Controlled Panel Samples

A third non-probability sampling device often used is the controlled panel sample. This technique pioneered by National Family Opinion, Inc. (NFO) of Toledo, Ohio, is an elaborate and highly controlled form of quota sampling. NFO and similar organizations have developed huge files of names, addresses, telephone numbers, and a wide array of demographic characteristics for households wiling to be interviewed by mail or telephone. Using computers, they have constructed “panels” (often of 1,000 households each) that approximately replicate the US household universe in demographic characteristics, such as age, income and the like, known to be related to consumer attitudes and behavior. In a given project one or more panels are interviewed via mail or telephone to obtain the requisite information.

A major advantage of this approach is that large national samples can be provided relatively cheaply and easily. Such samples are particularly valuable when sampling rare populations; those that make up less than 5 percent of the population. What one does is to sample in two phases. In the first, a large sample is used to identify members of the rare population, using an inexpensive screening questionnaire. Then a more detailed questionnaire (usually by mail) is used with the sample so identified.

The disadvantages of controlled panel samples are those attendant on any quota sample plus the obvious bias that such samples are comprised of people who are willing to be included in panels and to participate in surveys from time to time. Such bias may be particularly acute when the panel is a continuing one that demands extensive cooperation over an extended interval.

The three specialized non-probability sampling techniques described are all variants of convenience and quota sampling, as discussed earlier. All are widely used and can, under appropriate circumstances, be informative. As with any non-probability sampling method, it is essential that the researcher recognize their limitations compared with probability sampling and actively consider the trade offs involved in their use for the particular problem at hand.

Choice of Sample Design in Practice:

The widespread use of non-probability sampling in marketing research has also been noted, and a number of commonly used techniques of this type have been described. In this section, some of the issues which influence the choice of one design over another in a given case are discussed, and certain compromise solutions to the design problem are described.

Quality of Sample Design Required:

The major consideration in design choice is quality of sample design required, a vague and intuitive, but nevertheless useful, concept. As is shown by the common use of non-probability designs, probability sampling despite its many advantages is not always essential. The quality of sample design required varies from one problem situation to another. It is convenient to think of a continuum of quality of sample design required as schematic below

Quality of Sample Design Required:

Extremely Low Extremely High

(Convenience sampling, (probability sampling, from
From an accessible universe) most relevant universe)

In some situations, a low quality sample design, as represented by convenience sampling from an accessible universe may be adequate. An example would be an exploratory study to help define issues when virtually nothing is known of the subject.

At the other extreme, exceptionally high quality data will sometimes be necessary. If the analyst requires universe estimates with calculate precision from a universe that corresponds closely to the universe of interest then probability sampling is essential. These extremes can be regarded as the endpoints on a continuum of sample design quality required.

Both researchers and managers want high quality data, and the advantages of probability sampling are widely recognized. There is a continuing conflict between this perceived need and the limitations of time, money, and complexity. The result is that many studies utilize a sample design that falls some where between naïve convenience sampling and probability sampling form the precise universe of interest.