Analysis methods: Data fusion, matching, converging

 

How does one differentiate between findings and insights? Can it be concluded for research in the private sector that the principle difference between findings and insights is one's ability to transla ...

The paper through a case study will discuss an innovative segmentation approach that delivers actionable segmentation to marketers. It proposes segmenting consumers based on 'the cognitive mental proc ...

The key focus of this paper is to outline how different market research disciplines are starting to converge and how the consumer panel is particularly at the heart of this process, reaching this posi ...

Peter Masson, a partner at Bucknull & Masson International Media & Research, and Sue Elms, managing director of Carat Insight UK, each provide a personal view on the current state, and future, of mul ...

Tony Jarvis, chairman of the ARF blue ribbon committee who produced the ‘Guidelines for Data Integration’, looks at the value and future of single source data, fusion and data integration. He quotes ...

This paper describes a multi-method approach for measuring total television viewing of the 2000 NCAA men's basketball tournament by 18-24 year olds. The approach exploits three information sources - t ...

Collection of sufficient information on a single-source survey is a well documented barrier to multi-media evaluation. There are a number of methods used to attempt to ameliorate this information prob ...

This paper addresses the elusive quest for that one single best method for data integration. We assert that this is a fool's quest since at the heart of learning theory is the famous No Free Lunch The ...

In this chapter of the ‘Best Practice’ series, Colin McDonald looks at data fusion – the combining of data from two different surveys or databases so that they can be analysed as if they came from on ...

This paper advances the debate concerning the future of market research by presenting nine new rules to guide thought and action in a period of transition. These become the market researcher's manifes ...

This paper presents a quick data fusion algorithm (known as predictive isotonic fusion) that is customized on a case-by-case basis. The accuracy of this data fusion for target group ratings was compar ...

This paper has two purposes: first, to evaluate the commonly used methods of mixed media analysis in the light of relatively new research amongst users of such techniques; and secondly, to re-visit a ...

In this article Erwin Ephron suggests that data fusion could be an effective alternative to single source. He explains the concept of fusion and introduces a newly released example of the use of fusi ...

MRI viewing data were compared to Nielsen ratings across 84 programs to determine whether one system could serve as a single-source surrogate for the other. Exposure to TV Program was determined among ...

Report on a feasibility study by the CARF Data Integration Committee into possibilities for providing a unified product-linked media database for the whole advertising industry. Objectives and criteri ...

Discusses media-product data fusion. Arguments for and against fusion are considered. Applications for target group ratings and multimedia schedule evaluation are illustrated. Objections and problems, ...

Discusses media-product data integration, arguing that consumer analysis must precede any attempt at fusing different media. A general approach, Evaluative Frames, for constructing specific solutions ...

Discusses the potential and limitations of data integration (fusion) in the US and Canadian media context. ARF's 2000/2001 workshops on the subject. Key industry objectives summarised. Work of the Fus ...

Discusses data fusion, as now being developed in the US. Brief history of gradual acceptance of the idea, to make optimisation methods work. Describes: how fusions work, fusion laboratories, simple do ...

Response rates are among the hottest topics in the research industry. Panel research, in particular, is directly confronted with the effects of declining response rates. In the Netherlands, one of the ...

This report is a methodological proposal for creating a data fusion model whose product is an index, called Ad-Point, which integrates brand advertising investment, media management, and the real resp ...

Data fusion is a process used for the merging of separate surveys conducted with different samples of respondents. The result is a single database, enabling the user to understand the relationships be ...

This paper discusses the ways in which market researchers can work with databases within the guidelines set by The Market Research Society whereby respondent confidentiality must be maintained. It des ...

A review of single-source data which links purchasing and television viewing, whether through single-source panels or by data fusion, and its effects on media planning. The author considers the diffic ...

Discusses the problems involved in merging (or fusing) data sources: in particular market research behavioural data and lifestyle information which lists targetable individuals. The two main routes to ...

Describes an improved method of ascription as used by MRI to fill in missing data.

Discusses ascription, as used by Simmons to fill the gap between demographic and readership data (collected by personal interview) and product information (by self-completion booklet). Its advantages, ...

This paper reviews the origins of fusion, the latest extension of a well established set of statistical procedures for dealing with missing data. It describes the fusion process in non-statistical ter ...

This paper reports on AGB's introduction of a new single source type survey into the New Zealand and Australian markets. Combining the industry accepted currencies of TV viewing and print readership t ...

An explanation of how data fusion works, by matching data sets on common variables: the main problems faced when fusing two data sets (e.g. the tendency to regress to the mean): techniques for overcom ...