The study's purpose: to pinpoint problems with reliability and validity of particular survey questions. Subjectivity is thus associated with a lack of reliability and validity. Now obviously, objective scientific research has to concern itself very much with reliability and validity; but the pertinent question here is: reliability and validity with respect to which criteria? If we register a respondent as saying no, for heaven's sake to a particular question, we may want to know his or her answers to related questions and the strength of his or her feelings with respect to those; shortly, the universe or concourse for that particular respondent. Reliability and validity may then be established within the subjective experience, as communicated to the researcher, of this person; shortly: a single case analysis.
This paper shows the possibilities of business-to-business-research to outline the business travel market. The Business Travel Monitor, a yearly research project, covering 4000 business-establishments, creates additional ways for market segmentation for suppliers in the business travel market. It offers new entries for marketing-auditing and marketing-planning. Finally an upgrading of the reliability of the data is attained by interviewing two persons per establishment, the business traveller himself and the booker of the business trip.
The focus of this paper is a re-sampling technique, namely the bootstrap, for assessing the reliability of combining data from a large number of individuals in a conjoint analysis procedure. The issue of aggregation of preferences is a crucial one in large-scaled surveys where it is often used to simplify the analyses and obtain results in a more concise and therefore manageable form. The bootstrapping technique is applied to two large sets of data collected by an insurance firm. Results strengthen the relevance of this technique. The computer program, using the SAS package, is presented.
Elements of the design and operation of large scale surveys introduce sources of error not adequately dealt with in normal textbook formulae. Nevertheless, it is often possible by comparing the results of replicated surveys to arrive at objective and empirical estimates of accuracy and lack of bias in such surveys. Further, it is necessary to do this to convince our clients of the reliability of our work. Apart from the reliability of a survey, it should also be sensitive to changes in the situation. Examples of the sensitivity of opinion polls are given indicating how substantial variability and unpredictability in the way people's views respond to outside events implies that predictive models, especially in the course of an electoral campaign are fraught with danger. The unpredictable electorate reigns supreme and the opinion polls can only reflect, with as short a time lag as possible, the present rather than the future state of public opinion.
There is no doubt that the quality or rather the reliability with which findings of any type of market research can be translated into practical use, is heavily dependent on the final sample that has been obtained. The sample directly deriving from the applied sampling technique -and its control-; a technique which is directed by two elementary factors: 1. the complexity of the population from which the sample has to be drawn; 2. the problem analysis on hand. Other factors such as budget available may be of influence on the scope of the study, priorities that must be set and the like but have no fundamental impact on the sampling methods as such.
The problem I am going to present you regards a study which has contributed to solve a major problem of the client, a car manufacturer, and which has engaged our institute in a new area of technical development, quite unusual as compared with the normal fields of operation for a market research company. I shall try here to point out the main problems we had to face, without, of course, entering into much details, due to the complexity also of some mathematical aspects involved. The unusual problem which the client submitted us some three years ago was the following. We were asked: 1. To find a way for measuring, on a continuous basis, the "reliability", of each mechanical or electrical component of a selected list of car models in 4 European countries.
One of the oldest techniques to test the level of attention of advertisements, yet nevertheless still often in practice today, is the portfolio test: the test person goes through a folder usually containing 10 advertisements. Afterwards it is ascertained which products and brands are remembered. A series of tests, respectively re-tests, in 1979 with over 2000 interviews has shown that this method can be unreliable: the same advertisements from test to test can obtain different recall and therefore different awareness values - despite using the same test design, same sample size, same sample structure, same test method, same institute. The paper shows factors which may be responsible for this phenomena and gives recommendations how to improve portfolio test reliability.
One of the oldest techniques to test the level of attention of advertisements, yet nevertheless still often in practice today, is the portfolio test: the test person goes through a folder usually containing 10 advertisements. Afterwards it is ascertained which products and brands are remembered. A series of tests, respectively re-tests, in 1979 with over 2000 interviews has shown that this method can be unreliable: the same advertisements from test to test can obtain different recall and therefore different awareness values - despite using the same test design, same sample size, same sample structure, same test method, same institute. The paper shows factors which may be responsible for this phenomena and gives recommendations how to improve portfolio test reliability.
This paper tries to demonstrate how a marketing research project aids decision makers to improve the validity and reliability of their decisions. A survey was undertaken to find out the present and future levels of market share, the appropriate ratio of returned, "unsold", copies and the readers profile of the largest selling newspaper "Hurriyet" in Turkey. A simple descriptive model was chosen by utilizing the relationship between attitudes and behavior and the First Order Markovian Model to predict the future level of market shares.
This paper describes the results of an experiment which examines the reliability and validity of qualitative research. Two studies of the same marketing problem (a pack test) were conducted and compared: one a qualitative study (6 group discussions), and the other a hall test (550 respondents interviewed by questionnaire). The costs of the qualitative research were approximately half of the quantitative research. The background to the experiment is the tendency in several countries to use more qualitative research, sometimes at the expense of quantitative research. Data on the losses or gams in quality by using qualitative research is limited, however, and this research was done to provide a basis for evaluating it.