ESTIMATION I. Introduction. A. The goal of estimation is to use sample statistics to develop unbiased and efficient estimates of population parameters. B. Estimation in scientific research and polling. II. Point estimates. A. Using a single sample statistic to estimate a population parameter. B. Calculating point estimates. III. Confidence intervals. A. Defining a range of values in which you believe the actual value occurs. B. Selecting a confidence level. 1. Alpha level-the probability that an interval does not contain the actual population value. 2. Alpha and confidence. 3. Confidence and interval width. C. Calculating confidence intervals using z-scores. 1. Calculating confidence intervals for means. a. Assumptions. b. The formula. 2. Calculating confidence intervals for proportions. a. Assumptions. b. The formula. 3. Estimating sample size needed to obtain confidence intervals of a specified width. a. Assumptions. b. The formula. D. Calculating confidence intervals for means using t-scores. 1. Assumptions. a. The t-distribution. b. Similarities with the z-distribution. c. Differences from the z-distribution. d. The t-table. 2. The formula. IV. Bias and efficency in estimation. A. Bias. 1. Random vs. non-random sampling error. 2. An estimate is unbiased if the mean of its sampling distribution is equal to the actual population value. B. Efficiency. 1. An estimate is efficient if sample outcomes in a sampling distribution cluster around the mean of the distribution. 2. Influences on the efficiency of confidence intervals (interval widths). a. Dispersion of the population. b. Sample size. c. Confidence level.