VALIDITY

Overview

A study is valid if its measures actually measure what they claim to, and if there are no logical errors in drawing conclusions from the data. There are a great many labels for different types of validity, but they all have to do with threats and biases which would undermine the meaningfulness of research. Be less concerned about defining and differentiating the types of validity. Researchers disagree on the definitions and types, and yes, they do overlap. Be more concerned about the types of questions the researcher should ask about the validity of research: researchers agree on the importance of the questions.

The full content is now available from Statistical Associates Publishers. Click here.

Below is the unformatted table of contents.

Table of Contents

Overview 5
Historical background 5
Construct validity 7
Convergent validity 7
Internal consistency validity 7
Criteria 8
Common method variance 9
Criterion validity 9
Discriminant validity 12
Correlational Methods 12
Factor Methods 13
AVE Method 13
Structural equation modeling methods 14
Multi-trait multi-method (MTMM) methodologies 14
Content validity 15
Example 16
Internal validity 16
Hawthorne effect (experimenter expectation) 16
Mortality bias 17
Selection bias 17
Evaluation apprehension 17
Compensatory equalization of treatments 17
Compensatory rivalry 17
Resentful demoralization 18
Treatment imitation or diffusion 18
Unintended treatments 18
Instrumentation change 18
History (intervening events) 18
Maturation 19
Mortality 19
Regression toward the mean 19
Test experience 19
Statistical validity 19
Reliability 20
Type I Errors and Statistical Significance 20
Type II Errors and Statistical Power 20
Fallacies of aggregation 21
Strategies 21
Interaction and non-linearity 22
Causal ambiguity 22
Validity Checklist 23
Bibliography 25