nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2016‒02‒23
nine papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Eliciting preferences for public goods in non-monetized communities: Accounting for preference uncertainty By Pondorfer, Andreas; Rehdanz, Katrin
  2. Modeling Economic Choice under Radical Uncertainty: Machine Learning Approaches By Gerunov, Anton
  3. An integrated algorithm for the optimal design of stated choice experiments with partial profiles By CUERVO, Daniel Palhazi; KESSELS, Roselinde; GOOS, Peter; SÖRENSEN, Kenneth
  4. Empirical Analysis of Consumer Purchase Behavior: Interaction between State Dependence and Sensitivity to Marketing-Mix Variables By Olga Novikova; Dmitriy B. Potapov
  5. Determinants of innovation in Croatian SMEs: Comparison of service and manufacturing firms By Bozic, Ljiljana; Mohnen, Pierre
  6. Impacts of geographical locations and sociocultural traits on the Vietnamese entrepreneurship By Quan-Hoang Vuong
  7. The Effects of Money Laundering (ML) on Growth: Application to the Gulf Countries By Issaoui, Fakhri; WASSIM, TOUILI; HASSEN, TOUMI
  8. The Effect of Sin Tax and Anti-Smoking Campaign in Regulating Cigarette Smokers in Davao City, Philippines By Deluna, Roperto; maneja, Kimbely
  9. How task instructions impact the creativity of designers and ordinary participants in online idea generation By Cédric Chaffois; Thomas Gillier; Mustapha Belkhouja; Yannig Roth

  1. By: Pondorfer, Andreas; Rehdanz, Katrin
    Abstract: One major challenge when conducting contingent valuation studies in developing countries is the choice of the appropriate payment vehicle. Since regular cash-income does not exist for the majority of the population and market integration is low, households in rural areas have less experience with monetary exchanges. In these cases labour time may be a more appropriate payment vehicle. A common finding of studies using labour time as the payment vehicle is that households are more often willing to contribute working time as compared to money. However, so far empirical evidence is missing if the labour time elicitation format reduces respondent's uncertainty of contributions. In this study we analyze and compare uncertainty of people's stated willingness to contribute (WTC) time and money for a local public good in a non-monetized small-scale community in Bougainville, Papua New Guinea. We do so by establishing an open-ended method for eliciting people's WTC, the Range-WTC-method, which elicits the upper and lower bound of a person's WTC. We find that uncertainty is reduced when respondents are asked for labour time contribution instead of monetary contributions. Thus, we provide empirical evidence that, indeed, labour time is the preferred to money in the elicitation of stated WTC in non-monetized communities.
    Keywords: Contingent valuation,Non-monetized community,Payment vehicles,Preference uncertainty
    JEL: D81 Q51 Q56
    Date: 2015
  2. By: Gerunov, Anton
    Abstract: This paper utilizes a novel data on consumer choice under uncertainty, obtained in a laboratory experiment in order to gain substantive knowledge of individual decision-making and to test the best modeling strategy. We compare the performance of logistic regression, discriminant analysis, naïve Bayes classifier, neural network, decision tree, and Random Forest (RF) to discover that the RF model robustly registers the highest classification accuracy. This model also reveals that apart from demographic and situational factors, consumer choice is highly dependent on social network effects.
    Keywords: choice, decision-making, social network, machine learning
    JEL: D12 D81
    Date: 2016–01
  3. By: CUERVO, Daniel Palhazi; KESSELS, Roselinde; GOOS, Peter; SÖRENSEN, Kenneth
    Abstract: Stated choice experiments are conducted to identify the attributes that drive people's preferences when choosing between competing options of products or services. They are widely used in transportation in order to support the decision making of companies and governmental authorities. A large number of attributes might increase the complexity of the choice task in a choice experiment, and have a detrimental effect on the quality of the results obtained. In order to reduce the cognitive effort required by the experiment, researchers may resort to experimental designs where the levels of some attributes are held constant within a choice situation. These designs are called partial profile designs. In this paper, we propose an integrated algorithm for the generation of D-optimal designs for stated choice experiments with partial profiles. This algorithm optimizes the set of constant attributes and the levels of the varying attributes simultaneously. An extensive computational experiment shows that the designs produced by the integrated algorithm outperform those obtained by existing algorithms, and match the optimal designs that have been analytically derived for a number of benchmark instances. We also evaluate the performance of the algorithm under varying experimental conditions and study the structure of the designs generated.
    Keywords: Stated choice experiments, Multinomial logit model, Partial profiles, (Bayesian) D-optimality, Utility-neutral designs, Coordinate-exchange algorithm
    Date: 2015–01
  4. By: Olga Novikova (National Research University Higher School of Economics); Dmitriy B. Potapov (National Research University Higher School of Economics)
    Abstract: People are intent to make similar choices especially in consumer goods markets. To address both explanations of this persistence, i.e. state dependence and heterogeneity in preferences, we use random coefficient logit model based on scanner panel data on juice purchases. The product differentiation of the chosen category allows us to model three dimensions of state dependence on brand, size and flavor characteristics. We provide evidence that the persistence in brand choices is positively correlated with persistence in size and flavor choices, thus the consumer pattern is prone to be inertial or variety seeking in every product characteristics. Simultaneously we show that the more sensitive to price and promotional activities consumers are, the less inertial is their behavior
    Keywords: State dependence, random coefficient logit, product differentiation
    JEL: M31 D12
    Date: 2015
  5. By: Bozic, Ljiljana (Institute of Economics, Zagreb); Mohnen, Pierre (UNU-MERIT, SBE, Maastricht University)
    Abstract: In this paper we focus on SMEs in Croatia operating in the manufacturing and services sectors and seek to compare them in terms of their involvement in innovation activities, the factors that determine their decision to innovate in general and in four types of innovations in particular: product/service, process, organisational and marketing innovations. The analysis relies on the Croatian Community Innovation Survey 2010 (CIS 2010) data. To find out whether innovations have a different pattern of drivers in manufacturing and in services, we estimate the probit and multivariate probit models separately on these two groups of firms. The findings reveal that despite some differences, service and manufacturing SMEs are not that different from one another when it comes to innovation activities. Service SMEs are somewhat less likely to introduce technological innovations, but manufacturing and service SMEs do not significantly differ from each other when it comes to non-technological innovations. One noteworthy difference between manufacturing and service SMEs is that the latter rely much more than the former on acquired knowledge.
    Keywords: Croatia, innovation, services, manufacturing, SME, multivariate probit
    JEL: O31 L80
    Date: 2016–02–16
  6. By: Quan-Hoang Vuong
    Abstract: This paper presents new results that are obtained from investigations into a 2015 Vietnamese entrepreneurs survey data, containing 3071 observations. Evidence found from the estimations using multinomial logits supports relationships between several sociocultural factors and entrepreneurshiprelated performance or traits has been found. Specifically, those relationships include: a) Active participation in entrepreneurs' social networks and reported value of creativity; b) CSR-willingness and reported entrepreneurs' perseverance; c) Transforming of sociocultural values and entrepreneurs' decisiveness; and, d) Lessons learned from others' failures and perceived chance of success. Using geographical locations as control variate, evaluations of the baseline-category logits models indicate their varying effects on the outcomes when combined with the sociocultural factors that are found statistically significant. Empirical probabilities that help to learn in details about behavioral patterns are provided; and toward the end, the paper offers a discussion on some striking insights and useful explanations on this entrepreneurship data set.
    Keywords: Entrepreneurship; creativity; perseverance; cultural changes; transitional economies
    JEL: L26 M13 O33
    Date: 2016–02–04
  7. By: Issaoui, Fakhri; WASSIM, TOUILI; HASSEN, TOUMI
    Abstract: the strategic goal of this paper is to study the effects of the prevention policies against money laundering on growth in the gulf countries (Saudi Arabia, Kuwait, Qatar, Bahrain, UAE and Oman) from 1980 to 2014. Thus, the logistic regression (logit model) had given three fundamental results. The first had shown that the main policies in matter of fight against money laundering (anti money laundering law AMLL, suspicious transaction reporting STR, the criminalizing of terrorist financing CTF) have had positive effects on the increasing of probabilities to realize more growth. The second is that the said policies have had positive effects on the increasing of the degree of openness of the whole sample. The third is that the variable (proximity) had a positive and significant effect on anti-money laundering policies.
    Keywords: Money laundering, growth, efficiency, gulf countries
    JEL: G14 G15
    Date: 2016–02–12
  8. By: Deluna, Roperto; maneja, Kimbely
    Abstract: This study identified the effectiveness of Sin Tax and Anti-smoking media campaign in regulating cigarette smokers in Davao City. Descriptive statistics were used to present the socio demographic, awareness of anti-smoking media campaign and perception and attitude of a smoker. Logit regression analysis was used to know the responsiveness of the smokers to Sin Tax. Result revealed that current cigarette smokers are mostly male, age group of 10-24, employed, single, smaller family size, urban and smokers having 8 to 11 years in school. Based on perception of the respondents, anti-smoking media campaign did not affect the smoking behavior of the respondents. However highest fraction of cigarette smokers are aware and reduced their cigarette consumption because of anti-smoking ordinance. The result from Logit Regression Analysis revealed that occupational status, location and number of years in schooling are significant and having positive effects on their cigarette consumption in response to Sin Tax. While gender, age, marital status, family size, change in income, price of cigarette and price of rice are insignificant variables.
    Keywords: Sin Tax, Cigarette Regulations, Anti-Smoking Campaign, Smokers Behavior
    JEL: C54 D12 I18
    Date: 2015–04–01
  9. By: Cédric Chaffois (MTS - Management Technologique et Strategique - Grenoble École de Management (GEM)); Thomas Gillier (MTS - Management Technologique et Strategique - Grenoble École de Management (GEM)); Mustapha Belkhouja (MTS - Management Technologique et Strategique - Grenoble École de Management (GEM)); Yannig Roth (Université Paris 1 Panthéon-Sorbonne)
    Abstract: Online idea generation platforms are increasingly used to generate ideas of innovative products. Crafting the problem statement carefully is a key factor of success, however, the current literature remains limited concerning what kind of task instructions should be used to increase the quality of ideas in online idea generation. This research examines three different types of task instructions. The unbounded task instructions allowed participants generating the ideas they wish without any restriction. The suggestive task instructions indicate domains of ideas that are innovative. The prohibitive task instructions indicate domains of ideas that are not innovative. The impact of these three types of task instructions on creative outcomes is compared through an empirical study on eYeka, a global online idea generation platform. Based on logit models, we found that the task instructions have a significant impact on the creativity of participants. Our result shows that prohibitive task instructions enable the production of the most original ideas whereas suggestive task instructions favor the production of the most feasible and valuable ideas. Unbounded task instructions are mostly found to be inefficient. The implications for the management of online idea generation communities are discussed. 2 " The formulation of a problem is often more essential than its solution, which may be merely a matter of mathematical or experimental. " A. Einstein, L. Infeld in The Evolution of Physics (p.92).
    Keywords: task instructions,problem formulation,idea generation,crowdsourcing,creativity,fixation effect
    Date: 2015–06–14

This nep-dcm issue is ©2016 by Edoardo Marcucci. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.