Comparação dos métodos soma constante e análise conjunta de fatores para estimar a importância relativa

• Ano de defesa: 2010
• Autor(a) principal: Dias, Adriana
• Orientador(a): Silva, Carlos Henrique Osório
• Banca de defesa: Peternelli, Luiz Alexandre , Cecon, Paulo Roberto , Silva, Fabyano Fonseca e
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Viçosa
• Programa de Pós-Graduação: Mestrado em Estatística Aplicada e Biometria
• Departamento: Estatística Aplicada e Biometria
• País: BR
• Palavras-chave em Português: Análise conjunta de fatores; Soma constante; Validação de estimativas de importância relativa; Bebida láctea sabor café
• Palavras-chave em Inglês: Constant sum; Conjoint analysis; Validation of estimates of relative importance; Milk drink flavored coffee
• Área do conhecimento CNPq: CNPQ::CIENCIAS AGRARIAS
• Link de acesso: http://locus.ufv.br/handle/123456789/4028

Conjoint Analysis (CA) and the Constant Sum (CS) approach were both applied in a consumer preference study in order to estimate Relative Importance (RI%) of attributes. The main goal of this study was to verify if the CS approach can be used to evaluate estimates of RI% obtained from CA. A sample of 192 consumers, residents of Viçosa city, Minas Gerais State, evaluated 8 alternative packages of a milk based drink, formed by the combination of 3 factors with two levels each: Size (200mL and 1000mL), name (coffee and chocolate flavor and chocolate and coffee flavor) and information decaffeinated (with and without). We applied Descriptive (Box and Whisker plots, descriptive measures and dispersion plots) and inferential (paired and independent two sample t tests, general linear hypothesis tests) statistical analysis were applied using estimates of RI obtained from both methods and we concluded that CS does not provide a good evaluation for estimates obtained from CA, although this method can be used as a prior study in order to select factors for a CA study, specially when there exists many candidate factors.