Behavioral frontiers in choice modeling

We review the discussion at a workshop whose goal was to achieve a better integration among behavioral, economic, and statistical approaches to choice modeling. The workshop explored how current approaches to the specification, estimation, and application of choice models might be improved to better capture the diversity of processes that are postulated to explain how consumers make choices. Some specific challenges include how to capture and parsimoniously describe heterogeneous mixes of heuristic choice rules, methods for building realistic models of choice, and nontraditional methods for estimating models. An agenda for important future work in these areas is also proposed.     

Advances in random utility models report of the workshop on advances in random utility models duke invitational symposium on choice modeling behavior

In recent years, major advances have taken place in three areas of random utility modeling: (1) semiparametric estimation, (2) computational methods for multinomial probit models, and (3) computational methods for Bayesian estimation. This paper summarizes these developments and discusses their implications for practice.     

Estimating the Duplicated Audience of Media Vehicles in National Advertising Schedules

Abstract

This paper tests and evaluates the best available methods for estimating the duplicated audience of pairs of television programs, pairs of magazines and television-magazine pairs. Previous research in audience duplication estimation is surveyed, and the best existing methods for some situations are found to be inadequate or nonexistent. Improved estimation methods are provided for these cases. In particular, new models are developed for estimating the duplication of audiences of different episodes of a television program, and for estimating duplication of audience within particular target markets. The various models are empirically tested using diary data from a large, national sample.     

A new use of importance sampling to reduce computational burden in simulation estimation

Simulation estimators (Lerman and Manski 1981; McFadden, Econometrica 57(5):995–1026, 1989; Pakes and Pollard, Econometrica 57:1027–1057, 1989) have been of great use to applied economists and marketers. They are simple and relatively easy to use, even for very complicated empirical models. That said, they can be computationally demanding, since these complicated models often need to be solved numerically, and these models need to be solved many times within an estimation procedure. This paper suggests methods that combine importance sampling techniques with changes-of-variables to address this caveat. These methods can dramatically reduce the number of times a particular model needs to be solved in an estimation procedure, significantly decreasing computational burden. The methods have other advantages as well, e.g. they can smooth otherwise non-smooth objective functions and can allow one to compute derivatives analytically. There are also caveats—if one is not careful, they can magnify simulation error. We illustrate with examples and a small Monte-Carlo study.     

Modeling Methods for Discrete Choice Analysis

This paper introduces new forms, sampling and estimation approaches fordiscrete choice models. The new models include behavioral specifications oflatent class choice models, multinomial probit, hybrid logit, andnon-parametric methods. Recent contributions also include new specializedchoice based sample designs that permit greater efficiency in datacollection. Finally, the paper describes recent developments in the use ofsimulation methods for model estimation. These developments are designed toallow the applications of discrete choice models to a wider variety ofdiscrete choice problems.     

Understanding two‐sided persuasion: An empirical assessment of theoretical approaches

This study tries to evaluate empirically the validity and generality of causal models based on alternative theories and the integrative frame‐work provided by Crowley and Hoyer (1994) to explain the underlying persuasive mechanisms of two‐sided messages in marketing. In addition to an empirical test of the models, the study theoretically discusses and empirically explores suggestions for model modifications. Applying meta‐analytic‐based causal estimation, the results show that the parsimonious model based on attribution theory provides high generality and affirms the prevalent use of the theory in previous studies. All other models could be meaningfully improved by integrating alternative processes of less‐effortful message elaboration as suggested by dual‐process theories. The results suggest that the impact of argument quality in two‐sided messages is in line with previous models assuming effortful message elaboration, while less‐effortful elaboration processes seem to rely on the number of arguments used in two‐sided messages. © 2007 Wiley Periodicals, Inc.     

Staying Power of Churn Prediction Models

In this paper, we study the staying power of various churn prediction models. Staying power is defined as the predictive performance of a model in a number of periods after the estimation period. We examine two methods, logit models and classification trees, both with and without applying a bagging procedure. Bagging consists of averaging the results of multiple models that have each been estimated on a bootstrap sample from the original sample. We test the models using customer data of two firms from different industries, namely the internet service provider and insurance markets. The results show that the classification tree in combination with a bagging procedure outperforms the other three methods. It is shown that the ability to identify high risk customers of this model is similar for the in-period and one-period-ahead forecasts. However, for all methods the staying power is rather low, as the predictive performance deteriorates considerably within a few periods after the estimation period. This is due to the fact that both the parameter estimates change over time and the fact that the variables that are significant differ between periods. Our findings indicate that churn models should be adapted regularly. We provide a framework for database analysts to reconsider their methods used for churn modeling and to assess for how long they can use an estimated model.     

Combining revealed and stated preferences data

Our objective is to develop a unifying framework for the incorporation of different types of survey data in individual choice models. We describe statistical methodologies that combine multiple sources of data in the estimation of individual choice models and summarize the current state of the art of data combination methods that have been used with market research data. The most successful applications so far have combined revealed and stated preference data. We discuss different types of market and survey data and provide examples of research contexts in which one might wish to combine them. Although these methods show a great deal of promise and have already been used successfully in a number of applications, several important research issues remain. A discussion of these issues and directions for further research conclude the paper.     

Advances in computation,statistical methods,and testing of discrete choice models

This paper gives a brief overview of recent developments in computation, estimation, and statistical testing of choice models, with marketing applications. Topics include statistical models for discrete panel data with heterogeneous decision-makers, simulation methods for estimation of high-dimension multinomial probit models, specification tests for model structure and for brand and purchase clustering, and innovations in numerical analysis for estimation and forecasting. In collaboration with Denis Bolduc, David Bunch, Michael Keane, Don Kridel, and Steve Stern.     

Discrete and Continuous Representations of Unobserved Heterogeneity in Choice Modeling

We attempt to provide insights into how heterogeneity has been and can be addressed in choice modeling. In doing so, we deal with three topics: Models of heterogeneity, Methods of estimation and Substantive issues. In describing models we focus on discrete versus continuous representations of heterogeneity. With respect to estimation we contrast Markov Chain Monte Carlo methods and (simulated) likelihood methods. The substantive issues discussed deal with empirical tests of heterogeneity assumptions, the formation of empirical generalisations, the confounding of heterogeneity with state dependence and consideration sets, and normative segmentation.     

An adaptive nonlinear approach for estimation of consumer satisfaction and loyalty in mobile phone sector of India

To facilitate business growth assessment of customer׳s, satisfaction and loyalty levels in mobile sector are two important issues which need in-depth investigation. These two levels of customers are nonlinearly related to their corresponding attributes. The past studies have mostly assumed linear relation and have mostly used regression based models for estimation of these levels and the results are not encouraging. To overcome this limitation, the present study has developed simple nonlinear models for accurate estimation of these two parameters using their related key factors and results obtained are shown to be much better. This paper has also observed the positive effect of satisfaction on the loyalty estimation of customers. Employing the proposed nonlinear adaptive models, the service provider can also predict the satisfaction and loyalty levels of each of its customers which help the organization to determine the number of possible future churners.     

几种发射分集OFDM系统信道估计方法性能评估

给出了3种基于发射分集的OFDM系统信道估计方法,分别从训练序列对算法的影响、估计准确度、算法复杂度和算法适用性等方面对各自性能作了分析比较,并进行了仿真.分析比较和仿真结果表明,训练序列对3种算法的影响很大,通过训练序列的正交化设计,LS和EM算法可以得到很大程度的简化;EM算法与LS算法估计精度相当,信噪比较大时,多项式模型算法估计精度要远远高于LS和EM算法;总体上来说,多项式模型算法复杂度最高,EM算法复杂度最低.     

A Comparison of Conjoint Methods When There Are Many Attributes

This paper compares several methods of performing conjoint analysis when there is a large number of attributes. National parks were described in terms of 17 attributes and 56 levels. Subjects were randomly assigned to one of four groups and each person responded to a calibration questionnaire that allowed the estimation of one of the following conjoint analysis models: full profile, ACA, individual-level hybrid, or full profile on the person's eight stated most important attributes. Validations were performed in terms of individual choices and aggregate choice shares. Reliabilities were assessed on both ratings and choices.Surprisingly even with a large number of attributes, the full profile method consistently validated best. Second was a full profile model estimated on the respondent's stated eight most important attributes. ACA and individual hybrid conjoint analysis performed similarly, but worse than these two methods on most measures. Validation differences were more strongly related to differences in attribute importances than desirabilities for levels within an attribute. It appears that these respondents were not able to accurately report self-explicated importances with a large number of attributes.     

Single vs simultaneous equation models in capital asset pricing: The role of firm-related variables

An alternative modeling system that more adequately describes the returns-generating process than the usual single equation CAPM is provided in this paper. Firm-related variables are introduced directly into the model using a simultaneous equation system while avoiding the estimation problems of previous attempts. While not empirically testing this system with the single-equation “multi-beta” models, the relationships between the alternative processes are explored.     

均值计数模型下汽车保险索赔频数的估计方法

汽车保险的索赔频数预测问题是非寿险精算理论和应用研究的一个重要内容。但是，在含有高维附加信息的情形下，传统的估计方法就不再适用。本文在均值计数模型基础上，利用凸惩罚函数进行变量选择，找到影响车险索赔频数的显著性因子，并通过模拟和实例分析来评价该模型和所提出的方法的可行性。     

Use of two-limit probit regression model : An analysis of lender response to loan requests

Research problems where the observed dependent variable is restricted to lie within an interval with massing of some of the observations at the limiting values of the interval are frequent in business research studies. This paper analyzes one such problem—that of lender response to a business loan application. The unique features of a regression model with a doubly limited dependent variable are explained and interpreted. Parameter estimation for such models is undertaken by maximum-likelihood techniques. In this paper maximum likelihood estimates are obtained for an empirical problem and compared with ordinary least-squares estimators. Results show substantial differences between least-squares and maximum-likelihood estimates, indicating a possibility for serious errors by using least-squares methods on models with a doubly limited dependent variable.     

Towards a strategic place brand-management model

Abstract

Using earlier research into models of place branding-management processes, this paper develops a multi-level conceptual model of strategic place brand management designed to support managers in embracing a holistic approach to place brand management. The model identifies the following components for attention and activity: place brand evaluation; brand infrastructure relationships, including infrastructure (regeneration) and stakeholder engagement (management); place brand articulation; and brand communications. The model identifies the influences and action processes between these components, including brand identity and architecture, influencing brand experience. Existing place branding models take different perspectives on the branding process – respectively, relationship management, communications, and strategic planning; none of these models are comprehensive and neither are they widely adopted or tested. This paper proposes an integrative model that builds on and subsumes these earlier models and is also grounded in the wider research on branding and place branding concept and processes.     

Local Vega Index and Variance Reduction Methods

In this article we discuss a generalization of the Greek called vega which is used to study the stability of option prices and hedging portfolios with respect to the volatility in various models. We call this generalization the local vega index. We compute through Monte Carlo simulations this index in the cases of Asian options under the classical Black-Scholes setup. Simulation methods using Malliavin calculus and kernel density estimation are compared. Variance reduction methods are discussed.     

Stochastic multifactor models in risk management of energy futures

We adopt Schwartz and Smith's model to calculate risk measures of Brent oil and light sweet crude oil (WTI) futures contracts and Mirantes, Poblacion, and Serna's model to calculate risk measures of natural gas, gasoil, heating oil, RBOB gasoline, PJM Western Hub peak, and off-peak electricity futures contracts. The models generate well in-sample goodness of fit and satisfactory out-of-sample Value-at-Risk and expected shortfall forecasts for all the eight of the analyzed commodities. A simple and flexible estimation method improving upon existing estimation methods is developed.     

Models and optimal designs for conjoint choice experiments including a no-choice option

In a classical conjoint choice experiment, respondents choose one profile from each choice set that has to be evaluated. However, in real life, the respondent does not always make a choice: often he/she does not prefer any of the options offered. Therefore, including a no-choice option in a choice set makes a conjoint choice experiment more realistic. In the literature, three different models are used to analyze the results of a conjoint choice experiment with a no-choice option: the no-choice multinomial logit model, the extended no-choice multinomial logit model, and the nested no-choice multinomial logit model. We develop optimal designs for the two most appealing of these models using the D-optimality criterion and the modified Fedorov algorithm and compare these optimal designs with a reference design, which is constructed while ignoring the no-choice option, in terms of estimation and prediction accuracy. We conclude that taking into account the no-choice option when designing a no-choice experiment only has a marginal effect on the estimation and prediction accuracy as long as the model used for estimation matches the data-generating model.