STAT 110 1nd Edition Lecture 2 Outline of Previous Lecture I. Sampling FramesII. Error in Sampling III. Stratified Random SamplingOutline of Current LectureI. Computing Confidence Intervals for Stratified Random Samples II. Cluster SamplingIII. The Difference between Cluster Sampling and Stratified Random SamplingIV. Experiments Good, and BadCurrent LectureI. Computing Confidence Intervals for Stratified Random Samples a. In stratified random sampling, we have different groups that make up our complete sample. In order to get a confidence intervals for each stratum, complete the following steps for each individual stratum:i. First, use the quick formula for the margin of error (MOE)1. MOE= 1/√n, where n is the number of participants in each stratum ii. Second compute the confidence interval (CI) using your calculated MOE value 1. CI = sample statistic ± MOE = (statistic - MOE, statistic + MOE)iii. Complete the above two steps for each stratum b. It is important to note that when we are looking for differences between population proportions between stratum, we CANNOT identify any statistically significant differences IF the confidence intervals overlap. II. Cluster Samplinga. Cluster sampling is used to increase efficiency and save time and money. Clusters can be separated by geographic location, or some other defining factor.i. In order to gather a cluster sample, follow these steps:1. First, randomly select a cluster2. Second, interview everyone in that cluster III. The Difference between Cluster Sampling and Stratified Random SamplingThese notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.a. As we have just learned, in order to gather a cluster sample, we must first randomly select a cluster and then interview everyone in that cluster. In a stratified random sample, you stratify subjects first and then randomly interviewparticipants within each stratum. So, in a cluster sample, the randomizing comes first, and in a stratified sample, the randomizing comes second. IV. Experiments Good, and Bada. Definitionsi. Response variable: also known as the dependent variable, a response variable measures the changes, or outcomes of an experimentii. Explanatory variable: also known as the independent variable, an explanatory variables causes changes in the response variables iii. Treatment: experimental conditions applied to subjectsiv. Subjects: individuals or participants in the
View Full Document