Confidence Interval Estimation.pptVIP

Confidence Interval Estimation Point Estimates Population parameter (总体参数) Sample Statistics (样本统计量) Mean μ Standard deviation σ S Proportion p A point estimate (点估计) is a single value (statistic) used to estimate a population value (parameter). Confidence Interval Estimate An Interval Estimate states the range within which a population parameter probably lies A confidence interval is a range of values within which the population parameter is expected to occur at a specified probability. The probability that the population parameter will lie within a confidence interval is called the level of confidence. Find an interval [a, b] such that for a given significant level Given confidence level 95%,(α=0.05), Approx. Confidence Interval Estimate of the Population Mean μ (with σ known) ? (Use R) pnorm(1.96)-pnorm(0) X - μ P ( - 1.96 1.96 ) = .95 σ /√ n The 95% confidence interval (CI) as follows Where population standard deviation σ is known Confidence Interval Estimate The confidence interval of is given by (σ is known) Where Z is the value corresponding to a cumulative area of 1- /2 from the standard normal distribution. z Z -Z Where z follows Standard Normal Distribution z~N(0,1) the population standard deviation is unknown the underlying population is approximately normal, the sample size is less than 30 we use the t distribution. Confidence Interval estimate the Population Mean μ (with σ unknown) The value of t for a given confidence level depends upon its degrees of freedom. Z t 0 t (df = 5) Standard Normal t (df = 13) Bell-Shaped Symmetric ‘Fatter’ Tails t Distribution The t -distribution is very similar to the standard normal distribution. Characteristics of the t distribution It is a continuous distribution. It is bell-shaped and symmetrical. The t distribution is more spread out and flatter at the center than is the standard normal distribution, diffe