HLT1RAE Lecture Notes - Lecture 9: Level Of Measurement, Signify, Squared Deviations From The Mean
Document Summary
In the different scenarios listed in the introduction (e. g. analysing a client database in a hospital), the data you obtain will have distinct measurement properties. This is the simplest of the measurement scale types as the data or variable is allocated a name or identification (cid:374)u(cid:373)(cid:271)e(cid:396) a(cid:374)d is (cid:272)atego(cid:396)ised. I(cid:374) the e(cid:454)a(cid:373)ple a(cid:271)o(cid:448)e, the (cid:272)lie(cid:374)ts(cid:859) eth(cid:374)i(cid:272) (cid:271)a(cid:272)kg(cid:396)ou(cid:374)d is a (cid:374)o(cid:373)i(cid:374)al s(cid:272)aled (cid:448)a(cid:396)ia(cid:271)le (cid:894)i. e. irish, chinese, american). Therefore, these variables are qualitative and merely different from each other. Often the variables are coded numerically (i. e. country 1 or country 4), however there is no relationship between the allocated numbers. The next level of measurement involves the rank-ordering of a variable. Ordinal measurements describe order, but not relative size or degree of difference between the items measured. For example, in your audit of the hospital database you assign clie(cid:374)ts i(cid:374)to (cid:858)age g(cid:396)oups(cid:859) (cid:894)g(cid:396)oup (cid:1005): (cid:1007)(cid:1010)-40, group 2: 41-45, group 3: 46-50, group 4: 51-55 years).
