the potential “sources of confusion” (Hurlbert.

A Bestiary of Experimental and Sampling Designs. REMINDERS.....

Category: Documents
Advanced Cyber Illness Treatmant - IT klinika...Advanced Threat Protec0on Block, isolate and remove the advanced persistent threats Advanced Threat Protec0on Minimize environmental

Advanced Cyber Illness Treatmant - IT klinika...Advanced...

Category: Documents