HLTHAGE 2A03 Lecture Notes - Lecture 4: Stanford–Binet Intelligence Scales, Army Alpha, Content Validity

• School: McMaster University
• Department: Health, Aging and Society
• Course: HLTHAGE 2A03
• Professor: Housne Begum

Document Summary

Only if it can be made better (e. g. more reliable/valid/up-to-date/short) Saves time and effort: already validated (but do confirm) There are limits to number of ways questions can be asked. A mass of data available from clinical experiences and critical incidents. Could include observation of expert practice in addition to interview. But experts are fallible (e. g. , hysteria, self-pollution, personality typing) Follow-up (cid:449)ith fi(cid:374)di(cid:374)gs (cid:894)(cid:862)do the(cid:373)es (cid:396)eso(cid:374)ate (cid:449)ith e(cid:454)pe(cid:396)ie(cid:374)(cid:272)e? (cid:863) (cid:862)(cid:396)ate i(cid:373)po(cid:396)ta(cid:374)(cid:272)e of ea(cid:272)h (cid:272)o(cid:374)(cid:272)ept(cid:863)(cid:895) Participants who are likely to have in-depth knowledge. Items should provide a representative sample of all possible items in the domain: Improves public relations (colleagues, policy makers, media, and courts) Proportion of people who choose a specific response alternative ideally between 0. 2 and 0. 8. Test developers hope that respondents will carefully weigh each response. An outbreak of influenza is expected to kill 600 people. Program a: 200 people will be saved. Program b: 1/3 chance 600 people will be saved, 2/3 chance 0 people.