STAT 3005 Lecture Notes - Lecture 6: Confidence Interval, Interval Estimation, Point Estimation
Document Summary
Inference statistics allow us to make statements about a general population using the results of a random sample from the population. Point estimates are single values that would be used as a (cid:498)best guess(cid:499) for the parameter such as: (cid:1868) for (cid:1868),(cid:1877) for ,and (cid:1871) for . One must consider what is the probability that the answer is correct. This can be answered by assigning probabilities to intervals. Interval estimates are ranges of numbers in which the estimate is likely to fail. Confidence intervals are the most common interval estimate. They are computed from the sample data and can be thought as having a certain probability of containing the true parameter. Confidence level (c) is the probability of containing the true parameter value. It is written as (cid:883) and gives a (cid:4666)(cid:883) (cid:4667)(cid:883)(cid:882)(cid:882)% ci. Ci for proportion (cid:498)p(cid:499) are created by adding and subtracting the margin.