This paper demonstrates that those random procedures for selecting individuals in households will lead to enormous shortcomings in the representativeness of the individual sample while the agencies will need a second or third wave to obtain a minimum of representativeness. This is a costly sampling procedure which can easily be avoided. The basic assumption underlying the study presented in the paper is that nowadays one-person households and two-person households are in the majority in most European countries. This means that individuals living in such households have a far greater chance of being drawn in random individual samples than persons living in three-or-more person households. As persons living in smaller households have different socio-economic characteristics from persons living in larger households, random samples of individuals lead to wrong results - not only in terms of socio-economic characteristics, but also in the results of practically every market research study based on individuals. The study described was performed in NIPO's Telepanel where a questionnaire was used by applying different selection procedures. The paper describes the results of a few questions about political preference by applying the various methods. Finally an extremely practical solution will be discussed. This selection method - whose value is borne out by the results - is to select within the household: in a panel situation: youngest person (from a certain age) in a cross-section situation: youngest male and if not present youngest female (from a certain age).
In this paper we will discuss the quality of the data obtained by using computerised interviewing in a panel situation. For this form of research some extra advantages of computerised interviewing can be obtained. It will first be shown for data on income that the quality of the data is already on a high level, with important advantages because of the panel character when compared to ad hoc research. However from the same analysis follows that for policy relevant conclusions the quality of the data, and therefore of the questionnaire should be improved further. Another equally important aspect for panel research is that interviewees will become bored and irritated by exposure to similar questionnaires on a regular basis. Especially when they perceive little or no change in the answers they are providing. This may affect increased dropout and panel mortality, thereby reducing the usefulness and lifecycle of the panel. In the last part of the paper we will go into the improvements that may be obtained in computerised panel research by using information retained from previous interviews, when collecting new data.
From telephone interviewing and then computer assisted telephone interviewing (CATI) the last few years have brought along two new systems of datacollection by means of personal interviews. One is the Telepanel-system, which consists of a random sample of 1.000 households, of which the members answer questions that appear on their television set. The latter is connected to a home-computer they were supplied with by the research institute. By means of a modem and very userfriendly software the questionnaires are transmitted from the central computer to their home-computer and after the responses have been typed in, the data of the different members that were requested to respond in that particular weekend are transmitted back to the central computer. The data can then be processed immediately. The other development is CAPI, computer assisted personal interviewing in cross-sectional research. A group of specially trained interviewers visit homes or business addresses with portable personal computers. Questionnaires appear on the LCD-screen and the respondents themselves punch in the replies. In this paper we will focuss on extra advantages these methods have over existing procedures such as CATI and face-to- face interviews with paper and pencil. The first is obviously that the number of different response possibilities is more limited when using a telephone, the respondent will comprehend the question better if it can be read instead of heard and the third and in our opinion more decisive advantage is the reduction of the influence of the interviewer. The effects of these advantages will be shown to be of great value in: - getting more information concerning sensitive topics. - getting more and more valid information on difficult research topics. - getting more reliable data - enabling collection and analysis of non-sensitive data that write-in panels cannot produce.
This paper describes the application of a new technique for data-collecting in the field of quantitative research into financial services. Researchers know that quantitative research into financial services mostly creates relatively more fieldwork problems than research for other consumer goods. In the first part of this paper a number of these problems will be discussed. the CAPI-system (Computer Assisted Personal Interviewing) has been used for a research study on behalf 6 main Dutch banking corporations. This method will be discussed in the second part of the paper. The third part of this paper deals with the results of the pilot study carried out by means of the CAPI-method and compared with the traditional methods of data-collecting. In this study, using the same questionnaire, data were collected by means of the traditional face-to-face method, the CATI-system and the CAPI-method. Comparison of the results coming from these data-collecting methods leads to a number of conclusions.
This paper describes a research-program that started with a check on the execution of poster campaigns. By means of samples drawn from the files of poster sites in the Netherlands each month a number of sites was checked on the presence of posters according to the classification reports of the outdoor operators. This system was executed on a continuous base and in 1984 the need for a more sophisticated research program became apparent. An extensive research study was started with the following objectives: a) the calculation of confrontation chances (OTS) b) the measurement of "actual seeings" of the poster sites c) the calculation of coverage data in particular the total reach and the coverage of individual poster campaigns.
Two of the export organizations, each acting on its own responsibility, commissioned a wide scale survey in 1982. The purpose of this survey was to establish which bottlenecks are encounted by exporting small and medium-size companies in their export activities, as well as their contacts with export organizations, in order to find ways of contributing to solutions. The research scheme consisted of one survey among smaller exporting companies and another among export organizations. This paper shows that this type of research in which one is attempting to influence policy at Government level by confronting policymakers with research results, conclusions, and recommendations, is a correct and desirable intermediate phase in a research project.
The Dutch government has to issue: A. Stringent requirements concerning heat and insulation in new buildings; B. A system of subsidies for improving heat insulation in existing dwellings and other buildings. Previously, when energy was both abundant and cheap, insulation was hardly a consideration. The paper consist of interview with architects, building contractors, building experts in local and national government, big dealers in building materials and very large building investors (such as project developers, banks, insurance companies). The most important finding was that very few of these experts expected future developments in building methods and building materials related to thermic isolation.