Sampling Fundamentals - Sampling Fundamentals
Sampling Fundamentals - Sampling Fundamentals
Marketing research often involves the estimation of a characteristic of some population. For instance, the average usage level of a park by community residents might be of interest, or information on the attitudes of a student body toward a proposed intramural facility could be needed. In either case, it would be unlikely that all members of the population would be surveyed. Contacting the entire population, that is, the entire census list, simply would not be worthwhile from a cost—benefit viewpoint. It would be both costly and, in nearly all cases, unnecessary, since adequate reliability usually can be obtained from a sample. Further, it often would be less accurate since nonsampling errors like nonresponse, cheating, and data-coding errors are more difficult to control.
There are many ways of obtaining a sample. Some are informal and even casual. Passers-by may be queried as to their opinions of a new product. If the response of everyone in the population is uniform—they all either love it or hate it—such an approach may be satisfactory. If you want to determine if the water in a swimming pool is too cold, it isn't necessary to take a random sample; you just have to test the water at any one place, because the temperature will be constant throughout.
Table 11-1
Issues in Probability Sampling
• Idemifyjng_th^target population
• Selecjing^the probability sample
Simple random sampling Stratified sampling Cluster sampling Multistage sampling
• Determining the sample size
• Handling the nonresponse^ problem
In most cases, however, the situation is more complex. There are several questions to be answered and a wide variability in responses. It is then necessary to obtain a representative sample of the population consisting of more than a handful of units. It is possible, even necessary in some cases, to obtain a sample representative of the population just by using judgment and common sense. The preferred approach, however, is usually to use probability sampling to obtain a representative sample. In probability sampling, all population members have a known probability of being in the sample.
Probability sampling has several advantages over nonprobability sampling. First, it permits the researcher to demonstrate the representativeness of the sample. Second, it allows an explicit statement as to how much variation is introduced because a sample is used instead of a census of the population. Finally, it makes possible the more explicit identification of possible biases.
In this chapter, probability sampling will be described first, followed by a description and comparison of nonprobability sampling methods.
Probability sampling involves four considerations, as summarized in Table 11-1. First, the target population—the group about which information is being sought—must be specified. Second, the scheme for selecting the sample needs to be developed. As Table 11-1 indicates, there are several kinds of schemes to consider. Third, the sample size must be determined. The sample size will depend upon the accuracy needs, the variation within the population, and the cost. Finally, the nonresponse problem must be addressed.
Marketing research often involves the estimation of a characteristic of some population. For instance, the average usage level of a park by community residents might be of interest, or information on the attitudes of a student body toward a proposed intramural facility could be needed. In either case, it would be unlikely that all members of the population would be surveyed. Contacting the entire population, that is, the entire census list, simply would not be worthwhile from a cost—benefit viewpoint. It would be both costly and, in nearly all cases, unnecessary, since adequate reliability usually can be obtained from a sample. Further, it often would be less accurate since nonsampling errors like nonresponse, cheating, and data-coding errors are more difficult to control.
There are many ways of obtaining a sample. Some are informal and even casual. Passers-by may be queried as to their opinions of a new product. If the response of everyone in the population is uniform—they all either love it or hate it—such an approach may be satisfactory. If you want to determine if the water in a swimming pool is too cold, it isn't necessary to take a random sample; you just have to test the water at any one place, because the temperature will be constant throughout.
Table 11-1
Issues in Probability Sampling
• Idemifyjng_th^target population
• Selecjing^the probability sample
Simple random sampling Stratified sampling Cluster sampling Multistage sampling
• Determining the sample size
• Handling the nonresponse^ problem
In most cases, however, the situation is more complex. There are several questions to be answered and a wide variability in responses. It is then necessary to obtain a representative sample of the population consisting of more than a handful of units. It is possible, even necessary in some cases, to obtain a sample representative of the population just by using judgment and common sense. The preferred approach, however, is usually to use probability sampling to obtain a representative sample. In probability sampling, all population members have a known probability of being in the sample.
Probability sampling has several advantages over nonprobability sampling. First, it permits the researcher to demonstrate the representativeness of the sample. Second, it allows an explicit statement as to how much variation is introduced because a sample is used instead of a census of the population. Finally, it makes possible the more explicit identification of possible biases.
In this chapter, probability sampling will be described first, followed by a description and comparison of nonprobability sampling methods.
Probability sampling involves four considerations, as summarized in Table 11-1. First, the target population—the group about which information is being sought—must be specified. Second, the scheme for selecting the sample needs to be developed. As Table 11-1 indicates, there are several kinds of schemes to consider. Third, the sample size must be determined. The sample size will depend upon the accuracy needs, the variation within the population, and the cost. Finally, the nonresponse problem must be addressed.
Comments
Post a Comment