|
on Discrete Choice Models |
| By: | Daniel P\'erez-Troncoso |
| Abstract: | Discrete Choice Experiments (DCE) have been widely used in health economics, environmental valuation, and other disciplines. However, there is a lack of resources disclosing the whole procedure of carrying out a DCE. This document aims to assist anyone wishing to use the power of DCEs to understand people's behavior by providing a comprehensive guide to the procedure. This guide contains all the code needed to design, implement, and analyze a DCE using only free software. |
| Date: | 2020–09 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2009.11235&r=all |
| By: | Pauline Laille (Plante et Cité - Association Plante et Cité); Marianne Lefebvre (GRANEM - Groupe de Recherche Angevin en Economie et Management - UA - Université d'Angers - AGROCAMPUS OUEST - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - Institut National de l'Horticulture et du Paysage); Masha Maslianskaia-Pautrel (GRANEM - Groupe de Recherche Angevin en Economie et Management - UA - Université d'Angers - AGROCAMPUS OUEST - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - Institut National de l'Horticulture et du Paysage) |
| Keywords: | Discrete choice experiment,Pesticides,Urban green spaces,Individual preferences,France |
| Date: | 2020–02 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:hal-02867639&r=all |
| By: | Benjamin Ouvrard (TSE - Toulouse School of Economics - UT1 - Université Toulouse 1 Capitole - EHESS - École des hautes études en sciences sociales - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement); Raphaële Préget (CEE-M - Centre d'Economie de l'Environnement - Montpellier - FRE2010 - UM - Université de Montpellier - CNRS - Centre National de la Recherche Scientifique - Montpellier SupAgro - Institut national d’études supérieures agronomiques de Montpellier - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement); Arnaud Reynaud (TSE - Toulouse School of Economics - UT1 - Université Toulouse 1 Capitole - EHESS - École des hautes études en sciences sociales - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement); Laetitia Tuffery (CEE-M - Centre d'Economie de l'Environnement - Montpellier - FRE2010 - UM - Université de Montpellier - CNRS - Centre National de la Recherche Scientifique - Montpellier SupAgro - Institut national d’études supérieures agronomiques de Montpellier - Institut Agro - Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement) |
| Abstract: | In a global context of increasing water scarcity, reducing water use in the agricultural sector is one of the spearheads of sustainable agricultural and environmental policies. New technologies such as smart water meters are promising tools for addressing this issue, but their voluntary adoption by farmers has been limited. Conducting a discrete choice experiment with randomized treatments, we test two policy instruments designed to foster the voluntary adoption of smart water meters: a conditional subsidy and green nudges. The conditional subsidy is offered to farmers who adopt a smart meter only if the rate of adoption in their geographic area is sufficiently high (25%, 50% or 75%). In addition, we implement informational nudges by providing farmers specific messages regarding water scarcity and water management. With the responses of 1,272 French farmers, we show that both policy instruments are effective tools for fostering smart water meter adoption. Surprisingly, our results show that the willingness to pay for the conditional subsidy does not depend on the collective adoption threshold. We also demonstrate that farmers who receive an informational nudge are more likely to opt for a smart water meter. This result calls for a careful joint design of these two policy instruments.. |
| Keywords: | Behavioural economics,Choice experiment,Nudges,French farmers,Smart water meters,Social norms. |
| Date: | 2020–10–06 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpceem:hal-02958784&r=all |
| By: | Austin Knies; Emerson Melo |
| Abstract: | We introduce a route choice model that incorporates the notion of choice aversion in transportation networks. Formally, we propose a recursive logit model which incorporates a penalty term that accounts for the dimension of the choice set at each node of the network. We make three contributions. First, we show that our model overcomes the correlation problem between routes, a common pitfall of traditional logit models. In particular, our approach can be seen as an alternative to the class of models known as Path Size Logit (PSL). Second, we show how our model can generate violations of regularity in the path choice probabilities. In particular, we show that removing edges in the network can decrease the probability of some existing paths. Finally, we show that under the presence of choice aversion, adding edges to the network can increase the total cost of the system. In other words, a type of Braess's paradox can emerge even in the case of uncongested networks. We show that these phenomena can be characterized in terms of a parameter that measures users' degree of choice aversion. |
| Date: | 2020–10 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2010.02398&r=all |
| By: | Butler, Caroline |
| Abstract: | As the reach of mobile technology grows, it is becoming an increasingly powerful tool for access to welfare-enhancing information and services in low- and middle-income countries (LMICs). However, digital inclusion remains far from universal. Across LMICs, 14 per cent of adults still do not own a mobile phone, 39 per cent do not use mobile internet, and 38 per cent do not own a smartphone. Among other characteristics, these digitally excluded individuals are predominantly female. This study seeks to better understand the key drivers of mobile ownership, mobile internet, and smartphone use, with a particular focus on gender. Discrete-choice models, including logit, probit and linear models, are used to estimate the probability of adoption of these three types of technology. By including a suite of control variables for observable drivers of mobile adoption (e.g. education levels, age, employment, rural-urban location), the coefficient for gender represents non-observable effects which could be a product of discrimination and cultural norms. Furthermore, importance is placed on the inclusion of interaction terms in the regressions (for example, gender interacted with rural location), in order to isolate different degrees of marginalisation across the female population. In addition to the focus on gender, the marginal effects of the dependent variables for other factors (such as geography, education, employment, and age) will aid understanding of the key predictors of mobile use more generally. This research also shows how these predictors might vary by country and region, how they relate to each other, and which are the most important. This will provide relevant and important information for policy-makers. The research makes use of multiple years (2017, 2018, and 2019) of data from face-to-face consumer surveys sourced from the GSMA, which includes nationally representative samples of at least 1,000 respondents for 31 low- and middle-income countries. The wide geographic scope, and multi-year nature of the survey data results in a unique contribution to the literature, and the substantial number of observations allows for novel analysis of intersections of the female population. In summary, the initial results find that: women are 5 percentage points (pp) less likely to own a mobile phone then men, 6pp less likely to use mobile internet, and 4pp less likely to own a smartphone, even when other relevant socioeconomic and demographic factors are controlled for. This unobservable gender effect is more pronounced in certain regions, especially South Asia, but with no significant link in Latin America and Caribbean. The marginal effects of the interaction variables indicate that the negative impact is enhanced for women that live in rural areas, have low levels of literacy, and are not working. In addition, this study finds that the probability of mobile technology adoption increases (with varying magnitudes by technology type and region) with income, education, urban location, literacy, and employment. Adoption of mobile technology largely declines with age, but the impact generally does not appear to start until age 45 and above for mobile ownership. |
| Date: | 2020 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:itso20:224848&r=all |
| By: | Zheng Fang; Andres Santos; Azeem M. Shaikh; Alexander Torgovitsky |
| Abstract: | This paper considers the problem of testing whether there exists a non-negative solution to a possibly under-determined system of linear equations with known coefficients. This hypothesis testing problem arises naturally in a number of settings, including random coefficient, treatment effect, and discrete choice models, as well as a class of linear programming problems. As a first contribution, we obtain a novel geometric characterization of the null hypothesis in terms of identified parameters satisfying an infinite set of inequality restrictions. Using this characterization, we devise a test that requires solving only linear programs for its implementation, and thus remains computationally feasible in the high-dimensional applications that motivate our analysis. The asymptotic size of the proposed test is shown to equal at most the nominal level uniformly over a large class of distributions that permits the number of linear equations to grow with the sample size. |
| Date: | 2020–09 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2009.08568&r=all |
| By: | Martin Mugnier |
| Abstract: | By exploiting McFadden (1974)'s results on conditional logit estimation, we show that there exists a one-to-one mapping between existence and uniqueness of conditional maximum likelihood estimates of the binary logit model with fixed effects and the spatial configuration of data points. Our results extend those in Albert and Anderson (1984) for the cross-sectional case and can be used to build a simple algorithm that detects spurious estimates in finite samples. Importantly, we show an instance from artificial data for which the STATA's command clogit returns spurious estimates. |
| Date: | 2020–09 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2009.09998&r=all |
| By: | Hugo Kruiniger |
| Abstract: | Kitazawa (2013, 2016) showed that the common parameters in the panel logit AR(1) model with strictly exogenous covariates and fixed effects are estimable at the root-n rate using the Generalized Method of Moments. Honor\'e and Weidner (2020) extended his results in various directions: they found additional moment conditions for the logit AR(1) model and also considered estimation of logit AR(p) models with p>1. In this note we prove a conjecture in their paper and show that 2^{T}-2T of their moment functions for the logit AR(1) model are linearly independent and span the set of valid moment functions, which is a 2^{T}-2T -dimensional linear subspace of the 2^{T} -dimensional vector space of real valued functions over the outcomes y element of {0,1}^{T}. |
| Date: | 2020–10 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2010.03382&r=all |
| By: | Ruben C. Arslan; Martin Brümmer; Thomas Dohmen; Johanna Drewelies; Ralph Hertwig; Gert G. Wagner |
| Abstract: | People differ in their willingness to take risks. Recent work found that revealed preference tasks (e.g., laboratory lotteries)—a dominant class of measures—are outperformed by survey-based stated preferences, which are more stable and predict real-world risk taking across different domains. How can stated preferences, often criticised as inconsequential “cheap talk,” be more valid and predictive than controlled, incentivized lotteries? In our multimethod study, over 3,000 respondents from population samples answered a single widely used and predictive risk-preference question. Respondents then explained the reasoning behind their answer. They tended to recount diagnostic behaviours and experiences, focusing on voluntary, consequential acts and experiences from which they seemed to infer their risk preference. We found that third-party readers of respondents’ brief memories and explanations reached similar inferences about respondents’ preferences, indicating the intersubjective validity of this information. Our results help unpack the self perception behind stated risk preferences that permits people to draw upon their own understanding of what constitutes diagnostic behaviours and experiences, as revealed in high-stakes situations in the real world. |
| Keywords: | risk preferences, self-report, self-perception |
| JEL: | A12 C81 J10 |
| Date: | 2020 |
| URL: | http://d.repec.org/n?u=RePEc:ces:ceswps:_8586&r=all |
| By: | Claire Greene; Joanna Stavins |
| Abstract: | Why do US consumers pay their bills the way they do? Using data from a recent diary of consumer payment behavior, we find that the type of bill consumers are paying and how they are paying (online or automatically) are important factors in determining the payment method, in addition to the dollar value of the bill and the demographic and income profile of the individual who is paying. In contrast, dollar value and demographic attributes are found to be the most important factors determining the payment instrument chosen for purchases. Consumer choices for bill payments are somewhat constrained by requirements imposed by merchants, while the choice of payment instrument for purchases is not constrained by such requirements. The convenience and speed provided by automatic and online payments are not benefitting all US consumers equally. Unbanked consumers lack access to most payment methods and, hence, use cash or prepaid cards to pay their bills. Low-income consumers pay their bills differently from the rest of the sample: They are more likely to pay in person, use significantly more cash, and are less likely to set up automated or online bill payments, regardless of whether they have a bank account. Although consumers specify in the diary which methods they prefer to use to pay their bills, in practice they are not likely to act consistently with their stated preferences. We find that consumers who pay their bills online are less likely to deviate from their preferred payment method, while those who pay their bills automatically are more likely to deviate, after we control for income, demographic attributes, the dollar amount of the bill, and the merchant type. We find no evidence of the salience effect of automatic bill payments that Sexton (2015) finds for energy consumption. Rather, we find that consumers who pay their bills automatically have higher incomes and spend more on bills than lower-income consumers do, but that automatic bill payments are lower in value on average, which is the opposite of the finding by Sexton (2015). |
| Keywords: | bill payments; payment choice; payment preferences; consumer payments |
| JEL: | D12 D14 E42 |
| Date: | 2020–06–01 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedbwp:88884&r=all |
| By: | Dennis Guignet; Christoper Moore; Haoluan Wang |
| Abstract: | We propose a novel extension of existing semi-parametric approaches to examine spatial patterns of willingness to pay (WTP) and status quo effects, including tests for global spatial autocorrelation, spatial interpolation techniques, and local hotspot analysis. We are the first to formally account for the fact that observed WTP values are estimates, and to incorporate the statistical precision of those estimates into our spatial analyses. We demonstrate our two-step methodology using data from a stated preference survey that elicited values for improvements in water quality in the Chesapeake Bay and lakes in the surrounding watershed. Our methodology offers a flexible way to identify potential spatial patterns of welfare impacts, with the ultimate goal of facilitating more accurate benefit-cost and distributional analyses, both in terms of defining the appropriate extent of the market and in interpolating values within that market. |
| Keywords: | Bayesian; hotspot analysis; semi-parametric; spatial heterogeneity; stated preference; water quality |
| JEL: | C11 C14 Q51 Q53 |
| Date: | 2020–03 |
| URL: | http://d.repec.org/n?u=RePEc:nev:wpaper:wp202001&r=all |
| By: | Laurent Davezies; Xavier D'Haultfoeuille; Martin Mugnier |
| Abstract: | We consider fixed effects binary choice models with a fixed number of periods T and without a large support condition on the regressors. If the time-varying unobserved terms are i.i.d. with known distribution F, Chamberlain (2010) shows that the common slope parameter is point-identified if and only if F is logistic. However, he considers in his proof only T=2. We show that actually, the result does not generalize to T>2: the common slope parameter and some parameters of the distribution of the shocks can be identified when F belongs to a family including the logit distribution. Identification is based on a conditional moment restriction. We give necessary and sufficient conditions on the covariates for this restriction to identify the parameters. In addition, we show that under mild conditions, the corresponding GMM estimator reaches the semiparametric efficiency bound when T=3. |
| Date: | 2020–09 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2009.08108&r=all |