This page has only limited features, please log in for full access.
Currently, battery electric vehicles (BEVs) constitute prominent alternatives to vehicles with combustion motors. As the competition between BEV battery manufacturers increases, it is essential that they design batteries that perfectly meet the needs of BEV manufacturers. However, the needs of BEV manufacturers are actually derivatives of the needs of BEV customers. We, therefore, conducted an empirical discrete choice experiment with BEV customers in China and performed latent class analysis. We found substantial preference heterogeneity among BEV customers, which transfers into varying needs of BEV manufacturers w.r.t. batteries. Using these results, we determined the pricing and product design strategies for BEV battery manufacturers.
Friederike Paetz. Latent Class Analysis for the Derivation of Marketing Decisions: An Empirical Study for BEV Battery Manufacturers. Statistical Learning and Modeling in Data Analysis 2021, 139 -147.
AMA StyleFriederike Paetz. Latent Class Analysis for the Derivation of Marketing Decisions: An Empirical Study for BEV Battery Manufacturers. Statistical Learning and Modeling in Data Analysis. 2021; ():139-147.
Chicago/Turabian StyleFriederike Paetz. 2021. "Latent Class Analysis for the Derivation of Marketing Decisions: An Empirical Study for BEV Battery Manufacturers." Statistical Learning and Modeling in Data Analysis , no. : 139-147.
Sustainability marketing has emerged as an important trend both in practice and academic literature. The relevant literature has heavily focused on determinations of sustainable consumer behavior, and practitioners have used these results to derive short-term marketing decisions, e.g., adequate pricing of sustainable products. However, no study has scrutinized derivations of sustainable brand personalities or provided important long-term, strategic, managerial implications for marketing managers of sustainable brands. This study aims to contribute to this underrepresented research field and makes recommendations for preferred brand personality dimensions for sustainable brands. First, the personality structure of sustainable consumers by using a preference-based two-step segmentation approach is investigated, and subsequent profiling of the sustainable consumer segment is conducted. The research relies on the results of an empirical discrete choice experiment and a personality test, including the data of a representative German consumer sample. Sustainable consumers were found to be highly agreeable and open. Second, the personality results of sustainable consumers are linked to consumers’ personality-specific preferred brand personalities. Third, recommendations for harmonic brand personality dimensions for sustainable brands, e.g., competence, excitement, and sincerity, are derived, and therefore, long-term, strategic, managerial implications are provided.
Friederike Paetz. Recommendations for Sustainable Brand Personalities: An Empirical Study. Sustainability 2021, 13, 4747 .
AMA StyleFriederike Paetz. Recommendations for Sustainable Brand Personalities: An Empirical Study. Sustainability. 2021; 13 (9):4747.
Chicago/Turabian StyleFriederike Paetz. 2021. "Recommendations for Sustainable Brand Personalities: An Empirical Study." Sustainability 13, no. 9: 4747.
Currently, social consumption constitutes a rapidly increasing trend with significant potential for companies; moreover, the characterization of social consumers is highly relevant. To date, sociodemographic variables have been widely studied but appear to be less appropriate to uniquely characterize social consumers. Psychographic variables are credited with the ability to overcome these problems, since recent studies maintain that consumers’ personal values and lifestyles are predictors of social consumption. However, personal values and lifestyle represent only two categories of psychological variables. Personality is another variable further known to be an antecedent of personal values and lifestyle. In this study, we focus on the characterization of social consumers based on both their personalities and sociodemographic variables. We conduct an empirical discrete choice experiment and investigate consumers’ personalities as a driver of consumer preferences for the fair trade (FT) label attribute. To operationalize consumers’ personalities, we use the popular five-factor approach. For the determination of consumers’ preferences, we estimate a mixed logit model including both unobserved preference heterogeneity and observed heterogeneity. Observed heterogeneity is captured by consumers’ personalities and sociodemographic variables. We find that gender, academic degree, income and four personality traits are important drivers of consumers’ social preferences. We determine the interaction effects between sociodemographic and personality variables and argue for the consideration of personality in the characterization of social consumers as the core source of social preferences. A subsequent simulation study provides further insight into marketing strategies derived from the personality-characterization of social consumers.
Friederike Paetz. Personality traits as drivers of social preferences: a mixed logit model application. Journal of Business Economics 2020, 91, 303 -332.
AMA StyleFriederike Paetz. Personality traits as drivers of social preferences: a mixed logit model application. Journal of Business Economics. 2020; 91 (3):303-332.
Chicago/Turabian StyleFriederike Paetz. 2020. "Personality traits as drivers of social preferences: a mixed logit model application." Journal of Business Economics 91, no. 3: 303-332.
In a purchase decision process, consumers often tend to choose a branded product that arouses the most positive brand affect. Recent literature identified brand personality as a central driver for brand affect and showed that consumers prefer brands that are aligned with their own personality traits. Hence, harmonization of brand personality with personality traits of the target market segments may lead to affective brand loyalty. However, focusing on consumers’ personality traits for market segmentation is challenging, since personality traits are not directly observable. Linking personality traits to easily observable variables may simplify company’s communication efforts to create brand personality. We therefore explore whether a consumer’s preference for a specific sport may serve as a predictor of the consumer’s response to brand personality and found evidence that different sport clusters differ significantly with respect to certain personality traits.
Friederike Paetz; Regina Semmler-Ludwig. Consumer’s Sport Preference as a Predictor for His/Her Response to Brand Personality. Operations Research Proceedings 2018, 61 -66.
AMA StyleFriederike Paetz, Regina Semmler-Ludwig. Consumer’s Sport Preference as a Predictor for His/Her Response to Brand Personality. Operations Research Proceedings. 2018; ():61-66.
Chicago/Turabian StyleFriederike Paetz; Regina Semmler-Ludwig. 2018. "Consumer’s Sport Preference as a Predictor for His/Her Response to Brand Personality." Operations Research Proceedings , no. : 61-66.
Friederike Paetz; Winfried J. Steiner. Utility independence versus IIA property in independent probit models. Journal of Choice Modelling 2018, 26, 41 -47.
AMA StyleFriederike Paetz, Winfried J. Steiner. Utility independence versus IIA property in independent probit models. Journal of Choice Modelling. 2018; 26 ():41-47.
Chicago/Turabian StyleFriederike Paetz; Winfried J. Steiner. 2018. "Utility independence versus IIA property in independent probit models." Journal of Choice Modelling 26, no. : 41-47.
The estimation of consumer preferences with choice-based conjoint (CBC) models is well-established. In this context, the use of Hierarchical Bayesian (HB) models, which estimate consumers’ individual preferences is nowadays state-of-the-art. However, the knowledge of consumer preferences on a less disaggregated level, like segment-level, is key for demand predictions of non-customized products. Clustering individual HB data to achieve segment-level preferences is known as inappropriate, since 2-step segmentation approaches generally underlie 1-step approaches, e.g., Latent Class models. But, may the inclusion of different concomitant variables into the clustering process of individual CBC data relax that disadvantage? To answer this question, we used an empirical data set and compared the forecasting accuracy of 1- and 2-step approaches. While demographic variables showed small effects, psychographic variables turned out to heavily improve forecasting accuracy. In particular, 2-step approaches, that consider psychographic variables within the clustering process, showed a forecasting accuracy comparable to the one of 1-step approaches.
Friederike Paetz. Improving the Forecasting Accuracy of 2-Step Segmentation Models. Operations Research Proceedings 2017, 57 -62.
AMA StyleFriederike Paetz. Improving the Forecasting Accuracy of 2-Step Segmentation Models. Operations Research Proceedings. 2017; ():57-62.
Chicago/Turabian StyleFriederike Paetz. 2017. "Improving the Forecasting Accuracy of 2-Step Segmentation Models." Operations Research Proceedings , no. : 57-62.
We propose an application of a new finite mixture multinomial conditional probit (FM-MNCP) model that accommodates preference heterogeneity and explicitly accounts for utility dependencies between choice alternatives considering both local and background contrast effects. The latter is accomplished by using a one-factor structure for segment-specific covariance matrices allowing for nonzero off-diagonal covariance elements. We compare the model to a finite mixture multinomial independent probit (FM-MNIP) model that as well accommodates heterogeneity but assumes independence. That way, we address the potential benefits of a model that additionally accounts for dependencies over a model that accommodates heterogeneity only. Our model comparison is based on empirical data for smoothies and is assessed in terms of fit, holdout validation, and market share predictions. One of the main findings of our empirical study is that allowing for utility dependencies may counterbalance the effects of considering heterogeneity, and vice versa. Additional findings from a simulation study indicate that the FM-MNCP model outperforms the FM-MNIP model with respect to parameter recovery.
Friederike Paetz; Winfried J. Steiner. The benefits of incorporating utility dependencies in finite mixture probit models. OR Spectrum 2017, 39, 793 -819.
AMA StyleFriederike Paetz, Winfried J. Steiner. The benefits of incorporating utility dependencies in finite mixture probit models. OR Spectrum. 2017; 39 (3):793-819.
Chicago/Turabian StyleFriederike Paetz; Winfried J. Steiner. 2017. "The benefits of incorporating utility dependencies in finite mixture probit models." OR Spectrum 39, no. 3: 793-819.
Klassischen Segmentierungsvariablen wie Demografie oder Psychografie wird häufig die Fähigkeit Präferenzheterogenität widerzuspiegeln abgesprochen. Daher werden zunehmend Conjoint-basierte Segmentierungsverfahren eingesetzt, die Personen präferenzbasiert klassifizieren. Im Rahmen der psychografischen Segmentierung wurden mit Wertevorstellungen und Lifestyle bisher jedoch nur zwei Variablentypen tiefergehend untersucht. Persönlichkeitsmerkmale wurden hingegen kaum betrachtet. Dieser Beitrag zeigt anhand einer empirischen Studie, dass Persönlichkeitsmerkmale, die über das Five-Factor Modell operationalisiert werden, sehr wohl ein diskriminatorisches Potential aufweisen. Dies differenziert die pauschale Aussage der Nicht-Eignung psychografischer Variablen zur Segmentierung.
Friederike Paetz. Persönlichkeitsmerkmale als Segmentierungsvariablen: Eine empirische Studie. Schmalenbachs Zeitschrift für betriebswirtschaftliche Forschung 2016, 68, 279 -306.
AMA StyleFriederike Paetz. Persönlichkeitsmerkmale als Segmentierungsvariablen: Eine empirische Studie. Schmalenbachs Zeitschrift für betriebswirtschaftliche Forschung. 2016; 68 (3):279-306.
Chicago/Turabian StyleFriederike Paetz. 2016. "Persönlichkeitsmerkmale als Segmentierungsvariablen: Eine empirische Studie." Schmalenbachs Zeitschrift für betriebswirtschaftliche Forschung 68, no. 3: 279-306.
Friederike Paetz; Winfried J. Steiner. Die Berücksichtigung von Abhängigkeiten zwischen Alternativen in Finite Mixture Conjoint Choice Modellen: Eine Simulationsstudie. Marketing ZFP 2015, 37, 90 -100.
AMA StyleFriederike Paetz, Winfried J. Steiner. Die Berücksichtigung von Abhängigkeiten zwischen Alternativen in Finite Mixture Conjoint Choice Modellen: Eine Simulationsstudie. Marketing ZFP. 2015; 37 (2):90-100.
Chicago/Turabian StyleFriederike Paetz; Winfried J. Steiner. 2015. "Die Berücksichtigung von Abhängigkeiten zwischen Alternativen in Finite Mixture Conjoint Choice Modellen: Eine Simulationsstudie." Marketing ZFP 37, no. 2: 90-100.
Die zunehmende Globalisierung der Wirtschaft erhöht weiter den Wettbewerb zwischen Unternehmen und führt dazu, dass die Erforschung und Kenntnis des Konsumentenverhaltens zur zentralen Aufgabe eines jeden Unternehmens geworden ist. Zur Bestimmung und Quantifizierung von Konsumentenpräferenzen hat sich bereits seit den siebziger Jahren des zwanzigsten Jahrhunderts die Conjoint-Analyse, deren Einführung in die Literatur auf den Artikel von Luce und Tukey (1964) zurückgeht, etabliert.
Friederike Paetz. Einleitung. Finite Mixture Multinomiales Probitmodell 2013, 1 -9.
AMA StyleFriederike Paetz. Einleitung. Finite Mixture Multinomiales Probitmodell. 2013; ():1-9.
Chicago/Turabian StyleFriederike Paetz. 2013. "Einleitung." Finite Mixture Multinomiales Probitmodell , no. : 1-9.
Im folgenden Kapitel steht die theoretische Herleitung des Finite Mixture – Multinomialen Probitmodells im Vordergrund: Im Anschluss an allgemeine, theoretische Grundlagen (vgl. Abschnitt 2.2) zu Kaufverhaltensmodellen in Abschnitt 2.2.1 und eine kurze Einführung in die Marktsegmentierung in Abschnitt 2.2.2 wird in Abschnitt 2.3 das Finite Mixture – Multinomiale Probitmodell entwickelt.
Friederike Paetz. Finite Mixture – Multinomiales Probitmodell: Theoretische Grundlagen. Finite Mixture Multinomiales Probitmodell 2013, 11 -38.
AMA StyleFriederike Paetz. Finite Mixture – Multinomiales Probitmodell: Theoretische Grundlagen. Finite Mixture Multinomiales Probitmodell. 2013; ():11-38.
Chicago/Turabian StyleFriederike Paetz. 2013. "Finite Mixture – Multinomiales Probitmodell: Theoretische Grundlagen." Finite Mixture Multinomiales Probitmodell , no. : 11-38.
Im Folgenden werden die in Kapitel 2 entwickelten Finite Mixture – Probitmodelle im Rahmen einer Simulationsstudie getestet. In Abschnitt 3.2 werden daher zunächst explizit die Ziele dieser Studie erläutert. Abschnitt 3.3 stellt die Experimentfaktoren und die aus der Kombination ihrer Faktorstufen resultierenden Treatments vor. Dazu werden die Experimentfaktoren in Abschnitt 3.3.1 tiefergehend betrachtet und ihr erwarteter Einfluss auf die Gütemaße in Abschnitt 3.3.2 diskutiert.
Friederike Paetz. Finite Mixture – Multinomiales Probitmodell: Simulationsstudie. Finite Mixture Multinomiales Probitmodell 2013, 39 -109.
AMA StyleFriederike Paetz. Finite Mixture – Multinomiales Probitmodell: Simulationsstudie. Finite Mixture Multinomiales Probitmodell. 2013; ():39-109.
Chicago/Turabian StyleFriederike Paetz. 2013. "Finite Mixture – Multinomiales Probitmodell: Simulationsstudie." Finite Mixture Multinomiales Probitmodell , no. : 39-109.
In Abschnitt 4.2 werden zunächst die Grundlagen zum Aufbau der empirischen Studie (vgl. Abschnitt 4.2.1) und die Einstellungen des Algorithmus zur Schätzung des Finite Mixture – IP Modells und des Finite Mixture – MNP Modells (vgl. Abschnitt 4.2.2) erläutert. Im Anschluss werden in Abschnitt 4.3 die Ergebnisse der Modellschätzungen bei unterschiedlichen Segmentanzahlen und die Modellselektion (vgl. Abschnitt 4.3.1) diskutiert sowie die Ergebnisse der besten Finite Mixture – IP und Finite Mixture – MNP Segment-Lösungen erläutert und miteinander verglichen (vgl. Abschnitt 4.3.2).
Friederike Paetz. Empirische Studie. Finite Mixture Multinomiales Probitmodell 2013, 111 -147.
AMA StyleFriederike Paetz. Empirische Studie. Finite Mixture Multinomiales Probitmodell. 2013; ():111-147.
Chicago/Turabian StyleFriederike Paetz. 2013. "Empirische Studie." Finite Mixture Multinomiales Probitmodell , no. : 111-147.
Hauptziel der Arbeit war der Vergleich von finiten Mischverteilungsmodellen, die auf Segmentebene Abhängigkeiten zwischen den Nutzen einzelner Alternativen zulassen bzw. Unabhängigkeit unterstellen.
Friederike Paetz. Schlussbetrachtung und Ausblick. Finite Mixture Multinomiales Probitmodell 2013, 149 -152.
AMA StyleFriederike Paetz. Schlussbetrachtung und Ausblick. Finite Mixture Multinomiales Probitmodell. 2013; ():149-152.
Chicago/Turabian StyleFriederike Paetz. 2013. "Schlussbetrachtung und Ausblick." Finite Mixture Multinomiales Probitmodell , no. : 149-152.