What is the conceptual definition of validity?
A valid test does what it was designed to do and measures what it was designed to measure.
What are the four main types of validity?
1️⃣ Face
2️⃣ Content
3️⃣ Criterion (concurrent & predictive)
4️⃣ Construct.
What does assessing validity mean in general?
It examines how well a measurement tool actually measures what it intends to measure.
What is face validity?
How well an instrument appears, on its face, to test what it is supposed to test.
Who determines face validity?
Typically, the respondents or anyone reviewing the tool—asking, “Does this look like it measures what it should?”
Give an example of face validity.
A nutrition-knowledge test reviewed by others to see if it appears to measure nutrition knowledge.
What is content validity?
The extent to which items represent all relevant aspects of the concept being measured.
How is content validity established?
By consulting experts to verify that all important areas are covered.
Define criterion validity.
The ability of a tool to predict or align with results from an external, valid criterion or gold standard.
What are the two sub-types of criterion validity?
- Concurrent validity (present)
- Predictive validity (future).
What is the key difference between parallel-form reliability and criterion validity?
Reliability → two forms of the same test on the same group; Validity → comparing test results to a different external criterion (gold standard).
What does construct validity assess?
How well a tool measures an underlying abstract concept (e.g., “healthy eating”).
What makes construct validity difficult?
Abstract constructs require multiple approaches and comparisons.
Name two types of construct validity.
- Convergent validity – similar constructs correlate.
- Discriminant validity – unrelated constructs do not correlate.
Give examples of each Convergent and Discriminant Validity
Convergent: Healthy eating tool vs Canada’s Food Guide → similar scores.
Discriminant: Healthy eating tool vs financial knowledge tool → different scores.
What is absolute validity?
When a tool is compared to a true gold standard that exactly measures the intended construct.
List three common approaches to establish validity.
1️⃣ Correlate new test with an established test.
2️⃣ Show people with and without certain traits score differently.
3️⃣ Ensure test tasks align with the theory underpinning the construct.
Why is it hard to measure change over time?
Requires valid & reliable tools; initial levels affect results (floor/ceiling effects); practice and natural changes can skew results.
What are floor and ceiling effects?
When scores cannot go lower or higher due to test limits, masking true change.
-
Importance of Research for Professional Practices8
-
Finding the Evidence18
-
Research Dissemination25
-
Importance of Sampling22
-
Measurement Reliability22
-
Reliability Validity19
-
Descriptive Statistics30
-
Inferential Statistics Part 130
-
Inferential Statistics Part 221
-
Ethics36
-
Qualitative Research39
-
Cross Section + Survey Research30
-
Case Control Studies26
-
Cohort Studies16
-
Animal Models in Human Nutrition15
-
Experimental Design pt.117
-
Experimental Design Pt.218
-
Review Studies & Meta-Analysis19
