Chapter 3: When size does not matter: compositional data analysis in marketing research
Compositional Data analysis (CoDa) is the standard statistical methodology when data contain information about the relative importance of parts of a whole. Many research questions in marketing have to do with distribution of a whole (e.g., market share, product portfolio, spending distribution), or...
| Autores: | , , , |
|---|---|
| Tipo de documento: | capítulo de livro |
| Estado: | Versión aceptada para publicación |
| Data de publicação: | 2021 |
| País: | España |
| Recursos: | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| Repositório: | Recercat. Dipósit de la Recerca de Catalunya |
| OAI Identifier: | oai:recercat.cat:10256/26652 |
| Acesso em linha: | http://hdl.handle.net/10256/26652 |
| Access Level: | Acceso aberto |
| Palavra-chave: | Anàlisi multivariable Multivariate analysis Anàlisi de conglomerats Cluster analysis |
| Resumo: | Compositional Data analysis (CoDa) is the standard statistical methodology when data contain information about the relative importance of parts of a whole. Many research questions in marketing have to do with distribution of a whole (e.g., market share, product portfolio, spending distribution), or with relative importance (e.g., advertising content or style, preferred product attributes). CoDa solves the statistical problems that arise when treating compositional data with classical statistical methods and focuses on research questions about relative importance. In a costumer opinion platform the dominant types of reviews matter more than the number of reviews. We show how to apply the most common CoDa tools (visualization and linear models), by means of real data from an electronic word-of-mouth platform: are hotel characteristics affecting the share of valuation categories (e.g., from terrible to excellent reviews), or is it related to other compositions (e.g., by type of travelers)? |
|---|