STA215H5 Lecture Notes - Lecture 1: Univariate, Sepal, Categorical Variable
Document Summary
The sampleis the collection of all the individuals that you actually observe. We hope the sa(cid:373)ple is represe(cid:374)tati(cid:448)e of the populatio(cid:374) of i(cid:374)terest it (cid:373)ight (cid:271)e. We record data about each individual in the sample. This collection of data is called sample data. Sometimes the population actually sampled is not the same as the population of interest. Example: a ps(cid:455)(cid:272)holog(cid:455) e(cid:454)peri(cid:373)e(cid:374)t, (cid:272)o(cid:374)du(cid:272)ted (cid:271)(cid:455) a u(cid:374)i(cid:448)ersit(cid:455) professor, populatio(cid:374) of i(cid:374)terest is all adults, sa(cid:373)ple (cid:272)o(cid:374)sists of u(cid:374)i(cid:448)ersit(cid:455) stude(cid:374)ts. We observe the values of variables(or random variables) on each individual in our sample: varia(cid:271)les differ fro(cid:373) i(cid:374)di(cid:448)idual to i(cid:374)di(cid:448)idual, varia(cid:271)les are ra(cid:374)do(cid:373) (cid:449)e do(cid:374)"t k(cid:374)o(cid:449) the (cid:448)alue of a(cid:374) i(cid:374)di(cid:448)idual"s (cid:448)aria(cid:271)le u(cid:374)til we observe the individual. Examples: we"re i(cid:374)terested i(cid:374) the defi(cid:374)i(cid:374)g the differe(cid:374)(cid:272)es (cid:271)et(cid:449)ee(cid:374) three t(cid:455)pes of iris: setosa, versicolor, and virginica. Useful variables include sepal length and petal width: we"re i(cid:374)terested i(cid:374) staffi(cid:374)g the e(cid:373)erge(cid:374)(cid:272)(cid:455) u(cid:374)it of a hospital.
