nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2015‒09‒18
eleven papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Homebuyers’ preference for installed PV systems – Discrete choice experiment By B. Glumac; W. Thomas
  2. Domestic energy prepayment and fuel poverty: Induced self-selection of housing characteristics influencing the welfare of fuel-poor households By S. Thanos; M. Karmagianni; I. Hamilton
  3. Demand for Piped Drinking Water and a formal Sewer System in Bhutan By Ngawang Dendup; Kuenzang Tshering
  4. Who are bike sharing schemes members and how they travel daily? The case of the Lyon’s “Velo’v” scheme By Charles Raux; Ayman Zoubir
  5. Measuring the effect of unobservable factors in residential choice behavior By B. Lundgren; F.Yang Wallentin
  6. Too Much Attention on Low Prices? Loss Leading in a Model of Sales with Salient Thinkers By Inderst, Roman; Obradovits, Martin
  7. Multi-level labelling: Too complex for consumers? By Weinrich, Ramona; Franz, Annabell; Spiller, Achim
  8. High school human capital portfolio and college outcomes By Guy Tchuente
  9. An existence theorem for bounds (restrictions) on the expectation of a random variable. Its opportunities for utility and prospect theories By Harin, Alexander
  10. Employment Conditions in the Senegalese Horticultural Export Industry: A Worker Perspective By VAN DEN BROECK, Goedele; VAN HOYWEGHEN, Kaat; MAERTENS, Miet
  11. Evolutionary competition and profit taxes: market stability versus tax burden By Schmitt, Noemi; Westerhoff, Frank

  1. By: B. Glumac; W. Thomas
    Abstract: Purpose - This paper contains the findings of dwelling buyers' preferences towards installed photovoltaic (PV) system on their potential homes and thus provides an insight on the overall impact of PV systems to home purchasing._Design/methodology/approach - These preferences are determined by a discrete choice model that is based on stated preference data of dwelling buyers in the Eindhoven region. Findings - The most important findings are that a PV system is on average highly appreciated by dwelling buyers and that this appreciation is relatively larger by dwelling buyers that live in more urban/central neighborhoods. Research limitations/implications - This paper is essentially exploratory and raises a number of questions for further investigation such as determining the real estate value of installed PV systems. Practical implications - The findings would suggest that the diversity of homebuyers' preferences would vary. It is dependent on the homebuyers;personal characteristics but also on institutional settings of an energy system. Therefore, the provided insight must be regarded as local and further research is necessary for understanding the impact on the European residential real estate markets. Originality/value - This paper estimates the impact of the installed PV system on the housing choice by stated choice data on the local housing market.
    Keywords: Eindhoven; Multi Nominal Logit (MNL); Preferences; Pv System; Willingness To Pay (WTP)
    JEL: R3
    Date: 2015–07–01
  2. By: S. Thanos; M. Karmagianni; I. Hamilton
    Abstract: Prepayment meters are normally installed in the UK to address the risk of non-payment from overindebted households and the literature shows a discrepancy of higher energy prices in prepayment meters. This research seeks to understand the spatial aspect of this sorting process, where prepayment meters and higher energy prices are concentrated in the areas of higher fuel poverty. A corollary research question is whether this sorting affects aspects of the consumption of housing services with respect to structural and neighbourhood characteristic. State-of-the-art latent class discrete choice models (LCM) are employed on the choice of prepayment to standard payment meter. LCM approach identifies unobservable subgroups within the population and the housing stock, allowing better understanding the impact of exposure to patterns of multiple risks, as well as the antecedents and consequences of complex behaviours. Therefore, interventions can be tailored to target the subgroups that are affected most; in this case, households vulnerable to fuel poverty affected by market failures that lead to adverse self-selection.
    Keywords: Discrete Choice Models; Energy Prices; Fuel Poverty; Housing Services; Sorting
    JEL: R3
    Date: 2015–07–01
  3. By: Ngawang Dendup; Kuenzang Tshering
    Abstract: In this study, we estimate demand for sewage connections and piped drinking water in Bhutan. To estimate household willingness to pay for these services, we use data from a sample of 18,766 households surveyed through the Bhutan Living Standard Survey of 2007 and 2012. A Hedonic model is estimated using pooled data with sub-district level fixed effects to control for heterogeneity and unobserved effects across sub-districts. The findings from our study indicate that there is significant demand for sewage and piped water connections inside dwellings. On average, unconnected urban households are willing to pay Nu 348 and Nu 362 (USD 5 to 6) per month for sewage and piped drinking water connections or 6 percent of their monthly household expenditures for each service. Un-connected urban households are willing to pay significantly more than the current joint charge of Nu 78 per month for water and sanitation. Similarly, rural households are willing to pay some 2 percent of monthly household expenditures for piped water. There is scope for municipalities in Bhutan to increase their revenues from public services and to cover potential investment costs associated with expanding services. This study also provides a baseline for designing contracts should Bhutan choose to privatize water and sanitation services.
    Keywords: Hedonic pricing method, Sanitation, Sewage, Drinking water, Valuation, Willingness to pay, Bhutan
  4. By: Charles Raux (LET - Laboratoire d'économie des transports - CNRS - UL2 - Université Lumière - Lyon 2 - École Nationale des Travaux Publics de l'État [ENTPE]); Ayman Zoubir (LET - Laboratoire d'économie des transports - CNRS - UL2 - Université Lumière - Lyon 2 - École Nationale des Travaux Publics de l'État [ENTPE])
    Abstract: This paper analyzes the socio-demographic profile and travel behavior of the “Velov” bikesharing scheme members in Lyon (France). This scheme started in 2005 and has now around 350 stations and 4500 bikes in operation, with more than 50,000 annual members. Thanks to a specific Internet-based survey more than 3,000 respondents were described by their detailed socio-demographic profile, their travel means and habits, a one-day activity-travel diary and additionally a seven days activity-travel diary log by around 700 volunteers. By this way the survey covers all travel modes and day-to-day variations in travel behavior beyond the sole use of shared bike. We analyze with a discrete choice model the socio-demographic and spatial factors affecting the probability of being an annual member of the Velov scheme. Then we explore with descriptive statistics their daily travel behavior involving as well bike sharing as other traditional modes. When possible this behavior is compared with the latest Household Travel Survey available in the Lyon area (2006). Velov annual members are rather younger and hold higher social positions when compared with the Lyon’s reference population. An individual higher social position and the residential proximity to stations have both separate and positive effects on the probability of being an annual member of the service. Velov members are not captive from public transport, they have access to a car and they are fully multimodal in their day-to-day travel behavior. Velo’v bikes are used by them for any activity, not necessarily every day, like any other travel mode.
    Keywords: Bikesharing,Lyon,annual members,one week travel diary,discrete choice model,descriptive statistics
    Date: 2015
  5. By: B. Lundgren; F.Yang Wallentin
    Abstract: Previous research has shown that it is likely that residential choice behavior is mostly affected by unobservable factors. The purpose of this research paper is to investigate the effect of heterogeneous unobservable factors in residential developments on residential choice behavior using exploratory and confirmatory factor analysis. Our results show that there are significant effects of unobservable factors on residential choice behavior. The methodology presented can be used to advise developers, architects or planners in evaluating those attributes that create value to improve, for example, the overall design solutions in real estate development projects.
    Keywords: Real Estate Development; Residential Choice Behavior; Structural Equation Modeling
    JEL: R3
    Date: 2015–07–01
  6. By: Inderst, Roman; Obradovits, Martin
    Abstract: Loss leading is analyzed in a model of promotions (as in Varian 1980) with limited consumer attention: (i) Consumers only compare prices of a selected number of products and (ii) they may pay more attention either to price or quality, depending on the salience of the respective attributes. When consumers have standard preferences, which is our benchmark case, manufacturers benefit when one-stop shopping induces retailers to discount their products, as this expands demand. Results are strikingly different when consumers are salient thinkers. When one-stop shopping or retail competition increases the scope for loss leading, manufacturers' profits decline and there may be an inefficient substitution to lower-quality products. In particular, shoppers who compare products may end up with a choice that is strictly inferior to that of non-shoppers who are locked in to a (local) retailer. Our analysis has implications both for competition policy, as we analyze the implications of a ban on loss leading, and for marketing, as we also analyze how salience affects retailers' product and promotion strategies.
    Keywords: limited attention; loss leading; manufacturer profits; product choice; promotions; quality choice; retailing; sales; salience
    JEL: D21 D43 D83 L11 L13 L15
    Date: 2015–09
  7. By: Weinrich, Ramona; Franz, Annabell; Spiller, Achim
    Abstract: As more food labels enter the retail market, it is becoming increasingly difficult for consumers to review the underlying standards of products. The most common labels communicating ethical values tend to be binary. However, many attributes, such as animal welfare, are of a continuous nature and are not binary. One solution to communicate differentiated information about the process or product standards is through the use of multi-level labels, which indicate various levels of standards. This way, consumers might realize the differences in the production or process qualities more easily. However, since multi-level labels are more complex, the impact on consumers' comprehension is not clear. The objective of this paper is to test whether a multi-level labelling approach is comprehensible for consumers and could therefore be an effective tool to communicate information about standards and thus enhancing willingness to pay. The results show that when an explanation about the levels of the label is provided, there is an increasing willingness to pay for products with higher standards of animal welfare. Hence, a multi-level label can work if information is provided.
    Keywords: labelling,multi-level labelling,binary labels,animal welfare,consumer research
    Date: 2015
  8. By: Guy Tchuente
    Abstract: This paper assesses the relationship between courses taken in high school and college major choice. Using High School and Beyond survey data, I study the empirical relationship between college performance and different types of courses taken during high school. I find that students sort into college majors according to subjects in which they acquired more skills in high school. However, I find a U-shaped relationship between the diversification of high school courses a student takes and their college performance. The underlying relation linking high school to college is assessed by estimating a structural model of high school human capital acquisition and college major choice. Policy experiments suggest that taking an additional quantitative course in high school increases the probability that a college student chooses a science, technology, engineering, or math major by four percentage points.
    Keywords: human capital; discrete choice; college major
    JEL: J24 I21
    Date: 2015–07
  9. By: Harin, Alexander
    Abstract: An existence theorem is proved for the case of a discrete random variable with finite support. If the random variable takes on values in a finite interval and there is a lower non-zero bound on its dispersion, then non-zero bounds (or non-zero “forbidden zones”) on its expectation exist near the borders of the interval. The theorem can be used in utility and prospect theories, in particular, in the analysis of Prelec’s probability weighting function.
    Keywords: probability theory; dispersion; scatter; scattering; noise; economics; utility theory; prospect theory; decision theories; human behavior; Prelec; probability weighting function;
    JEL: C1 D8 D81
    Date: 2015–09–16
    Keywords: discrete choice experiment, employment preferences, rural off-farm employment, horticultural exports, Senegal, Agribusiness, Agricultural and Food Policy, Community/Rural/Urban Development, Crop Production/Industries, International Development, Labor and Human Capital, Research Methods/ Statistical Methods, J43, Q12, Q17,
    Date: 2015–09
  11. By: Schmitt, Noemi; Westerhoff, Frank
    Abstract: The seminal cobweb model by Brock and Hommes reveals that fixed-point dynamics may turn into increasingly complex dynamics as firms switch more quickly between competing expectation rules. While policy-makers may be able to manage such rational routes to randomness by imposing a proportional profit tax, the stability-ensuring tax rate may cause a very high tax burden for firms. Using a mix of analytical and numerical tools, we show that a rather small profit-dependent lump-sum tax may even be sufficient to take away the competitive edge of cheap destabilizing expectation rules, thereby contributing to market stability.
    Keywords: cobweb models,discrete choice approach,intensity of choice,profit taxes,tax burden,stability analysis
    JEL: D84 E30 Q11
    Date: 2015

This nep-dcm issue is ©2015 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.