|
on Discrete Choice Models |
| By: | Duffy, Sean; Gussman, Steven; Smith, John |
| Abstract: | We design a choice experiment where the objects are valued according to only a single attribute with a continuous measure and we can observe the true preferences of subjects. However, subjects have an imperfect perception of their own preferences. Subjects are given a choice set involving several lines of various lengths and are told to select one of them. They strive to select the longest line because they are paid an amount that is increasing in the length of their selection. Subjects also make their choices while they are required to remember either a 6-digit number (high cognitive load) or a 1-digit number (low cognitive load). We find that subjects in the high load treatment make inferior line selections and perform worse searches. When we restrict attention to the set of viewed lines, we find evidence that subjects in the high load treatment make worse choices than subjects in the low load treatment. Therefore the low quality searches do not fully explain the low quality choices. Our results suggest that cognition affects choice, even in our idealized choice setting. We also find evidence of choice overload even when the choice set is small and the objects are simple. Further, our experimental design permits a multinomial discrete choice analysis on choice among single-attribute objects with an objective value. The results of our analysis suggest that the errors in our data are better described as having a Gumbel distribution rather than a normal distribution. Finally, we observe the effects of limited cognition, consistent with memory decay and attention. |
| Keywords: | cognitive load, choice, choice overload, judgment, memory, search |
| JEL: | C91 |
| Date: | 2019–04–06 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:93126&r=all |
| By: | Dennis Kristensen; Patrick K. Mogensen; Jong Myun Moon; Bertel Schjerning |
| Abstract: | We propose to combine smoothing, simulations and sieve approximations to solve for either the integrated or expected value function in a general class of dynamic discrete choice (DDC) models. We use importance sampling to approximate the Bellman operators defining the two functions. The random Bellman operators, and therefore also the corresponding solutions, are generally non-smooth which is undesirable. To circumvent this issue, we introduce a smoothed version of the random Bellman operator and solve for the corresponding smoothed value function using sieve methods. We show that one can avoid using sieves by generalizing and adapting the `self-approximating' method of Rust (1997) to our setting. We provide an asymptotic theory for the approximate solutions and show that they converge with root-N-rate, where $N$ is number of Monte Carlo draws, towards Gaussian processes. We examine their performance in practice through a set of numerical experiments and find that both methods perform well with the sieve method being particularly attractive in terms of computational speed and accuracy. |
| Date: | 2019–04 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1904.05232&r=all |
| By: | Daniel Czarnowske; Amrei Stammann |
| Abstract: | Empirical economists are often deterred from the application of binary choice models with fixed effects mainly for two reasons: the incidental parameter bias and the computational challenge in (moderately) large data sets. We show how both issues can be alleviated in the context of binary choice models with individual and time fixed effects. Thanks to several bias-corrections proposed by Fernandez-Val and Weidner (2016), the incidental parameter bias can be reduced substantially. In order to make the estimation feasible even in panels with many fixed effects, we develop an efficient software routine, embedded in the R -package alpaca, that combines these corrections with an approach called method of alternating projections. Further, we contribute to the existing literature by conducting extensive simulation experiments in large and even unbalanced panel settings. Finally, we estimate a dynamic probit model, to study the inter-temporal labor force participation of women in Germany. |
| Date: | 2019–04 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1904.04217&r=all |
| By: | Parvaneh Shahnoori (Department of Economics, Eastern Mediterranean University, Mersin 10, Turkey and Payame Noor University, Bandar Abbas, Iran); Glenn P. Jenkins (Department of Economics, Queen's University, Kingston, Canada and Eastern Mediterranean University, North Cyprus) |
| Abstract: | This study investigates the important attributes of online banking system for Small and Medium Enterprises (SMEs) and their willingness to pay for each attribute. Zero travel and waiting time, high security, and 24/7 accessibility are the key attributes for this service. The results show that SMEs engaged in international trade value online banking services significantly more than the others. Domestically focused firms value high quality service at about $163 a month while import-focused businesses value such a service at approximately US$646 per month. Export-intensive SMEs value high quality online services 14% further, for an average of $736 per month. Revised paper published as; Valuation of the Quality Attributes of Online Banking Services by Small and Medium Enterprises Engaged in International Trade in the South African Journal of Economics Vol 87; 1 (2019) |
| Keywords: | Online banking; SME; valuation; service attributes; willingness to pay; international trade; mixed logit model. |
| JEL: | C13 C25 C93 G21 F10 |
| Date: | 2018–11 |
| URL: | http://d.repec.org/n?u=RePEc:qed:dpaper:4514&r=all |
| By: | Dancke Sandorf, Erlend (University of Stirling, Stirling Management School, Economics Division); Persson, Lars (CERE - the Center for Environmental and Resource Economics); Broberg, Thomas (CERE - the Center for Environmental and Resource Economics) |
| Abstract: | Internet panels are increasingly used for stated preference research, and members of such panels receive compensation for each completed survey. One concern is that over time this creates professional respondents who answer surveys to receive the monetary compensation. We identify professional respondents using data on panel tenure, survey response frequency, completion rates and total number of completed surveys. We find evidence of two types of professional respondents: "hyperactives" who answer surveys frequently and "experienced" who have long panel tenure and a large number of completed surveys. Using an integrated choice and latent variable model in a stated preference survey, we nd that "hyperactive" respondents are less likely to choose the 'status quo' and have a more stochastic choice process as seen from the econometrician's point of view, whereas "experienced" respondents have a relatively more deterministic choice process. Our results show that "hyperactive" respondents significantly impact estimated values. |
| Keywords: | Professional respondents; Internet panels; Discrete Choice Experiments; Integrated Choice and Latent Variable Model |
| JEL: | C35 Q51 |
| Date: | 2019–04–09 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:slucer:2019_003&r=all |
| By: | Prateek Bansal; Rico Krueger; Michel Bierlaire; Ricardo A. Daziano; Taha H. Rashidi |
| Abstract: | Variational Bayes (VB) methods have emerged as a fast and computationally-efficient alternative to Markov chain Monte Carlo (MCMC) methods for Bayesian estimation of mixed multinomial logit (MMNL) models. It has been established that VB is substantially faster than MCMC at practically no compromises in predictive accuracy. In this paper, we address two critical gaps concerning the usage and understanding of VB for MMNL. First, extant VB methods are limited to utility specifications involving only individual-specific taste parameters. Second, the finite-sample properties of VB estimators and the relative performance of VB, MCMC and maximum simulated likelihood estimation (MSLE) are not known. To address the former, this study extends several VB methods for MMNL to admit utility specifications including both fixed and random utility parameters. To address the latter, we conduct an extensive simulation-based evaluation to benchmark the extended VB methods against MCMC and MSLE in terms of estimation times, parameter recovery and predictive accuracy. The results suggest that all VB variants perform as well as MCMC and MSLE at prediction and recovery of all model parameters with the exception of the covariance matrix of the multivariate normal mixing distribution. In particular, VB with nonconjugate variational message passing and the delta-method (VB-NCVMP-Delta) is relatively accurate and up to 15 times faster than MCMC and MSLE. On the whole, VB-NCVMP-Delta is most suitable for applications in which fast predictions are paramount, while MCMC should be preferred in applications in which accurate inferences are most important. |
| Date: | 2019–04 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1904.03647&r=all |
| By: | Gabriela Demarchi (CEE-M - Centre d'Economie de l'Environnement - Montpellier - FRE2010 - INRA - Institut National de la Recherche Agronomique - UM - Université de Montpellier - CNRS - Centre National de la Recherche Scientifique - Montpellier SupAgro - Institut national d’études supérieures agronomiques de Montpellier); Subervie Julie (CEE-M - Centre d'Economie de l'Environnement - Montpellier - FRE2010 - INRA - Institut National de la Recherche Agronomique - UM - Université de Montpellier - CNRS - Centre National de la Recherche Scientifique - Montpellier SupAgro - Institut national d’études supérieures agronomiques de Montpellier); Fernando Palha Leite (CENIBRA - Celulose Nipo-Brasileira SA); Jean-Paul Laclau (UMR Eco&Sols - Ecologie fonctionnelle et biogéochimie des sols et des agro-écosystèmes - IRD - Institut de Recherche pour le Développement - INRA - Institut National de la Recherche Agronomique - Montpellier SupAgro - Centre international d'études supérieures en sciences agronomiques - Montpellier SupAgro - Institut national d’études supérieures agronomiques de Montpellier - CIRAD - Centre de Coopération Internationale en Recherche Agronomique pour le Développement) |
| Abstract: | In a climate change context, changing temperature and precipitation pattern are expected to have strong impacts on Brazilian eucalyptus plantations. Implementing adaptive water-efficient management practices is thus becoming necessary to maintain high levels of productivity while preserving the water resources. This paper investigates the ability of eucalyptus farmers to modify their current silvicultural practices in order to adapt to drought in the near future. We ran a choice experiment in the state of Minas Gerais, among 80 eucalyptus producers, who were asked to choose from several management options associated with various financial supports. The results show that adaptation by reducing the length of the eucalyptus rotation proves to be by far the preferred option, despite the associated costs. On the contrary, reducing density appears to be the least chosen option by the respondents, which may suggest that they underestimate the benefits of this strategy. We moreover find a clear and relevant segmentation of farmers'choice behavior, the general preference for reducing the length of the eucalyptus rotation being driven by themost vulnerable farmers of the sample. |
| Keywords: | Brazil,water resources,drought,choice experiment,eucalyptus |
| Date: | 2019 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:hal-02086526&r=all |
| By: | Koşar, Gizem (Federal Reserve Bank of New York); Ransom, Tyler (Oklahoma University, IZA); Van der Klaauw, Wilbert (Federal Reserve Bank of New York) |
| Abstract: | Residential mobility rates in the United States have fallen considerably over the past three decades. The cause of the long-term decline remains largely unexplained. In this paper we investigate the relative importance of alternative drivers of residential mobility, including job opportunities, neighborhood and housing amenities, social networks, and housing and moving costs, using data from two waves of the New York Fed’s Survey of Consumer Expectations. Our hypothetical choice methodology elicits choice probabilities from which we recover the distribution of preferences for location and mobility attributes without concerns about omitted variables and selection biases that hamper analyses based on observed mobility choices alone. We estimate substantial heterogeneity in the willingness to pay (WTP) for location and housing amenities across different demographic groups, with income considerations, proximity to friends and family, neighbors’ shared norms and social values, and monetary and psychological costs of moving being key drivers of migration and residential location choices. The estimates point to potentially important amplifying roles played by family, friends, and shared norms and values in the decline of residential mobility rates. |
| Keywords: | geographic labor mobility; migration; neighborhood characteristics |
| Date: | 2019–04–01 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fednsr:883&r=all |
| By: | Kayo MURAKAMI; Takanori IDA |
| Abstract: | This study investigates consumers’ status quo bias against new alternatives after deregulation in the residential electricity market in Japan. We conducted two choice experiments using online surveys before and after deregulation, and analyzed the relationship between consumers’ stated preferences and their revealed switching behaviors. The results indicate that the average Japanese consumer experiences status quo bias in electricity plan choice; consumers preferred to remain with their default provider despite the obvious 5% bill savings that could be gained from switching to a new provider. Moreover, respondents who did not switch in the real market became twice as attached to their default plan after their actual decision. In addition, respondents who switched soon after deregulation had a higher stated preference for renewable energy sources. This implies that new electricity plans that enhance clean energy have more potential to moderate consumer status quo bias in electricity plan choice. By simulating the potential share of new providers in the liberalized market, we found that a 50% renewable-energy plan has a larger potential market share than a plan that offers a 7% bill reduction under price competition. |
| Date: | 2019–04 |
| URL: | http://d.repec.org/n?u=RePEc:kue:epaper:e-19-001&r=all |
| By: | Parvaneh Shahnoori (Department of Economics, Eastern Mediterranean University, Mersin 10, Turkey and Payame Noor University, Bandar Abbas, Iran); Glenn P. Jenkins (Department of Economics, Queen's University, Kingston, Canada and Eastern Mediterranean University, North Cyprus) |
| Abstract: | This study estimates the willingness to pay of small and medium-sized enterprises (SMEs) for a business online banking services. The estimation utilizes a contingent valuation method employing data from 400 SMEs in the United Arab Emirates free zones. An interval regression model is used to identify company characteristics affecting WTP. The results indicate an average WTP for online banking of $518.50 per month. Firms engaging in international trade value these services at least 10% more than those with only domestic operations. Other variables that significantly affect WTP include number of employees and the transportation cost of using traditional branch banking. |
| Keywords: | contingent valuation method, interval regression model, willingness to pay, business online banking. |
| JEL: | C13 F10 G21 |
| Date: | 2018–12 |
| URL: | http://d.repec.org/n?u=RePEc:qed:dpaper:4511&r=all |