Week 5 (Standardised Measures) Flashcards
What does reliability mean psychometrics
Is the measure as free as possible from random error
What does validity mean psychometrics
Are we measuring what we think we’re measuring
What does unidimensionality mean psychometrics
Are we measuring just the one thing we want to measure, or have we ended up measuring other things too
What does discrimination mean psychometrics
How well do our items distinguish between levels f the thing we’re measuring
What does equivalence mean psychometrics
Does this measure perform the same way for different groups of people (e.g, teenagers and adults)
What does norm-referencing mean psychometrics
How are scores distributed the population.
Difference between random and systematic errors
Systematic errors do not cancel each other out, they accumulate over time
How to reduce random error
-Repeat measurements and average them (though isn’t simple for psychological variables)
How to reduce systematic error
-Use multiple measurements, each with different downsides
-That way the variable of interest is measured consistently, but the ‘noise’ is not
-This is why psychological instruments tend to take the form oof questionnaires rather than single questions.
Reliability vs validity
Reliability: A measure is accurate and consistent
Validity: Measures what you think its measuring
Types of reliability
-Test-retest
-Parallel form reliability
-Internal consistency
Test retest reliability
-If I measure your extraversion today, will it be the same as when I measured it yesterday
Parallel form reliability
Two alternative forms of the same standardised measure
Reduces risk of learning effects over time
Internal consistency reliability
-Are all the items doing just as good a job as one another of measuring the psychological construct of interest.
-A sub scale should be unidimensional, so we look at whether every item on the sub scale measures the same thing
-Measured with cronbach’s alpha, between 0-1, anything above 0.7 indicates reliability.
Test retest reliability pros and cons
PROS
-Demonstrates the measure s temporally stable
CONS
-Based on a total score (items could be completely unrelated)
-What about emotion or motivation
-How long between testing sessions
Split-half technique
Quantifies internal consistency, split a set of items in half and check whether both halves correlate
Internal consistency reliability pros and cons
PROS
-It’s essential poor internal consistency can only be due to items measuring different things
-Rubbish in, rubbish out
CONS
-If you increase the number of items, you increase Cronbach’s alpha- so exercise caution with very brief or very long measures
-Extremely high Cronbach’s alpha values might be ‘bloated’: too narrow a range of questions was asked.
Inference validity
Internal: Can the causal relationship that we established be explained by other factors?
External: Can we generalise to other situations, populations
Construct validity
-How well are we measuring what we want to measure
-Made up of translation and criterion validity
Translation validity
Is the operationalisation a good reflection of the construct?
Face: Does the instrument APPEAR to measure the construct
Content: To what extent does the items actually represent the whole of the construct dimension we are trying to measure
Criterion validity
How well does the measure agree with some external standard
Made up of
-Predictive validity
-Concurrent validity
-Convergent validity
-Discriminant validity
Predictive validity
Does a score on the measure PREDICT the value of another variable in the future
Concurrent validity
Does the measure NOW correlate with info from a related measure?
Convergent validity
Does the measure correlate with another variable that it should theoretically be related to.
Discriminant validity
Does the measure correlate with a conceptually unrelated construct (IQ and personality)
