nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2015‒03‒27
six papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. A nested recursive logit model for route choice analysis By Mai, Tien; Frejinger, Emma; Fosgerau, Mogens
  2. Determining Visitor Preferences for Rhinoceros Conservation Management at Private, Ecotourism Game Reserves in the Eastern Cape Province, South Africa: A Choice Modeling Experiment By Deborah E Lee and Mario Du Preez
  3. The Individual Travel Cost Method with Consumer-Specific Values of Travel Time Savings By Mikołaj Czajkowski; Marek Giergiczny; Jakub Kronenberg; Jeffrey Englin
  4. Valuing the Effects of Air and Noise Pollution on Health Status in Turkey By Ozdamar, Oznur; Giovanis, Eleftherios
  5. Financial constraints and modes of market exit in Slovenian manufacturing and service firms By Nina Ponikvar; Katja Zajc Kejžar; Darja Peljhan
  6. Export behaviour of SMEs in the Swedish computer service industry By Falk, Martin; Hagsten, Eva

  1. By: Mai, Tien; Frejinger, Emma; Fosgerau, Mogens
    Abstract: We propose a route choice model that relaxes the independence from irrelevant alternatives property of the logit model by allowing scale parameters to be link specific. Similar to the the recursive logit (RL) model proposed by Fosgerau et al. (2013), the choice of path is modelled as a sequence of link choices and the model does not require any sampling of choice sets. Furthermore, the model can be consistently estimated and efficiently used for prediction. A key challenge lies in the computation of the value functions, i.e. the expected maximum utility from any position in the network to a destination. The value functions are the solution to a system of non-linear equations. We propose an iterative method with dynamic accuracy that allows to efficiently solve these systems. We report estimation results and a cross-validation study for a real network. The results show that the NRL model yields sensible parameter estimates and the fit is significantly better than the RL model. Moreover, the NRL model outperforms the RL model in terms of prediction.
    Keywords: route choice modelling; nested recursive logit; substitution patterns; value iterations; maximum likelihood estimation; cross-validation
    JEL: C25
    Date: 2015–03–23
  2. By: Deborah E Lee and Mario Du Preez
    Abstract: South Africa harbours 95 percent of the world’s threatened white rhinoceros (18 000) population and 40 percent of the critically endangered black rhinoceros (1 950) population. Increased levels of rhinoceros poaching in South Africa, and the imminent threat of extinction, has emphasized the need for improved management and conservation policies. This pilot study employs a discrete choice experiment in order to value selected supply-side rhinoceros management and conservation strategies at private, ecotourism game reserves in the Eastern Cape Province, South Africa. The valuation setting is couched in real-world management and conservation strategies presently under consideration at state-owned and privately-owned nature reserves in South Africa. Results suggest that visitors to private, ecotourism reserves support the sale of stockpiled rhinoceros horn (as indicated by positive and significant derived values) but are strongly opposed to the introduction of trophy hunting or the continuation of rhinoceros darting experiences (as indicated by negative and significant derived values). Based on the findings of this study, it appears that the choice experiment technique is a promising instrument, which can inform the design of rhinoceros management and conservation policies for privately-owned, ecotourism game reserves in South Africa, with the possibility of extending its use to state-owned nature reserves.
    Keywords: Discrete choice experiment, implicit price, ecotourism, game reserve, rhinoceros
    JEL: C25 Q57
    Date: 2015
  3. By: Mikołaj Czajkowski (Faculty of Economic Sciences, University of Warsaw); Marek Giergiczny (Faculty of Economic Sciences, University of Warsaw); Jakub Kronenberg (Faculty of Economics and Sociology, University of Lodz); Jeffrey Englin (Morrison School of Agribusiness, Arizona State University)
    Abstract: The treatment of the opportunity cost of travel time in travel cost models has been an area of research interest for many decades. This analysis develops a methodology to combine the travel distance and travel time data with respondent-specific estimates of the value of travel time savings. The individual travel time values are elicited with the use of discrete choice stated preference methods. The travel time valuation procedure is integrated into the valuation exercise to create a two equation structural model of site valuation. Since the travel time equation of the structural model incorporates individual preference heterogeneity full structural model provides a travel cost site demand model based upon individualized values of time. The methodology is illustrated in a study of recreational birdwatching, more specifically, visits to a stork village in Poland. We show that the usual practice of basing respondents’ value of travel time savings on their wage rate is largely unfounded.
    Keywords: contingent valuation, stated preference, validity, incentive compatibility
    JEL: Q26 Q51 Q57
    Date: 2015
  4. By: Ozdamar, Oznur; Giovanis, Eleftherios
    Abstract: This study explores the determinants of health status in Turkey. Moreover, this study explores the willingness to pay for reducing the air and noise pollution. The estimates are based on data from the annual Income and Living Conditions Survey (ILCS) in Turkey which took place in period 2006-2012. The effects of air and noise pollution on individuals’ health status and whether an individual suffers from chronic illness are estimated and their monetary value is calculated. This is the first study which examines the effects of noise and air pollution in Turkey using a great variety of econometric models as ordered Logit and binary Logit models for cross sectional data. Moreover using a pseudo panel data created based on age and region cohorts various panel data econometric approaches are followed. Regarding the health status the first model is the adapted Probit fixed effects, the “Blow-Up and Cluster” (BUC) and Ferrer-i-Carbonell and Frijters (FCF) estimators to account for intercept heterogeneity. The second approach is the Random Effects Generalized Logit Model to account for slope heterogeneity. Finally, two and three stage least squares instrumental variables approaches are followed using wind direction and regional complaint rates on air and noise pollution as instruments. Income and education are the most important determinants of health status. Based on the favoured estimates individuals who reported problems with air and noise pollution are willing to pay for air and noise quality improvement more by 20.00-21.00 Turkish Liras (TL) and 22.80-25.00 TL respectively than the individuals than did not report any complaint. Finally, the MWTP values of air and noise pollution effects on wages, working hours lost, house rents and expenses and moving dwelling are calculated.
    Keywords: Air pollution, Environmental valuation, Health Status, Noise, Pseudo-Panel
    JEL: I31 Q51 Q53 Q54
    Date: 2014–11
  5. By: Nina Ponikvar (University of Ljubljana, Faculty of Economics); Katja Zajc Kejžar (University of Ljubljana, Faculty of Economics); Darja Peljhan (University of Ljubljana, Faculty of Economics)
    Abstract: The recent financial and economic crisis has brought back the attention to studying the characteristics of surviving firms and those exiting the market. Among these characteristics the access to finance has received large attention, since the economic crisis decreased the availability of finance and increased its costs. Further, literature from industrial organization, entrepreneurship and strategic management all show that factors behind different types of firm exit decisions, such as bankruptcy, voluntary liquidation, mergers and acquisitions (M&A) differ. Our paper studies factors that influence the firm’s decision to exit the market by explicitly considering alternative firm exit modes. Our competing risk models are estimated with a standard multinomial logit model and the alternative multinomial probit model on the population of Slovenian firms in 2006-2012. We distinguish between (1) court driven exit as a result of bankruptcy or forced liquidation; (2) voluntary liquidation, (3) disappearances from the dataset as a result of mergers and acquisitions, and (4) termination based on a resolution/decision of the registration agency or according to the law. We argue that decision over whether to close down a business or to sell out to another company is influenced by financial constraints, firm specific characteristics (size, age, productivity, capital intensity), and industry factors. The paper tests whether different facets of financial constraints and other firm and industry level characteristics hold different degrees of relevance for alternative routes of the firm operations termination. In measuring financial constraints as antecedent to an exit event, we propose the exploratory factor analysis and derive to three dimensions of the financial constraint measure, i.e. liquidity, operational-efficiency factor, and profitability factor and in this way contribute to the financial constraints literature. We contribute to the firm exit literature by showing that court-driven exit, voluntary liquidation and M&A follow diverse exit routes driven by different firm level and industry characteristics. We find that the main difference between bankrupt and liquidated firms is that the choice of exiting through voluntary liquidation is characterized by economic distress while firms choosing to exit by bankruptcy are firms in financial and economic distress. Economically distressed firms have bad prospects because of low or negative profitability and little opportunity for improvement. The main characteristic of financially distressed firms is high leverage level causing problems in repaying debts. Firms that decided to exit by M&A usually have profitability problems, but are not financially distressed.
    Keywords: firm exit, financial constraints, bankruptcy, liquidation, merger and acquisition (M&A)
    JEL: G32 L25 C23
    Date: 2014–07
  6. By: Falk, Martin; Hagsten, Eva
    Abstract: Export participation of SMEs in Swedish computer services has increased rapidly over the last decade. Despite the increase, export participation rates of SMEs including micro enterprises remain rather low at 13 percent in 2010. Based on uniquely linked firm-level datasets with full coverage of micro enterprises and sole proprietors, this study investigates the determinants of export participation of Swedish SMEs in the computer service industry. Exports include both goods and services. Estimates based on the conditional logit model show a significantly positive relationship between initial labour productivity and the decision to export. An interesting and new finding is that the magnitude of the relationship between the probability to export and initial labour productivity is low once firm effects are controlled for. Surprisingly, the impact of labour productivity on exporting does not differ between micro enterprises and the remaining SMEs (10-249 employees). Furthermore, skill intensity is significantly related to the probability of exporting with low marginal effects. Overall, labour productivity and skill intensity only explain a small proportion of the export boom of Swedish software SMEs.
    Keywords: exports,productivity,computer service industry,human capital,conditional logit model
    JEL: F14
    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.