OPER1135 Lecture Notes - Lecture 25: Null Hypothesis
Document Summary
Review for hypothesis test: other things being equal, as the sample size increases, the standard error of a statistic, increases, decreases, approaches the standard deviation of the population, approaches the population mean in numerical value, remains constant if the value of sigma is known, suppose you take 50 measurements on the speed of cars on interstate 90, these measurements follow roughly a normal distribution. Null hypothesis (in this chart they are all two-tailed tests but they could also be one-tailed by having a or sign instead of the = sign. Test stati stic you use (z, t, or. Ignore this case: it never happens in real life. t z. H0: 12 = 22 sizes n1 and n2. Sample standard deviations s1 and s2 from independent populations and sample sizes n1 and n2, assume populations have equal variance. Sample standard deviations s1 and s2 from independent populations and sample sizes n1 and n2, cannot assume populations have equal variance.