MGCR 271 Chapter Notes - Chapter 6: Null Hypothesis, Statistical Inference, Standard Deviation

• School: McGill University
• Department: Management Core
• Course: MGCR 271
• Professor: Glenn Zabowski

Document Summary

Statistical inference draws conclusions about a population on the basis of sample data and uses probability to indicate how reliable the conclusions are. A (cid:272)o(cid:374) de(cid:374)(cid:272)e level is the probability that the method for constructing a (cid:272)o(cid:374) de(cid:374)(cid:272)e i(cid:374)te(cid:396)(cid:448)al actually produces an interval that contains the unknown parameter. A 95% (cid:272)o(cid:374) de(cid:374)(cid:272)e i(cid:374)te(cid:396)(cid:448)al gi(cid:448)es a (cid:272)o(cid:396)(cid:396)e(cid:272)t (cid:396)esult 95% of the ti(cid:373)e (cid:449)he(cid:374) (cid:449)e use it (cid:396)epeatedly. A sig(cid:374)i (cid:272)a(cid:374)(cid:272)e test shows how strong the evidence is for some claim about a parameter. The probabilities in both (cid:272)o(cid:374) de(cid:374)(cid:272)e intervals and tests tell us what would happen if we used the same procedure for the interval construction or test computation very many times. observed result if the null hypothesis really were true. A -value is the probability that the sample would produce a result at least as extreme as the. A -value tells us how surprising the observed outcome is.