PSYCH 2220 Chapter Notes - Chapter 8: Confidence Interval, Interval Estimation, Statistical Power
18 Feb 2018
School
Department
Course
Professor
Document Summary
Psych 2220 - chapter 8: confidence intervals, effect size, and statistical power. A fi(cid:374)di(cid:374)g is either statisti(cid:272)ally sig(cid:374)ifi(cid:272)a(cid:374)t or (cid:374)ot, (cid:271)ut that does(cid:374)(cid:859)t tell us if it(cid:859)s i(cid:373)porta(cid:374)t or not. New statistics include: effect sizes, confidence intervals, and meta-analyses. Hypothesis testing may be thrown out entirely in favor of new statistics. Point estimate is a summary statistic from a sample that is just one # used as an estimate of the pop. parameter. Ex) a mean, the difference b/t 2 means, An interval estimate is based on a sample stat and provides a range of plausible values for the pop. parameter. Usually constructed by adding and subtracting a margin of error. When 2 intervals do not overlap, we conclude that their means are different. A confidence interval is an interval estimate based on a sample statistic; it includes the pop. mean a certain percentage of the time if the same pop. is sampled from repeatedly.
