ECONOMETRIC ASSESSMENT OF CUSTOMERS’ PERSONALITY BIASES AND COMMUNICATION PREFERENCES CORRELATION
Name and surname of author:
Katarina Kostelić, Danijela Križman Pavlović
Personality traits/biases, logistic regression, consumer decision-making, communication preferences
DOI (& full text):
The tendency of bias identification and quantification with the goal of better estimation and prediction, grows. The purpose of this paper is to question how deep analysis is necessary to increase…more
The tendency of bias identification and quantification with the goal of better estimation and prediction, grows. The purpose of this paper is to question how deep analysis is necessary to increase prediction of communication preferences given the customer’s personality traits/biases. Examined communication preferences regard to the communication approach, language use and information sharing.
This paper offers a psychometric assessment of the personality estimates and traits, as well as econometric examination of correlation to consumer first-choice communication preferences using linear logit model with binomial dependent variable.
The results point out that the more detail analysis provides more accurate predictions, to the point where estimators as regressors for communication choices provide more accurate prediction than the use of the personality traits as independent variables.
Paper delivers empirical assessment of consumers’ communication preferences using primary data set. Practical implications relate to the use of the findings in communication with consumers in online and/ or digital marketing communication. One of the possible practical use of the results can be as an input for the recommendation agents. Theoretical implications of the findings request questioning the use of the personality traits as an interim stage in decision-making predictions. In addition, these findings fill the gap in the field of communication preference based on personality traits and personality estimators.
The data set has been previously used for the doctoral thesis research. For the purpose of this research, data was re-coded and analyzed using different approach, namely binomial logistic regression.