Journal of Marketing Research

The evaluation of total error in survey findings is largely neglected. Confidence intervals and other common tools deal only with random and occasionally other limited errors. This article presents a new method by which market researchers and clients can interpret their information and judgment about all survey errors.

Is there a common marketing model of man? Implicitly very probably, but how adequate the model is can be another question.

This article suggests an explicit system for evaluating the quality of work performed by outside suppliers of marketing research.

Research findings in the experimental social psychology area indicate the phenomenon of the experimenter effect. Major research findings are reviewed, and implications for laboratory experiments in marketing are considered. Some measures are also suggested to reduce experimenter bias.

This study compares seven marketing research methods for selecting a brand name. All methods indicate an adequate, high test-retest reliability. Inter-method correlations indicate that six of the seven methods generate nearly identical results, affirming an assumption often made but seldom tested.

A method of analyzing the components of a trend in consumer purchasing is described. An empirically-based mathematical model is first used to predict the purchasing pattern in the absence of a trend. Comparison between the observed data and these predicted norms permits a detailed evaluation of the trend. Two examples of practical applications of the technique are presented.

What are the predictive factors related to savings inflows in new savings and loan offices? Analysis of a sample of southern California offices reveals the importance of growth and the promotional aggressiveness of existing competitors in submarkets as predictive factors. The analysis casts doubt on the reliability of static measures such as population, average income, and savings penetration.

This exploratory study of the relationship between sales success of selected gasoline service stations and certain interaction characteristics of their personnel shows the importance of interaction in marketing.

Constrained and unconstrained models of a variable-sum market game characterizing the problem of television programming are developed. Solutions are obtained through the introduction of a nonresponding pseudo-firm which turns the game into a constant-sum one. The relative values of competitive and noncompetitive models are then discussed.

Media strategies aimed at penetrating the heavy half are frequently based on matching socioeconomic and demographic profiles of the media under consideration to those believed representative of the target group. This assumes that socioeconomic and demographic variables are correlated with product consumption. The authors evaluate the validity of this assumption by analyzing the relationship between socioeconomic-demographic variables and consumption for each of 57 grocery products.

Identical interviews with 645 husbands and wives provided an opportunity to examine agreement between spouses on reporting annual family income. Three-fifths of the pairs reported the same income, using 13 intervals. The ratio of husbands to wives reporting higher income was about 3 to 2.

The need for a clearinghouse on computer applications in marketing research is developed and a solution proposed. A possible format for such a forum in JMR is outlined.

The number of “no preference” responses in a paired comparison test can definitely be influenced by the wording of the question. More important, allocation of such responses among the total test score can have serious effects. This article suggests a method for handling the neutral vote.

The effect of the advance letter was examined by experiments during two mail surveys. Results show the advance letter significantly improved response rates. The advance letter, however, did not affect how fast a questionnaire was returned, how many questions were not answered, and how the respondent answered the questions.

Because efficient media selection is a complex process, and because media costs are essentially linear, the most promising technique for media selection is linear programming. To improve its usefulness, it will first be necessary to collect more detailed readership data and to utilize more realistic restraints.

In this rejoinder to Professor Stasch, the authors defend their approach.