安达信咨询方法与工具资料库meth001.doc免费

DATE06/23/95 TIME8:49 AM 165392 MR 06/92 Market Research PRACTICE AID SAMPLE SELECTION METHODS Type of Sampling Description Advantages Disadvantages Type of Sampling Description Advantages Disadvantages A. Simple Random Sampling Assign to each population member a unique number; select sample by use of a table of random numbers. Requires minimum knowledge of population in advance. Simplest of all sampling methods. Easy to conduct, analyze data, and compute errors. Does not make use of knowledge of population which researcher may have. Larger errors for same sample size than in stratified sampling. B. Stratified Subdivide the population into subgroups; randomly select given number of respondents from each subgroup. Assures representatives with respect to characteristic which forms basis of classifying units; therefore, yields less variability than A. Decreases chance of failing to include adequate numbers of population segments because of classification process. Characteristics of each subgroup can be estimated, and hence comparisons can be made. Requires accurate information on proportion of population in each subgroup, otherwise increases error. If stratified lists are not available, may be costly to prepare them; possibility of faulty classification and hence increase in variability. Often requires larger sample size than A. Need at least 20 people to make statistical comparisons meaningful. C. Simple Random Cluster Select groups/clusters of respondents by some form of random sampling; survey all individuals who are members of these units. If clusters are geographically defined, yields lowest field costs. Requires listing only individuals in selected clusters. Characteristics of clusters as well as those of population can be estimated. Can be used for subsequent samples, since clusters, not individuals, are selected, and substitution of individuals may be permissible. Larger errors for comparable size than other probability samples. Requires ability to assign e