Sampling plan in market research

After deciding on the research approach and instruments, the marketing researcher must design a sampling plan. This calls for three decisions:

1. Sampling unit: Who is to be surveyed? The marketing researcher must define the target population that will be sampled. In the American Airlines survey providing an internet facility in their First class with a nominal fee, should the sampling unit be only first–class or business travelers, first–class vacation travelers or both? Should travelers under age 18 be interviewed? Should both husbands and wives be interviewed? Once the sampling unit is determined, a sampling frame must be developed so that everyone in the target population has an equal or known chance of being sampled.

2. Sample size: How many people should be surveyed? Large samples give more reliable results than small samples. However, it is not necessary to sample the entire target population or even a substantial portion to achieve reliable results. Samples of less than 1% of a population can often provide good reliability, with a credible sampling procedure.

3. Sampling procedure: How should the respondents be chosen? To obtain a representative sample, a probability sample of the population should be drawn. Probability sampling allows the calculation of confidence limits for sampling error. Thus, one could conclude after the sample is taken that “the interval 5 to 7 trips per year has 95 chances in 100 of containing the true number of trips taken annually by first class passengers flying between Chicago and Tokyo.�

Three types of probability sampling are described below part A. When the cost or time involved in probability sampling is too high, marketing researchers will take non-probability samples. Part B describes three types.

A. Probability Sample

Simple random sample: every member of the population has an equal chance of selection.

Stratified random sample: The population is divided into mutually exclusive groups (such as age groups), and random samples are drawn from each group.

Cluster (area) sample: The population is divided into mutually exclusive groups (such as city blocks) and the researcher draws a sample of the groups to interview.

B. Non-probability Sample

Convenience sample: The researchers select the most accessible population members.

Judgment sample: The researcher selects population members who are good prospects for accurate information.

Quota sample: The researcher finds and interviews a prescribed number of people in each of several categories.

Some marketing researchers feel that non-probability samples are very useful in many circumstances, even though they do not allow sampling error to be measured.