BUSS1020 Lecture Notes - Lecture 8: Sampling Distribution, Statistical Parameter, Interval Estimation

• School: University of Sydney
• Department: Business Studies
• Course: BUSS1020
• Professor: All

Document Summary

A point estimate is a single number. Confidence interval provides additional information about the variability of the estimate. ^an interval estimate provides more info about a pop parameter than a point estimate. When only 1 sample size n taken and mean () is not known, calculated interval may/may not contain ; but x% of intervals formed in this manner contain. ^conclusion you gain from 1 sample: you are x% confident your interval contains. Our confidence that the interval will contain the unknown population parameter as a % If confidence level is 95% written as (1-)=0. 95 so =0. 05. ^without knowing , 0. 05 chance that is inside interval. Confidence interval for when is known: if pop not normal use (cid:494)large(cid:495) sample (cid:523)clt(cid:524) Commonly used confidence levels are 90%, 95% and 99%: Note that confidence intervals extend from (1-)x 100% of intervals contain and ((cid:524)x (cid:883)(cid:882)(cid:882)% don(cid:495)t: This introduces extra uncertainty since s varies from sample to sample.