1-3 Collecting Sample Data 29 MAIN CENTER Heritage School Park St. North St. 1st St. 2nd St. 3rd St. 82nd St. 52nd St. 36th St. 43rd St. A St. B St. C St. D St. E St. F St. Way St. 4th St. 5th St. MLK PKWY 555-867-5309 555-606-0842 555-777-9311 Simple Random Sample A sample of n subjects is selected so that every sample of the same size n has the same chance of being selected. Stratified Sample Subdivide population into strata (groups) with the same characteristics, then randomly sample within those strata. Cluster Sample Partition the population in clusters (groups), then randomly select some clusters, then select all members of the selected clusters. Systematic Sample Select every kth subject. Convenience Sample Use data that are very easy to get. Men Women 3rd 6th FIGURE 1-4 Common Sampling Methods HINT Because it’s difficult to remember the distinction between stratified sampling and cluster sampling, picture your entire class as one cluster among all classes at your college. Remember the alliteration of “cluster class” to recall that with cluster sampling, you choose all of the members of selected clusters. Associate “cluster” with “all.” Then, stratified sampling is the other method of choosing samples from selected classes or subgroups. Multistage Sampling Professional pollsters and government researchers often collect data by using some combination of the preceding sampling methods. In a multistage sample design, pollsters select a sample in different stages, and each stage might use different methods of sampling, as in the following example. Multistage Sample Design EXAMPLE 3 The U.S. government’s unemployment statistics are based on surveys of households. It is impractical to personally survey each household in a simple random sample, because they would be scattered all over the country, making it nearly continued Wording in Surveys Can Affect Results Pew Research Center pollsters conduct experiments to better understand how wording in questions can affect the responses of survey subjects. In a Pew Research Center survey of 1505 adults in the United States, half of the respondents were asked about finding “jobs” while the other half were asked about “good jobs.” For the “jobs” group, 33% said that jobs were difficult to find. For the “good jobs” group, 45% said that good jobs were difficult to find.
RkJQdWJsaXNoZXIy NjM5ODQ=