MATH 140 Lecture Notes - Lecture 9: Sampling Distribution, Central Limit Theorem, Statistical Parameter
Document Summary
Statistical inference: draw conclusions on the population based entirely on a sample taken from it: only acceptable if it is randomized: the subjects that are used are chosen entirely based on chance. Difference in symbols used based on the population parameter or the sample statistic: population: mean- , standard deviation- , proportio(cid:374) of (cid:862)su(cid:272)(cid:272)esses(cid:863)-p, number of. Units-n: sample: mean-(cid:454) , standard deviation-s, proportion of successes- p , number of units-n. True random sampling means that each unit once chosen is taken out as a possible choice once agai(cid:374), it is said i(cid:374) pro(cid:271)le(cid:373)s as (cid:862)without replacement(cid:863) Different than judgement sampling, which is when you choose units you think are fairly representative of the population. Variability due to sampling/sampling variability: using the random sample to make an estimate about the population parameter. Formula for p (statistic estimate/sample proportion) x= number of successes in the sample. N= number of units within the sample.
