Nearest neighbour prediction method in mixed logit discrete choice model

Mode choice behaviour is often modelled by discrete choice models, in which the utility of each mode is characterized by mode-specific parameters reflecting how strongly the utility of that mode depends on attributes such as travel speed and cost, and a mode-specific constant value. For new modes, the mode-specific parameters and the constant in the utility function of discrete choice models are not known and are difficult to estimate on the basis of stated preferences data/choice experiments and cannot be estimated on the basis of revealed preference data. This paper demonstrates how revealed preference data can be used to estimate a discrete mode choice model without using mode-specific constants and mode-specific parameters. This establishes a method that can be used to analyze any new mode using revealed preference data and discrete choice models and is demonstrated using the OViN 2017 dataset with trips throughout the Netherlands using a multinomial and nested logit model. This results in a utility function without any alternative specific constants or parameters, with a rho-squared of 0.828 and an accuracy of 0.758. The parameters from this model are used to calculate the future modal split of shared autonomous vehicles and electric steps, leading to a potential modal split range of 24–30% and 37–44% when using a multinomial logit model, and 15–20% and 33–40% when using a nested logit model. An overestimation of the future modal split occurs due to the partial similarities between different transport modes when using a multinomial logit model. It can therefore be concluded that a nested logit model is better suited for estimating the potential modal split of a future mode than a multinomial logit model. To the authors’ knowledge, this is the first time that the future modal split of shared autonomous vehicles and electric steps has been calculated using revealed preference data from existing modes using an unlabelled mode modelling approach.

Inspired by the interactive discrete choice logit models [Aggarwal, 2019], this paper presents the advanced families of discrete choice models, such as nested logit, mixed logit, and probit models to consider the interaction among the attributes. Besides the DM's attitudinal character is also taken into consideration in the computation of choice probabilities. The proposed choice models make use of Choquet integal and the recent attitudinal Choquet integral. The models are termed as Choquet nested logit (CNL), Choquet mixed multinomial logit (CMMNL), and Choquet multinomial probit (CMP). These are further extended to represent the DM's attitudinal character, and termed as attitudinal CNL, attitudinal CMMNL, and attitudinal CMP.

ABSTRACTIn order to understand the mode shift behavior of car travelers and relieve traffic congestion, a Stated Preference survey has been conducted in the city of Ji'nan in China to analyze bus choice behavior and the heterogeneity of car travelers. Several discrete choice models, including multinomial logit, mixed logit and latent class model (LCM) are developed based on these survey data. A comparative analysis indicates that the LCM has the highest precision and is more suitable to analyze the heterogeneity of car travelers. The LCM divides car travelers into three classes. Different classes have different sets of influencing factors in the model. Policy recommendations are also proposed for those classes to promote bus shift from car travelers based on the model results. Finally, sensitivity analysis on parking fees and fuel cost is carried out on the LCMs under different bus service levels. Car travelers have different sensitivities to the influencing factors. The conclusions indicate that the LCM can reflect the heterogeneity and preferences of car travelers and can be used to understand how to shift the behavior of car travelers and make more effective traffic policy.

This paper analyzes and synthesizes the fundamentals of discrete choice models. This paper alsodiscusses the basic concept and theory underlying the econometrics of discrete choice, specific choicemodels, estimation method, model building and tests, and applications of discrete choice models. Thiswork highlights the relationship between economic theory and discrete choice models: how economictheory contributes to choice modeling and vice versa.
 Keywords: Discrete choice models; Random utility maximization; Decision makers; Utility function;Model formulation

This paper develops nonparametric estimation for discrete choice models based on the mixed multinomial logit (MMNL) model. It has been shown that MMNL models encompass all discrete choice models derived under the assumption of random utility maximization, subject to the identification of an unknown distribution $G$. Noting the mixture model description of the MMNL, we employ a Bayesian nonparametric approach, using nonparametric priors on the unknown mixing distribution $G$, to estimate choice probabilities. We provide an important theoretical support for the use of the proposed methodology by investigating consistency of the posterior distribution for a general nonparametric prior on the mixing distribution. Consistency is defined according to an $L_1$-type distance on the space of choice probabilities and is achieved by extending to a regression model framework a recent approach to strong consistency based on the summability of square roots of prior probabilities. Moving to estimation, slightly different techniques for non-panel and panel data models are discussed. For practical implementation, we describe efficient and relatively easy-to-use blocked Gibbs sampling procedures. These procedures are based on approximations of the random probability measure by classes of finite stick-breaking processes. A simulation study is also performed to investigate the performance of the proposed methods.

: The Brogden optimal classification framework measures potential classification benefits of predictors by assigning applicants to the jobs that will maximize predicted performance subject to job quota constraints. Current implementations of Brogden?s framework do not include classification policy constraints (e.g., cut scores and gender restriction), applicant preferences, or the impact of other classification tools available to the Army (e.g., monetary incentives to channel applicants to particular job training). To accommodate elements of real world classification systems and thereby better inform operational problems, this research reformulated Brogden?s classification framework using discrete choice modeling. We specified a mixed multinomial logit model for classification that is mathematically equivalent to a multivariate normal based implementation of Brogden?s framework. We also proposed an empirical or sample based method for classification analysis based on the multinomial logit (MNL) model that can accommodate personnel classification policy constraints, such as cut scores and gender restriction, and is robust to the functional form and distribution of the criterion estimates. Illustrative example applications of the MNL classification model showed the expected effects of policy constraints, with practical implications for the analysis results.

This paper investigates freight market segmentation to seek the potential market of modal shift from road to rail-based intermodal (only pre- and end- haulage are transported by road), using discrete choice analysis. The Defficient design approach was used to generate SP scenarios. The data, including 2160 SP observations of 135 companies, was collected in China's Yangtze River Delta region. The multinomial logit (MNL) model, the mixed logit (ML) model, and the latent class (LC) model were constructed successively. Freight mode attributes (cost, time and reliability), shipment characteristics (distance, time threshold), cargo characteristics (value and density) were considered. In addition, the logistics elements such as the stages of production process and psychological characteristics such as choice inertia were also introduced in this paper. The results show that the LC model with segment variables performs better than the counterpart without segment variables, the MNL model and the ML model. Using the LC model, shippers are classified into four market segments. There are significant differences in shippers' preference among different classes. Based on the class membership function, the characteristic of each class can be identified by a combination of different attributes. The difficulty of achieving the modal shift from road to rail-based intermodal is ranked according to the values of attributes, further determining the priority of the potential market. This study helps to understand the shippers' freight mode choice better. Rail service suppliers can design transportation products that match the shippers' demand characteristics for different classes to improve the market share.

The study addressed the increasing complexity faced by students when selecting a university major at the Universidad de las Fuerzas Armadas – ESPE, considering the expansion of academic offerings and the changing demands of the labor market. Its objective was to identify the key determinants guiding this decision through the application of discrete choice models. The Multinomial Logit and Hierarchical Logit models were employed to examine the influence of personal, institutional, and expectation-related variables, organizing program alternatives into disciplinary categories to capture preference heterogeneity. The results showed that personal factors mainly vocation, individual interests, and long-term professional aspirations exerted the strongest influence on major selection, while institutional and economic considerations played a secondary role. The Hierarchical Logit model exhibited a superior fit compared with the Multinomial Logit model, indicating that disciplinary nesting allowed a more accurate representation of decision patterns. Additionally, expected employability and opportunities for career advancement emerged as critical motivations driving students’ choices. In conclusion, the study demonstrated that discrete choice models provided a robust methodological framework to explain educational decision-making processes, offering valuable evidence to strengthen vocational guidance, align academic programs with market demands, and support institutional planning based on empirical insights.

Discrete choice models are widely used to explain transportation behaviors, including a household's decision to own a car. They show how some distinct choice of human behavior or preference influences a decision. They are also used to project future demand estimates to support policy exploration. This latter use for prediction is indirectly aligned with and conditional to the model's estimation which aims to fit the observed data. In contrast, machine learning models are derived to maximize prediction accuracy through mechanisms such as out-of-sample validation, non-linear structure, and automated covariate selection, albeit at the expense of interpretability and sound behavioral theory. We investigate how machine learning models can outperform discrete choice models for prediction of car ownership using transportation household survey data from Singapore. We compare our household car ownership model (multinomial logit model) against various machine learning models (e.g. Random Forest, Support Vector Machines) by using 2008 data to derive, i.e. estimate models that we then use to predict 2012 ownership. The machine learning models are inferior to the discrete choice model when using discrete choice features. However, after engineering features more appropriate for machine learning they are superior. These results highlight both the cost of applying machine learning models in econometric contexts and an opportunity for improved prediction and better urban policy making through machine learning models with appropriate features.

This dissertation presents several novel contributions to the fields of technology management, entrepreneurship, organisational studies, and strategic management. The following sections outline the unique insights and new scientific findings generated through this research: ▪ This study provides a comprehensive examination of blockchain technology through the perspectives of organisation theories, including technology adoption theories and sensemaking theory, as well as two categories of Burrell and Morgan’s typology of sociological paradigms, the functionalist and interpretive paradigms. ▪ A new methodological approach is employed to examine the profiles of high-tech manufacturing enterprises within specific regional contexts, focusing on two Spanish regions. ▪ The application of novel-to-the-topic methodology, specifically two discrete choice models—the multinomial logit and mixed logit models—brings a new perspective to evaluating the likelihood of a firm’s innovation decisions on innovation novelty. ▪ This study explores the implementation of novel blockchain technology within small, early-stage businesses, shedding light on the challenges and opportunities associated with integrating blockchain into organisational processes. ▪ An actor-dependent view of external enablers has been incorporated into the external enabler theory within the context of blockchain-enabled emerging businesses. This theoretical advancement enriches the current framework by highlighting the influence of actors in shaping the adoption and dissemination of blockchain technology within organisations. ▪ The research integrates the theory of dynamic capabilities as a theoretical framework, providing a detailed analysis of the nature and function of dynamic capabilities in the establishment of new ventures. ▪ An in-depth analysis is offered on the advancement of sensing, seizing, and reconfiguring capabilities, supported by their microfoundations, within the context of early-stage companies, with particular attention given to the impact of blockchain technology. ▪ The conceptual model is constructed to demonstrate how the combination of external enablers, founders’ capabilities, and firm capabilities facilitated the formation and growth of new ventures. ▪ Two main propositions and three supporting sub-propositions are formulated that provide directions for future research. ▪ The conceptual framework is developed to illustrate how blockchain-enhanced dynamic capabilities reinforce the operations of emerging companies and sustain their competitiveness. ▪ Through the application of a case study approach, new empirical data on emerging Hungarian firms utilising blockchain was collected, addressing the deficiency in blockchain use cases. In summary, this dissertation makes significant theoretical and empirical contributions by offering novel perspectives, theoretical advancements, and empirical findings that enhance our understanding of the strategic implications of emerging technologies for organisational development and innovation.

Customer preference modelling has been widely used to aid engineering design decisions on the selection and configuration of design attributes. Recently, network analysis approaches, such as the exponential random graph model (ERGM), have been increasingly used in this field. While the ERGM-based approach has the new capability of modelling the effects of interactions and interdependencies (e.g., social relationships among customers) on customers’ decisions via network structures (e.g., using triangles to model peer influence), existing research can only model customers’ consideration decisions, and it cannot predict individual customer’s choices, as what the traditional utility-based discrete choice models (DCMs) do. However, the ability to make choice predictions is essential to predicting market demand, which forms the basis of decision-based design (DBD). This paper fills this gap by developing a novel ERGM-based approach for choice prediction. This is the first time that a network-based model can explicitly compute the probability of an alternative being chosen from a choice set. Using a large-scale customer-revealed choice database, this research studies the customer preferences estimated from the ERGM-based choice models with and without network structures and evaluates their predictive performance of market demand, benchmarking the multinomial logit (MNL) model, a traditional DCM. The results show that the proposed ERGM-based choice modelling achieves higher accuracy in predicting both individual choice behaviours and market share ranking than the MNL model, which is mathematically equivalent to ERGM when no network structures are included. The insights obtained from this study further extend the DBD framework by allowing explicit modelling of interactions among entities (i.e., customers and products) using network representations.

Enhancing algorithmic base for discrete choice modelling

Discrete choice models and the housing price and travel to work elasticities of location demand

Hybrid Choice Models: Principles and Recent Progress Incorporating Social Influence and Nonlinear Utility Functions

Discrete choice model is probably one of the most popularly used statistical methods in practice. The common feature of this model is that it considers the behavioral factors of a person and the assumption of independent individuals. However, this widely accepted assumption seems problematic because human beings do not live in isolation. They interact with each other and form complex networks. Then the application of discrete choice model to network data will allow for network dependence in a general framework. In this paper, we focus on a discrete choice model with probit error which is specified as a latent spatial autoregressive model (SAR). This model could be viewed as a natural extension of the classical SAR model. The key difference is that the network dependence is latent and unobservable. Instead, it could be measured by a binary response variable. Parameter estimation then becomes a challenging task due to the complicated objective function. Following the idea of composite likelihood, an approximated paired maximum likelihood estimator (APMLE) is developed. Numerical studies are carried out to assess the finite sample performance of the proposed estimator. Finally a real dataset of Sina Weibo is analyzed for illustration purpose.