行銷硏究 : Marketing research

Mind, Self and Society from the Standpoint of a Social Behaviorist

Generalized Linear Models (2nd ed.)

1. Repeat‐buying: Facts, Theory and Applications. By A. S. C. Ehrenberg, ISBN 0 19 5206347. Griffin, London, 1988. 378 pp. £29.50.

Repeat-Buying: Facts, Theory and Applications

Preface Acknowledgments Theory and Methods: 1. Introduction and overview of the book 2. The BWS object case 3. The BWS profile case 4. The BWS multi-profile case 5. Basic models 6. Looking forward Applications - Case 1: 7. BWS object case application: attitudes towards end-of-life care Terry N. Flynn, Elisabeth Huynh and Charles Corke 8. How consumers choose wine: using best-worst scaling across countries Larry Lockshin and Eli Cohen 9. Best-worst scaling: an alternative to ratings data Geoffrey N. Soutar, Jillian C. Sweeney and Janet R. McColl-Kennedy Applications - Case 2: 10. When the ayes don't have it: supplementing an accept/reject DCE with a case 2 best-worst scaling task Richard T. Carson and Jordan J. Louviere 11. BWS profile case application: preferences for treatment in dentistry Emma McIntosh and Terry N. Flynn 12. BWS profile case application: preferences for quality of life in Australia Terry N. Flynn and Elisabeth Huynh Applications - Case 3: 13. The stability of aggregate-level preferences in longitudinal discrete choice experiments Towhidul Islam and Jordan J. Louviere 14. Case 3 best-worst analysis using delivered pizza and toothpaste examples Bart D. Frischknecht and Jordan J. Louviere 15. Using alternative-specific DCE designs and best and worst choices to model choices Jordan J. Louviere References Subject index Author index.

Best-Worst Scaling: Theory, Methods and Applications

Purpose – The purpose of this paper is to apply a very simple but powerful analysis of the variance‐covariance matrix of individual best‐worst scores to detect which attributes are determining utility components and drive distinct consumer segments.Design/methodology/approach – First an analysis of variance and covariance is used to find attributes which are perceived to have different importance by different consumers and which jointly drive consumer segments. Then we model consumer heterogeneity with Latent Clustering and identify utility dimensions of on‐premise wine purchase behaviour with a principal component analysis.Findings – Four consumer segments were found on the UK on‐premise market, which differ in the relative strength of five wine choice utility dimensions: ease of trial, new experience, restaurant advice, low risk food matching and cognitive choice. These segments are characterised by sociodemographics as well as wine and dine behaviour variables.Research limitations/implications – Attrib...

Is there more information in best‐worst choice data?

Past research has recognised the influence of religion on marketing, particularly the role of religious cues in marketing communications. Drawing on symbolic interactionism theory, this empirical s...

The Effects of Religious Symbols in Product Packaging on Muslim Consumer Responses

Purpose – The usual method of analysis of product attributes in marketing is to fit a multinomial logit model within a stated choice experiment, to determine the impact of attributes on the choice probability, which is equivalent to market share. The market share is intuitive and is based on each single choice in the study. However, revealed preference allows for a study into repeat purchase and loyalty, which can also be rich constructs for determining consumer preference.Design/methodology/approach – The authors introduce a loyalty measure, polarisation, and show results based on a wine data set of revealed preference. Polarisation is a function of the beta binomial distribution (BBD) and can also be a function of the Dirichlet multinomial distribution (DMD). The DMD provides a standardised or average loyalty effect for each attribute (such as wine variety), and the BBD an individual effect for each attribute level (such as cabernet) within the attribute. While the DMD results provide a rich “first‐pass...

Revealed preference analysis of red wine attributes using polarisation

The Dirichlet Model is used in marketing to provide a probability density function for the repeated purchases, by shoppers over a period of time, of the competing brands within a product category. The model is used to analyze a range of measures which report on the performance and competitive status of the brands. This Research Note provides an overview of the algebra and statistical theory of aspects of the Dirichlet Model. Specifically, it provides the algebra for using the parameter of the Dirichlet Model (or estimates) to generate the theoretical brand performance measures. These are marketing metrics such as market share, penetration, 100% loyals, share of category requirements and others. This algebra, which is critical to the further development of the Dirichlet Model, has not been previously documented. Program files to calculate the formulas are provided separately for both Excel and MATLAB.

/pdf/calculation-of-theoretical-brand-performance-measures-from-34lnzcoy92.pdf

Cam Rungie

Papers

Is there more information in best‐worst choice data?

The Effects of Religious Symbols in Product Packaging on Muslim Consumer Responses

Revealed preference analysis of red wine attributes using polarisation

Calculation of Theoretical Brand Performance Measures from the Parameters of the Dirichlet Model

Measuring and modeling the (limited) reliability of free choice attitude questions