HSS 2381 Lecture Notes - Lecture 6: Confidence Interval, Interval Estimation, Null Hypothesis
Document Summary
When we have 2 sets of measures made on the same sample of participants at different times (before vs after treatment) The variability of both sets of measures should be the same. We don"t care about variance of scores in each sample. High w/in group variability doesn"t affect the test. We care about the variance of difference scores. In formula, population mean is assumed to be 0 for null hypothesis. Numerator: difference of means of 2 sets of measures. Denominator: estimated standard error of the 2 sets of measures. Inferential process of using sample statistics to approximate population parameters. Point estimate: use a single number as your estimate. Interval estimate: range of values used as your estimate. Confidence interval: the range around a sample mean, within which the population mean is likely to fall. Calculated for a particular level of confidence (ex; 95%, etc. ) A level of confidence accompanies an interval estimate.