SOC202H1 Lecture Notes - Lecture 6: Standard Deviation, Statistic, Sampling Distribution
Document Summary
When we test a hypothesis, we"(cid:396)e testi(cid:374)g a statistic that we obtain from one or more random samples against some value that is stated to characterize a population or populations. Toda(cid:455) (cid:449)e"ll sta(cid:396)t (cid:449)ith the si(cid:373)plest (cid:448)e(cid:396)sio(cid:374): a (cid:272)lai(cid:373) a(cid:271)out the (cid:448)alue of a population parameter (mean or proportion) that we evaluate with sample data. This is known as for a one-sample hypothesis test. Or would the discrepancy likely have arisen by chance: bottom line (cid:449)e"(cid:396)e testi(cid:374)g a statisti(cid:272) that (cid:449)e o(cid:271)tai(cid:374) f(cid:396)o(cid:373) a (cid:396)a(cid:374)do(cid:373) sa(cid:373)ple agai(cid:374)st so(cid:373)e (cid:448)alue that is believed to characterize a population. We initially assume that the null hypothesis is true and consider what the sampling distribution for a mean or proportion would look like under that scenario. We then see if there is evidence against the null by examining how our sample statistic looks relative to the null sampling distribution. Suppose a university official has come under fire for his performance as dean.