Download Psychology Exam: Reliability and Validity and more Exams Nursing in PDF only on Docsity!
OCR Psychology- Reliability and
Validity exam
Reliability - answer - Consistency. The extent to which the findings can be repeated. In other words, if something is measured more than once, the same effect should result. Internal Reliability - answer - How consistently a method measures within itself. External Reliability - answer - How consistently a method measure over time, place and people, when repeated. 3 ways reliability is assessed - answer - Split half reliability, test- retest reliability and inter-rater reliability.
1 way internal reliability is assessed - answer - Split half reliability. Split half reliability and how it is done - answer - Comparing 2 halves of a test to see if the results are consistent (reliable). The test is split into two halves, such as by odd and even questions (questions 1,3,5,7,9 versus 2,4,6,8,10) and the scores of both halves are compared. If the results in the two halves are similar, it can be assumed that the test is reliable. 2 ways external reliability is assessed - answer - Test-retest reliability and inter-rater reliability. Inter-rater reliability and how it is done - answer - Where 2 (or more) observers consistently rate or observe the same behaviour and the 2 sets of ratings are correlated (to 80% or more concordance) to ensure that observations are not subjective. Test-retest reliability and how it is done - answer - Assessing consistency by asking the same Ps to do the test twice. The measure is given to the same group of people twice. If the results on the two tests are similar, it can be assumed that the test is reliable (consistent) Validity - answer - Truth. The extent to which a measure measures what it is supposed to measure.
Extraneous variable (EV) - answer - Any variable other than the IV that could cause a change in the DV and alter the results. These can include: participant variables (e.g. age, IQ), participant effects (e.g. screw you, Hawthorne), investigator effects (e.g. Greenspoon), situational variables (e.g. time, temperature). 3 types of internal validity - answer - Construct, concurrent, criterion. Construct Validity - answer - Does the test measure all aspects of the behaviour? Concurrent Validity - answer - Comparing current performance with previously validated performance on a study / test with the same nature Criterion Validity - answer - Can the study/questionnaire predict future behaviour or attitudes? Improve reliability of self-reports - answer - Ambiguous questions could be clarified or in the case of interviews the interviewers could be given training.
Improve validity of self-reports - answer - Leading questions could be avoided, open questions could be added to allow respondents to expand upon their replies and confidentiality could be reinforced to allow respondents to give more truthful responses.
