What is internal reliability?
The consistency within a test, meaning all parts measure the same thing.
What is external reliability?
The consistency of results over time or across researchers.
Types of external reliability?
Test-retest reliability (consistency over time)
Inter-rater reliability (consistency between observers)
How can reliability be improved?
Standardised procedures
Clear instructions
Controlled variables
Training observers
What is inter-rater reliability?
The extent to which different observers give similar ratings.
Strengths and weaknesses?
Increases objectivity
− Requires training → time-consuming
What is test-retest reliability?
Measuring consistency by repeating the test at a later time.
Strengths and weaknesses?
Shows stability over time
− Practice effects may affect results
What is split-half reliability?
Dividing a test into two halves and comparing results.
Strengths and weaknesses?
Quick way to assess internal consistency
− Halves may not be equivalent
What is internal validity?
The extent to which a study accurately measures what it intends to and establishes cause and effect.
What is external validity?
The extent to which findings can be generalised to other settings, people, or times.
What is researcher bias?
When the researcher’s expectations influence results.
What are demand characteristics?
Cues that cause participants to change behaviour based on perceived aims.
What is social desirability bias?
When participants give socially acceptable answers rather than truthful ones.
How can validity be improved?
Random allocation
Blind/double-blind procedures
Deception (to reduce demand characteristics)
Standardisation
Pilot studies
What is predictive validity?
The extent to which results predict future behaviour.
What is concurrent validity?
Comparing results with an existing, established measure.
What is face validity?
Whether a test appears to measure what it claims to.
What is content validity?
Whether a test covers all aspects of the construct being measured.
What is construct validity?
Whether the test truly measures the theoretical construct it intends to measure.
What is the relationship between reliability and validity?
A study must be reliable to be valid
But a study can be reliable without being valid
→ Consistency does not guarantee accuracy
-
milgram and Kohlberg34
-
research methods32
-
methodologies54
-
location of research16
-
sampling20
-
experimental design9
-
levels of measurement11
-
graphical representation18
-
descriptive statistics11
-
inferential statistics24
-
reliability and validity22
-
ethics21
-
personal investigation x277
-
role of the scientific community in validating new knowledge12
