This paper investigates the small sample properties of minimum chi-square estimates of the parameters of stochastic brand choice models. It also describes and evaluates a statistical test which is appropriate for discriminating between two stochastic brand choice models when one is a constrained version of the other. [ABSTRACT FROM AUTHOR]
MARKETING research, RELATIONSHIP marketing, ADAPTABILITY (Personality), CONSUMER behavior, PURCHASING, CONSUMER preferences, MODEL cars (Toys), BRAND choice, CHI-squared test
Abstract
This article presents a reply to a response by Donald Morrison about the article "Adaptive Behavior in Automotive Brand Choices," from the February 1969 issue of "Journal of Marketing Research." The author believes that Morrison is mistaken in his conclusion that the original research is erroneous. He says that Morrison is actually testing a different hypothesis with the same set of data. Morrison's hypothesis is that individuals are not homogenous, as the author stated in his original paper. The author concludes by showing a chi-square test where the results favor his belief that past purchases of a particular make influence the probability that the consumer will again purchase that make.
STATISTICAL sampling, SAMPLING (Process), COMMERCIAL statistics, BUSINESS information services, MATHEMATICAL statistics, RETAIL industry, WHOLESALE trade, CHI-squared test, SAMPLE size (Statistics)
Abstract
The article reports on sampling problems in trade statistics in the field of marketing. The author focuses on the success rate and reliability of patented sampling techniques utilized by the U.S. Bureau of Foreign and Domestic Commerce. Government sampling techniques relevant to the retail and wholesale trade are criticized. A case study focusing on grocery wholesales located in the U.S. is discussed in relation to the 1935 Census of Distribution. Applications of the Chi Square test are also examined.
The concepts of alpha error, beta error, power and alternative hypotheses are first developed for a simple percentage problem in market research. These concepts are then used to explain the method of calculating simple size in the multi-cell case using the non-central Chi-Square distribution. The development is by means of an advertising research problem for delineating "different" geographical trading areas and the sample size necessary to detect differences of given magnitudes. [ABSTRACT FROM AUTHOR]