Is the respondent disappearing? For some years now, non-response has been a major cause of concern for market researchers. And those people who are still prepared to co-operate in research, i.e. the respondents, are being converted into participants and ambassadors. Traditional methods are apparently being traded in for bricolage, ethnography, semiotics, diaries, photographs, home videos, observation and large workshops with consumers or clients (so-called consumer shoe groups). Disciplines such as linguistics, neuroscience and cognitive psychology are being used to provide additional consumer insight. This is indeed fascinating but what are we actually doing by giving the respondent a different and sometimes broader role? What exactly is being measured and how reliable is the information? There is also a growing trend to contact respondents through remote control. A considerable amount of research is being conducted using online access panels especially when it comes to international research. This development offers quite a few opportunities but on the other hand, you no longer see or hear the respondent at all. Who is participating in this type of research? What can you do and what should you not do? Which tools can be used and which not? The total lack of physical contact has its advantages but there are also a number of obvious limitations.
In this paper additional support is given to our statement that the quality of panel data must be improved before these data can be used as a firm basis for decision-making in marketing. To this end the case study is extended to cover data which refer to six brands instead of to one brand. The results are shown in the following section. Then we show the results of a formal analysis in which the differences between actual data and consumer panel data are explained by a number of exogenous variables such as price, advertising expenditures and product characteristics. From this analysis a number of guidelines is obtained which may be used to correct consumer panel data in order to decrease the data bias in consumer panel data to a significant degree. We proceed by showing the improvements in the quality of retail audit data which result from a new way of dealing with non-response in retail audits. Finally, we shall summarise our findings.
This paper deals with the results which can be expected when an intensive effort is made to attain the highest representative portrayal of the population studied, by means of eliminating non-response. The findings are based on a study in which compliant respondents were interviewed, as well as absentees and refusers.
This paper presents the synthesis of the work carried out by CEO and SOFRES with the aim oh studying in greater depth the behavior and attitudes of the public as regards collaboration on panels of limited duration. Two types of approaches are presented: a quantitative approach and the second approach, more qualitative.
This paper presents the synthesis of the work carried out by CEO and SOFRES with the aim oh studying in greater depth the behavior and attitudes of the public as regards collaboration on panels of limited duration. Two types of approaches are presented: a quantitative approach and the second approach, more qualitative.
For years now, one has been able to note ever decreasing rates of exhaustiveness in random surveys. The decrease in exhaustiveness is mainly a phenomenon of the respondents, caused by continually increasing inclination towards non-response. Up to now, the methods known for approaching this problem usually involve considerable increases in expenditures and a prolongation of dead-line, and can therefore be used but to a limited degree. Our proposal comprises a means of eliminating the decrease of representativeness due to non-responses without such an increase in expenditures. The method is therefore based on the inclusion of behavioural factors in factorial sample adjustment. In this way it can overcome the difficulty generally found in the usual demographic weightings: the latter must abstract the different behaviour of identical demographic groups, whereas our method uses different behaviours as criteria for weighting. The improvements achievable using this method are demonstrated by results of surveys and model calculations.
For years now, one has been able to note ever decreasing rates of exhaustiveness in random surveys. The decrease in exhaustiveness is mainly a phenomenon of the respondents, caused by continually increasing inclination towards non-response. Up to now, the methods known for approaching this problem usually involve considerable increases in expenditures and a prolongation of dead-line, and can therefore be used but to a limited degree. Our proposal comprises a means of eliminating the decrease of representativeness due to non-responses without such an increase in expenditures. The method is therefore based on the inclusion of behavioural factors in factorial sample adjustment. In this way it can overcome the difficulty generally found in the usual demographic weightings: the latter must abstract the different behaviour of identical demographic groups, whereas our method uses different behaviours as criteria for weighting. The improvements achievable using this method are demonstrated by results of surveys and model calculations.
In this paper, the author brings together from varying sources evidence as to the extent of the growth in refusal rates, discusses and evaluates possible causes of the increase in the percentage of selected respondents who will not co-operate and briefly suggests areas to which modern researchers' attention should be directed.
Results of an experimental investigation concerning erroneous answering, non-representativeness of respondents, revisiting of interviewees refusing to answer.
The following considerations aim at determining the criteria decisive for appreciating the value of each interview and as such for the whole study. With this in mind a study among 100 companies which may be considered as potential buyers of a special kind of machine has shown to what extent the quota of refusals differs with various categories of questions response themes. The second step was an analysis under the aspect of in how far the average quota of refusals depends on the operating characteristics of the investigated plant and on the personal characteristics of the interviewed expert.
The following considerations aim at determining the criteria decisive for appreciating the value of each interview and as such for the whole study. With this in mind a study among 100 companies which may be considered as potential buyers of a special kind of machine has shown to what extent the quota of refusals differs with various categories of questions response themes. The second step was an analysis under the aspect of in how far the average quota of refusals depends on the operating characteristics of the investigated plant and on the personal characteristics of the interviewed expert.