Multinomial Choice Model Research Articles

Does the Academic Rank Matter? Study on the Trip Preferences of Academicians from Different Ranks Employed at Istanbul Technical University

This study estimates a stratified multinomial logit mode choice model of the trip preferences of academicians employed at the Ayazaga campus of Istanbul Technical University. The mode choice model contains three alternatives that are dominantly preferred among academicians: private vehicle, public transport, and service vehicle modes. The data are obtained from a face-to-face questionnaire distributed to a randomly selected number of academicians working on campus. The estimated model is used for a simulation study that aims to understand the differences in modal preferences based on academic ranks and for a scenario analysis to observe the attitudes of the private vehicle users under policy changes. According to the assessment of the analyses, among academician groups of different ranks, different tendencies mostly related to income and age are recognized for actual mode choices, whereas similar approaches prioritizing convenience are noticed under suggested policy changes.

Development of a utility function for airline travel: a logarithmic goal programming approach

An airline passenger has a number of choices before he/she makes his/her travel decision. Competing airlines are also interested in the preference set of the traveller. Passenger choice modelling is an essential component of any revenue management system. In this paper, we develop a linear utility model for airline travel using a logarithmic goal programming method. The utility score of the competing airlines can help the passengers to choose the best feasible option among several alternatives. The rank can also provide a system of mechanism that compares the competing airlines in a common framework. In addition, we derive the choice probability of the airlines by a multinomial logit choice model which in turn facilitates the airlines to make a relative comparison among them and to estimate the market share.

Participation to forest conservation in National Kabore Tambi Park in Southern Burkina Faso

The main objective with this study is to investigate how different household characteristics, households' perceptions about the security of land use rights, and the households' proximity to forests affect the individual household's willingness to engage in activities that are meant to promote sustainable forest management in Burkina Faso. To achieve this objective we use a multinomial choice model of engagement (or non-engagement) in forest management activities based on household data from 4 villages surrounding the National Kabore Tambi Park in Burkina Faso. The results show that the participation by household members in forest conservation activities is mainly determined by the three variables that are related to policy: membership in community based forest management associations, security of land use rights, and training. The current training programs focus only on forest conservation practices. To be more efficient it should focus on increasing people's knowledge about the benefits due to conservation and the threats resulting from the lack of forest management. Furthermore the results indicate that improving land use right security would increase farmer's willingness to participate in forest management activities such as community work and forest surveillance. Thus particular attention should be paid to the prevailing system of land rights and its incentives, or disincentives, for promoting sustainable management of the forest resource.

The Impact of Local Labor Market Conditions on Work and Welfare Decisions: Revisiting an Old Question Using New Data

Using Maryland administrative data between 1996 and 2005, this paper examines the impact of local labor market conditions on work and welfare use among single mothers. Our estimates rely on the new Census Bureau Quarterly Workforce Indicators database, which provides county-level economic indicators filtered by industry, gender, and age-group. We specify a multinomial choice model to estimate the effects of these local labor market variables on the full set of work–welfare combinations. The results indicate that lower unemployment rates and increased new hires and new hires’ earnings in key industries increase the likelihood that women choose alternatives that include work. African American women and those with fewer years of education respond differently to changing economic conditions. Our results are robust to controls for fixed effects, county-specific time trends, and endogenous migration.

An Alternative Approach to Ml Estimation of Multinomial Choice Models

The principal assumption of a multinomial choice model is that there are a number of individuals whose properties are known; I also observe the choice of each individual, and the set of alternatives available to him. I can then construct a utility function that is associated with each of the outcomes, and estimate its parameters --- usually through the maximim likelihood method (although sometimes different methods, such as Bayesean estimation, are used). This methodology ignores additional information that is sometimes available in the problem context. Consider, for example, a problem of modeling a voter's choice in an election. On the input, one usually has data from a pre-election survey, where each respondent indicates his socio-economic characteristics, his policy preferences on a set of issues, and the political party (or candidate) he intends to vote for. In a spatial' voting model it is assumed that the voter's utility toward a party is a function of the distances between the voter's preferences on each issue, and the party's stated positions on those issues (Poole and Rosenthal, 1984; Schofield and Sened, 2006). All previous research treated party positions as exogenous and arbitrary. However, from the problem context I know that each party cares about the share of vote that it receives. I know that the observed policy positions of each party is rational, conditional on the party's utility function, the set of alternative policy positions available to the party, and the party's knowledge of the voters' decision model. That information is ignored in the traditional multinomial choice models, since the set of alternatives available to each party is not observable. This short paper proposes a methodology to incorporate this additional information in the likelihood function. In the first section, I postulate the assumptions used in this approach, and define the modified likelihood function. In the second section, I use it to re-evaluate a voting model estimated in Schofield (2007).

Incorporating Latent Variables into Discrete Choice Models — A Simultaneous Estimation Approach Using SEM Software

AbstractIntegrated choice and latent variable (ICLV) models represent a promising new class of models which merge classic choice models with the structural equation approach (SEM) for latent variables. Despite their conceptual appeal, applications of ICLV models in marketing remain rare. We extend previous ICLV applications by first estimating a multinomial choice model and, second, by estimating hierarchical relations between latent variables. An empirical study on travel mode choice clearly demonstrates the value of ICLV models to enhance the understanding of choice processes. In addition to the usually studied directly observable variables such as travel time, we show how abstract motivations such as power and hedonism as well as attitudes such as a desire for flexibility impact on travel mode choice. Furthermore, we show that it is possible to estimate such a complex ICLV model with the widely available structural equation modeling package Mplus. This finding is likely to encourage more widespread application of this appealing model class in the marketing field.

Tour-Based Time-of-Day Choices for Weekend Nonwork Activities

Research on time-of-day (TOD) choices has predominantly focused on weekday trips or activities, with few studies covering the behavior of TOD choices on weekends. This paper examines TOD choices on weekends using a tour-based approach. A multinomial discrete choice model was calibrated to explore the effects that household and individual socio-demographics have on TOD choice behavior. In light of unique travel patterns on weekends, the authors have combined both Saturday and Sunday into a single travel period, which is then divided into six TOD segments. The methodology is based on the observation that, unlike on weekdays, what individuals do on Saturdays is less likely to be repeated on Sundays with the same TOD pattern. This manuscript demonstrates the application of a tour-based TOD weekend forecast model using the 2001 Atlanta Household Survey data from Georgia. The survey contains detailed travel information on weekends. The study presents the exploratory analysis of weekend travel patterns at both trip-based and tour-based levels in Atlanta. A brief comparison of trip-based and tour-based models is also given. The study validates the suggestion that a tour-based model improves the overall goodness-of-fit of the model and produces a better forecast.

Instrumental Variables in Models with Multiple Outcomes: The General Unordered Case

This paper develops the method of local instrumental variables for models with multiple, unordered treatments when treatment choice is determined by a nonparametric version of the multinomial choice model. Responses to interventions are permitted to be heterogeneous in a general way and agents are allowed to select a treatment (e.g., participate in a program) with at least partial knowledge of the idiosyncratic response to the treatments. We define treatment effects in a general model with multiple treatments as differences in counterfactual outcomes that would have been observed if the agent faced different choice sets. We show how versions of local instrumental variables can identify the corresponding treatment parameters. Direct application of local instrumental variables identifies the marginal treatment effect of one option versus the next best alternative without requiring knowledge of any structural parameters from the choice equation or any large support assumptions. Using local instrumental variables to identify other treatment parameters requires either large support assumptions or knowledge of the latent index function of the multinomial choice model.

Examining Temporal Effects of Lifecycle Events on Transport Mode Choice Decisions

This paper describes the first results of a study on the impact of events on transport mode choice decisions. An Internet-based survey was designed to collect data concerning seven structural lifecycle events. In addition, respondents answered questions about personal and household characteristics, possession and availability of transport modes and their current travel behaviour. In total, 710 respondents completed the online survey. The complexity of transport mode choice is modelled using a Bayesian Decision Network. This paper focuses only on the time influence of events on transport mode choice decisions. We assume that people change or at least reconsider their behaviour after a structural lifecycle event, at times directly after experiencing a change and at times only after a period of time. We estimated a multinomial choice model to estimate the effect of these structural events, and in particular of the length of the time elapsed, on transport mode choice.

Nonlinear Effects in Brand Choice Models: Comparing Heterogeneous Latent Class To Homogeneous Nonlinear Models

We investigate whether the latent class multinomial logit choice model with segmentspecific linear utility functions implies effects that are similar to those of parametric homogeneous nonlinear models given that this latent class model performs at least as well. The two nonlinear models have higher-order polynomial (i.e. quadratic and cubic) and piecewise linear utility functions, respectively. Piecewise linear functions are represented by linear splines and can reproduce threshold, saturation and asymmetric effects. We evaluate models and their variants using a tenfold cross-validation. As criterion we use the geometric mean of choice probabilities across all purchases for the brand actually chosen. We measure the similarity of effects between two models by the absolute differences of choice probabilities implied by these models for varying values of a predictor. Logits of choice probabilities provide a more detailed insight into the effects implied by models. For the data set we analyze, the latent class model with linear utility is clearly superior to the two homogeneous nonlinear models. Overall, the effects implied by the latent class models are similar to those of the two parametric nonlinear models.

Integrating Human Resource and Technological Capabilities: The Influence of Global Business Strategies on Workplace Strategy Choices

Treating workplace strategies as the integration of human resource and technological capabilities, a typology of workplace strategy emphases is developed. The choice among these alternative workplace strategy emphases is treated as a function of market‐positioning priorities and the multinational scope of firms. Accordingly, a multinomial choice model is specified, which is tested against a sample of firms in the U.S. automotive supplier industry. The model obtains substantial empirical support. Among the findings is evidence consistent with the proposition that due to cross‐border, isomorphic constraints, multinational companies are less likely than national companies to pursue workplace strategies emphasizing human resource capabilities, choosing instead to favor the diffusion of workplace strategies emphasizing technological capabilities.

Behavioral Adaptations to Crowding Disturbance: Evidence from Nature Reserves in Israel

Crowding in natural settings such as nature reserves may lead to both long-and short-term spatial and temporal behavioral adjustments. This study analyzes the short-term coping process as a function of the crowding disturbance in two popular nature reserves in Israel. Using binary and multinomial choice models, a direct robust connection between the crowding disturbance and a hierarchical set of behavioral responses was found. People less sensitive to crowding tried to avoid or reduce the length of the contact by changing pace. More sensitive visitors may change route. Finally, visitors most sensitive to crowding may terminate their visit altogether.

Liquidity and the choice to abandon production in declining industries

The study presents tests of several theoretical hypotheses that are potential determinants of the choice to abandon production in declining industries. A binary qualitative choice model of the abandonment decision is estimated. The probability of choosing abandonment is found to be positively related to the firm’s debt ratio, and negatively related to liquidity at the firm level, the level of efficiency of the operating unit, and uncertainty about liquidity at the operating unit level as measured by output and input price variability. Results are also presented for a multinomial choice model accounting for the full menu of capacity decisions open to the firm over time. The results are robust across all specifications as well as to alternative statistical assumptions

A behavioral model of work-trip mode choice in Shanghai

This paper analyzes travelers' choice behavior by using data from a stated preference survey on work-trip mode choice in Shanghai. Several versions of a multinomial choice model are specified and estimated. According to the estimation results the utility function with money cost divided by income adjusted by an equivalence scale is chosen as the preferred model. Based on the estimation results from the preferred model, value of time, elasticities of aggregate mode choice with respect to income, cost, travel and waiting time, are computed. The conditional elasticities given low, middle and high adjusted income levels are calculated and discussed as well. The results obtained may be useful for transportation policy makers in Shanghai.

Simultaneous estimation of work choices and the level of farm activity using panel data

We analyse the simultaneous determination and evolution over time of work choices and the level of farm activity, using a panel of Israeli farm households. We estimate jointly a multinomial choice model of work activity and an endogenous switching regression of farm size, accounting for unobserved heterogeneity and correcting for simultaneity bias. Our results imply that some family farms tend to expand over time and specialise in farming, whereas other farm households downsize their farming operation and increase their engagement in the off-farm labour market. Therefore, the size distribution of farms is converging towards a bimodal distribution. Copyright 2006, Oxford University Press.

A Hybrid Choice Model that Uses Actual and Ordered Attribute Value Information

In the usual multinomial choice model, consumers choose to use “actual value” information; that is, utilities are continuous functions of product attributes (e.g., choices depend on actual magnitudes of price differences). The authors propose an alternative model in which consumers use only “ordered value” information; that is, utilities are functions only of the relative orderings of the attributes' values across alternatives (e.g., choices depend only on the price ordering and not on actual prices). The ordered value model is attractive because it fits well with psychological evidence that consumers often favor decision mechanisms that are cognitively less demanding. Using a supermarket shopper panel data set, the authors evaluate four models in which (1) all consumers use actual values; (2) all consumers use ordered values; (3) some consumers use actual values all the time, and some consumers use ordered values all the time; and (4) all consumers use both actual values and ordered values but with different propensities. In the analysis, the ordered value model finds stronger support than the actual value model: Model 1 outperforms Model 2; in the two hybrid choice models (Models 3 and 4), ordered value processing is more prevalent than actual value processing. These results suggest that consumers in some product categories engage more heavily in ordered value processing than in actual value processing.

THE ROLE OF CULTURAL AND DEMOGRAPHIC DIVERSITY IN CROWDING PERCEPTION: EVIDENCE FROM NATURE RESERVES IN ISRAEL

Crowding perceptions in natural settings, such as nature reserves, are an outcome of encounters between visitors to those settings. The implications of such encounters are mediated by the cultural diversity and demographic attributes of both parties to each encounter. This study explores the influence of visitors' cultural and demographic attributes and the degree of similarity between visitors and those encountered by them, on perceived crowding in two popular nature reserves in Israel. Using binary and multinomial choice models, it is seen that in Israel younger, better educated visitors of European and American descent are less tolerant of crowding than those who are older and/or of Asian-African descent. Our findings demonstrate that visitors' alikeness in terms of educational and ethnic background tends to lessen crowding perception, while demographic resemblance between the parties to encounters (primarily in terms of age) results in greater sensitivity to crowding. The findings of this study have implications for the management of nature reserves, and these are discussed here as well.

Choice-Based Segmentation As an Enrollment Management Tool

ABSTRACT This article presents an approach to enrollment management based on target marketing strategies developed from a choice-based segmentation methodology. Students are classified into “switchable” or “non-switchable” segments based on their probability of selecting specific majors. A modified multinomial logit choice model is used to identify “switchable” students and provides insight into the attributes that influence their choice.

The relationship between non-motorized mode choice and the local physical environment

By estimating multinomial choice models, this paper examines the relationship between travel mode choice and attributes of the local physical environment such as topography, sidewalk availability, residential density, and the presence of walking and cycling paths. Data for student and staff commuters to the University of North Carolina in Chapel Hill are used to illustrate the relationship between mode choice and the objectively measured environmental attributes, while accounting for typical modal characteristics such as travel time, access time, and out-of-pocket cost. Results suggest that jointly the four attributes of the local physical environment make significant marginal contributions to explaining travel mode choice. In particular, the estimates reveal that local topography and sidewalk availability are significantly associated with the attractiveness of non-motorized modes. Point elasticities are provided and recommendations given regarding the importance of incorporating non-motorized modes into local transportation planning and in the study of how the built environment influences travel behavior.

Modeling Medicare-Eligible Veterans’ Demand for Outpatient Services: A Two-Stage Approach

We apply a utility consistent, combined multinomial choice and count data model to identify factors that affect Medicare-eligible veterans’ outpatient health care usage and provider choice. Our first stage count data regression shows that a shadow cost index for visits calculated from the second stage multinomial choice model is significant in determining the Medicare-eligible veterans’ demand of outpatient services. In the second stage, we specify a multinomial choice model to study veterans’ allocation of outpatient visits between the VA and non-VA health care facilities, and find that veterans’ actual out-of-pocket cost and the distance to the health care facility have significantly negative effects on the probability of choosing the alternative. A number of other factors including family income, means of transportation, race, employment, and disability status are also found to be important at various stages of the decision making. We find some evidence of moral hazard effect in the market for private supplemental health insurance and prescription drugs, but adverse selection does not seem to be a problem for this special population.