Reliability
ability to produce similar results when replicated
Margin of error
amount of random sampling error, therefore precision of an estimate, varies from sample to sample
Interrater agreement
agreement among observers
Reliability of psychological test
natural change over time, simply repeating does not work all the time
- test-retest reliability (same test twice)
- parallel-forms reliability (parallel versions of the test)
- split-half reliability (parallel forms of test intermingles in the same test and setting)
Accuracy
ability to produce results that agree with known standard and satisfy objectives
Validity
ability to measure what you want to measure
Types of validity
- internal validity
- external validity
- face validity
- content validity
- criterion-related validity
- concurrent validity
- predictive validity
- construct validity
Internal and external validity
- ability to measure what you want to measure
- ability to apply to context outside of the study
if one is high, the other one is low -> balance each other
Types of measures
- behavioral
- physiological
- self-report
- implicit
How to reduce experimenter bias
- single-blind technique (experimenter does not know which treatment)
- double-blind treatment (neither experimenter nor subject know which treatment)
- automating experiment (use of computer)
Nonexperimental research
observing variables without manipulating them
How to quantify observations
frequency, duration, intervals
Sampling strategies for observations
time sampling, individual sampling, event sampling, recording
