Reliability

• Reliability concerns consistency.

  Validity concerns legitimacy
• Two types of reliability

  1 Internal - is the measure within consistent

  2 External - is the measure consistent over time
• Reliability refers to how consistent the findings from an investigation or measuring device are. A measuring device is said to be reliable if it produces consistent results every time its used.
• Inter observer reliability is the degree to which two or more observers agree on the same observation
• For inter rater reliability to be considered acceptable there must be a correlation coefficient of more than +0.8 between two or more observers
• The most reliable method is the laboratory experiment as it allows the highest levels of control and highest level of manipulation on the IV.
• In order to improve reliability observers should be trained in use of a coding system/ behaviour checklist. They should practise using it and discuss their observations. The investigator can then check reliability of observations.
• Internal reliability is the measure of the extent to which something is consistent within itself. For example all the questions on an IQ test should be measuring the same thing. This may not be relevant to all questionaries because sometimes internal consistent is not important for example a questionnaire about fear experiences might look at many aspects of being fearful
• External Reliability is a measure of consistency over several occasions. For example if an interviewer conducted an interview and then conducted the same interview with the interviewee a week later the outcome should be the same otherwise the interview isn’t reliable
• Split half method is used to test internal reliability. One group of participants is given a test once. The participants answers to test questions are divided in half and compared ( comparing all answers to odd number questions with all answers to even number questions . Individual scores on both halves should be similar two scores can be compared using a correlation coefficient.
• Test retest method is used to asses external reliability. A group of participants are given a test/interview and then given it again some time later (when ps are given me to forget it) Answers are compared using a correlation coefficient and should be the same.