|
on Discrete Choice Models |
| By: | Zachary Brown |
| Abstract: | Effective waste management policies are critical for addressing environmental issues ranging from climate change to pollution. This report uses new survey data to provide evidence on the most important factors in determining key waste-related outcomes at the household level. Results show that providing collection services is critical in supporting household waste prevention efforts and that charging schemes for mixed waste can play an important complementary role in supporting sustainable waste management. Based on a discrete choice experiment, most households are shown to be willing to pay a price premium for products with sustainable packaging, but at the same time, around a third of households would require a price discount in order to opt for such products. Taken together, findings from the analysis show that waste policies play an important role in stimulating demand for sustainable consumption. |
| JEL: | D1 D12 D91 Q53 C25 |
| Date: | 2024–09–13 |
| URL: | https://d.repec.org/n?u=RePEc:oec:envaaa:249-en |
| By: | Odolinski, Kristofer (Swedish National Road and Transport Research Institute (VTI)); Ek, Karin (Swedish National Road and Transport Research Institute (VTI)) |
| Abstract: | Multinomial logit models of firms’ choice of transport chain and shipment size are estimated for 16 commodity groups. The estimations are based on the Swedish Commodity Flow Survey (CFS) for 2016 and 2021 with choice data for individual shipments. The CFS is combined with cost and transport time data from the Swedish national freight transport model, Samgods, in order to estimate the impact of transport costs on firms’ transport chain and shipment size choice. Empirical midpoints of shipment sizes are included in the estimations such that the impact of ordering cost and holding cost are considered, which influences the transport cost estimates. Overall, results show that transport costs have a statistically significant impact on firm’s choice of transport, and the impact varies with respect to commodity group. |
| Keywords: | Stochastic freight model; Disaggregate freight model; Freight mode choice; Transport chain; Shipment size; Commodity flow survey |
| JEL: | R41 |
| Date: | 2024–09–09 |
| URL: | https://d.repec.org/n?u=RePEc:hhs:vtiwps:2024_005 |
| By: | Thomas Hagedorn (Institute of Transport Economics, Muenster); Jan Wessel (Institute of Transport Economics, Muenster); Marlena Meier (Institute of Transport Economics, Muenster) |
| Abstract: | This paper analyzes (i) the influence of electric bicycle (“e-bike†) ownership on transport mode choice and (ii) how a change in e-bike ownership affects carbon dioxide (CO2) emissions in Germany. Using longitudinal data from household surveys from 2016 to 2022, we first conduct a trip-level analysis with a mixed multinomial logit model (MMNL model) to estimate mode choice probabilities. The results show that the change in e-bike ownership significantly affects travel behavior, by increasing the likelihood of choosing an e-bike as means of transportation by 14.6 percentage points (p.p.), while correspondingly decreasing the likelihood of choosing other modes, especially conventional bicycles by 5.6 p.p., as well as car and public transportation by about 4 p.p. each. Second, by using observed changes in individual distances traveled and transport-mode-specific emissions values, we calculate net emissions savings per person after acquiring an e-bike. These savings amount to 526.9kg CO2 per person and year. |
| Keywords: | E-Bikes, transport mode choice, CO2 emissions, longitudinal data, mixed multinominal logit model |
| JEL: | R40 C33 Q59 |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:mut:wpaper:40 |
| By: | Rubal Dua; Prateek Bansal; Jinghai Huo (King Abdullah Petroleum Studies and Research Center) |
| Abstract: | Since the seminal work of Berry, Levinsohn, and Pakes (1995), random coefficient logit (RCL) has become the workhorse model for estimating demand elasticities in markets with differentiated products using aggregated sales data. While the ability to represent flexible substitution patterns makes RCL a preferable model, its estimation is computationally challenging due to the numerical inversion of the demand function. The recently proposed inverse product differentiation logit (IPDL) addresses these computational challenges by directly specifying the inverse demand function and representing flexible substitution patterns through nonhierarchical product segmentation in multiple dimensions. Unlike the two-stage simulation-based estimation of RCL, IPDL requires the estimation of a traditional linear instrumental variable (IV) regression model. In theory, IPDL appears to be an attractive alternative to RCL, but its potential has not yet been explored in empirical studies. We present the first application of IPDL in understanding the demand for passenger cars in China using provincial-level sales data. Our results indicate that the elasticity estimates of IPDL and RCL are not significantly different, i.e., that IPDL can capture substitution patterns in a similar manner as can RCL. The estimation of IPDL takes less than a second on a regular computer (i.e., it is approximately 500 times faster than RCL). Overall, the flexibility and computational efficiency of IPDL makes it a workhorse model for demand estimation using market-level aggregated sales data. |
| Date: | 2023–12–26 |
| URL: | https://d.repec.org/n?u=RePEc:prc:mpaper:ks--2023-mp05 |
| By: | Alyssa Carlson (Department of Economics, University of Missouri); Anastasia Semykina (Royal Melbourne Institute of Technology) |
| Abstract: | We present a general framework for nonlinear dynamic panel data models subject to missing outcomes due to endogenous attrition. We consider two cases of attrition. First, ignorable attrition where the distribution of the outcome does not depend on missingness conditional on the unobserved heterogeneity. Second, non-ignorable attrition where the conditional distribution of the outcome does depend on attrition. In either case, a major challenge posed by the dynamic specification is the inherent correlation between the lagged dependent variable and unobserved individual heterogeneity. Our key assumption is that the distribution of the unobserved heterogeneity does not depend on attrition conditional on observed covariates and initial condition. The resulting estimator is a joint MLE that accommodates a dynamic specification, correlated unobserved heterogeneity, and endogenous attrition. We discuss the derivation and estimation of the average partial effects within this framework and provide examples for the binary response, ordinal response, and corner solution cases. Finite sample properties are studied using Monte Carlo simulations. As an empirical application, the proposed method is applied to estimating a dynamic health model for older women. |
| Keywords: | attrition, dynamic, nonlinear, panel data, correlated random effects |
| JEL: | C23 C24 C25 |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:umc:wpaper:2408 |
| By: | Holger Gerhardt (University of Bonn); Rafael Suchy (University of Oxford, UK) |
| Abstract: | We propose an easy-to-use method for estimating preference parameters experimentally: choices from strictly concave budget restrictions (SCBRs). SCBRs generalize the popular method of analyzing choices from linear budget restrictions (LBRs). SCBRs promise (i) to improve the informational content of individual choices by reducing the number of corner allocations and (ii) to increase the range of identifiable behavioral types. Two online studies on risk and time preferences confirm the benefits of SCBRs vis-à-vis LBRs: (i) They reduce corner allocations drastically and make more participants estimable individually. (ii) They elicit a richer distribution of preference parameters, specifically, distinguishing linear from convex utility. |
| Keywords: | Preference elicitation, time preferences, risk preferences, budget constraints |
| JEL: | C91 D01 D81 D90 |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:ajk:ajkdps:336 |
| By: | Leonardo Matone; Ben Abramowitz; Nicholas Mattei; Avinash Balakrishnan |
| Abstract: | Aggregating the preferences of multiple agents into a collective decision is a common step in many important problems across areas of computer science including information retrieval, reinforcement learning, and recommender systems. As Social Choice Theory has shown, the problem of designing algorithms for aggregation rules with specific properties (axioms) can be difficult, or provably impossible in some cases. Instead of designing algorithms by hand, one can learn aggregation rules, particularly voting rules, from data. However, the prior work in this area has required extremely large models, or been limited by the choice of preference representation, i.e., embedding. We recast the problem of designing a good voting rule into one of learning probabilistic versions of voting rules that output distributions over a set of candidates. Specifically, we use neural networks to learn probabilistic social choice functions from the literature. We show that embeddings of preference profiles derived from the social choice literature allows us to learn existing voting rules more efficiently and scale to larger populations of voters more easily than other work if the embedding is tailored to the learning objective. Moreover, we show that rules learned using embeddings can be tweaked to create novel voting rules with improved axiomatic properties. Namely, we show that existing voting rules require only minor modification to combat a probabilistic version of the No Show Paradox. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.13630 |
| By: | Patrick Joel Turkson (Methodist University Ghana); Felix Amoah (Nelson Mandela University, South Africa); Joseph Gyamfi Yeboah (Methodist University Ghana); Elizabeth Afia Primang Turkson (Elitek International School, Ghana); Laura Novienyo Abla Amoah (Nelson Mandela University, South Africa) |
| Abstract: | This study examined online shopping by highlighting the variations in consumer profiles using selected variables such as gender, age, highest educational level, and marital status. Data was collected through an online survey sent via email to respondents. The online survey was conducted within four months in 2023. A convenience sampling technique was employed to select the total respondents of 437, which constituted the sample size of the study. A 100% response rate was attained. Descriptive statistics, comparing means, and the ANOVA test were employed to analyze the data collected. SPSS version 26 was the statistical tool used for the analysis of the collected data. The study revealed that males aged between 31 and 40, post-graduates, and single mothers mostly shop online frequently. Differences in gender, age, and marital status influence online shopping, however, the highest educational level does not influence online shopping. |
| Keywords: | Online shopping, gender, age, marital status and highest educational level |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:smo:raiswp:0417 |