The negative effects of failed service recoveries

Research has shown that more than half of attempted recovery efforts fail, producing a ‘double deviation’ effect. Surprisingly, these double deviation effects have received little attention in marketing literature. This paper examines what happens after these critical encounters, which behavior or set of behaviors the customers are prone to follow and how customers’ perceptions of the firm’s recovery efforts influence these behaviors. For the analysis of choice of the type of response (complaining, exit, complaining and exit, and no-switching), we estimate multinomial Logit models with random coefficients (RCL). The results of our study show that magnitude of service failure, explanations, apologies, perceived justice, angry and frustration felt by the customer, and satisfaction with service recovery have a significant effect on customers’ choice of the type of response. Implications from the findings are offered.

Direct versus indirect channels: Differentiated loss aversion in a high‐involvement, non‐frequently purchased hedonic product

Purpose – This article aims to investigate whether intermediaries reduce loss aversion in the context of a high-involvement non-frequently purchased hedonic product (tourism packages). Design/methodology/approach – The study incorporates the reference-dependent model into a multinomial logit model with random parameters, which controls for heterogeneity and allows representation of different correlation patterns between non-independent alternatives. Findings – Differentiated loss aversion is found: consumers buying high-involvement non-frequently purchased hedonic products are less loss averse when using an intermediary than when dealing with each provider separately and booking their services independently. This result can be taken as identifying consumer-based added value provided by the intermediaries. Practical implications – Knowing the effect of an increase in their prices is crucial for tourism collective brands (e.g. “sun and sea”, “inland”, “green destinations”, “World Heritage destinations”). This is especially applicable nowadays on account of the fact that many destinations have lowered prices to attract tourists (although, in the future, they will have to put prices back up to their normal levels). The negative effect of raising prices can be absorbed more easily via indirect channels when compared to individual providers, as the influence of loss aversion is lower for the former than the latter. The key implication is that intermediaries can – and should – add value in competition with direct e-tailing. Originality/value – Research on loss aversion in retailing has been prolific, exclusively focused on low-involvement and frequently purchased products without distinguishing the direct or indirect character of the distribution channel. However, less is known about other types of products such as high-involvement non-frequently purchased hedonic products. This article focuses on the latter and analyzes different patterns of loss aversion in direct and indirect channels.

MGOF: Stata module to perform goodness-of-fit tests for multinomial data

mgof computes goodness-of-fit tests for the distribution of a discrete (categorical, multinomial) variable. The default is to perform classical large sample chi-squared approximation tests based on Pearson's X2 statistic and the log likelihood ratio (G2) statistic or a statistic from the Cressie-Read family. Alternatively, mgof computes exact tests using Monte Carlo methods or exhaustive enumeration. A Kolmogorov-Smirnov test for discrete data is also provided. The moremata package, also available from SSC, is required.

Multinomial goodness-of-fit: large sample tests with survey design correction and exact tests for small samples

A new Stata command called -mgof- is introduced. The command is used to compute distributional tests for discrete (categorical, multinomial) variables. Apart from classic large sample $\chi^2$-approximation tests based on Pearson's $X^2$, the likelihood ratio, or any other statistic from the power-divergence family (Cressie and Read 1984), large sample tests for complex survey designs and exact tests for small samples are supported. The complex survey correction is based on the approach by Rao and Scott (1981) and parallels the survey design correction used for independence tests in -svy:tabulate-. The exact tests are computed using Monte Carlo methods or exhaustive enumeration. An exact Kolmogorov-Smirnov test for discrete data is also provided.

Neighborhoods neighboring neighborhoods: adjacency, relative position and tract-level racial change in the U.S. 2000 to 2010

Thesis (Master's)--University of Washington, 2016-06

Methods for Categorical Longitudinal Survey Data: Understanding Employment Status of Australian Women

Many variables that are of interest in social science research are nominal variables with two or more categories, such as employment status, occupation, political preference, or self-reported health status. With longitudinal survey data it is possible to analyse the transitions of individuals between different employment states or occupations (for example). In the statistical literature, models for analysing categorical dependent variables with repeated observations belong to the family of models known as generalized linear mixed models (GLMMs). The specific GLMM for a dependent variable with three or more categories is the multinomial logit random effects model. For these models, the marginal distribution of the response does not have a closed form solution and hence numerical integration must be used to obtain maximum likelihood estimates for the model parameters. Techniques for implementing the numerical integration are available but are computationally intensive requiring a large amount of computer processing time that increases with the number of clusters (or individuals) in the data and are not always readily accessible to the practitioner in standard software. For the purposes of analysing categorical response data from a longitudinal social survey, there is clearly a need to evaluate the existing procedures for estimating multinomial logit random effects model in terms of accuracy, efficiency and computing time. The computational time will have significant implications as to the preferred approach by researchers. In this paper we evaluate statistical software procedures that utilise adaptive Gaussian quadrature and MCMC methods, with specific application to modeling employment status of women using a GLMM, over three waves of the HILDA survey.

Entrepreneurs, expectations and business expansion:lessons from Lithuania

This article applies a multinomial logit estimator to investigate which factors affect SME owners' expectations to grow their businesses in Lithuania. Our findings provide evidence that SME owners' human capital (education) matters and that growth expectations are positively related to exporting. In addition, we analyse the link between the perceptions of business constraints and growth expectations and find that the factors, which are perceived as main business barriers, are not necessarily those which are associated with reduced growth expectations. However, perceptions of corruption seem to affect growth expectations the most.

When moving information online diminishes change:advisory services to SMEs

Improving the performance of private sector small and medium sized enterprises (SMEs) in a cost effective manner is a major concern for government. Governments have saved costs by moving information online rather than through more expensive face-to-face exchanges between advisers and clients. Building on previous work that distinguished between types of advice, this article evaluates whether these changes to delivery mechanisms affect the type of advice received. Using a multinomial logit model of 1334 cases of business advice to small firms collected in England, the study found that advice to improve capabilities was taken by smaller firms who were less likely to have limited liability or undertake business planning. SMEs sought word-of-mouth referrals before taking internal, capability-enhancing advice. This is also the case when that advice was part of a wider package of assistance involving both internal and external aspects. Only when firms took advice that used extant capabilities did they rely on the Internet. Therefore, when the Internet is privileged over face-to-face advice the changes made by each recipient of advice are likely to diminish causing less impact from advice within the economy. It implies that fewer firms will adopt the sorts of management practices that would improve their productivity. © 2014 Taylor & Francis.

A diszkrét kiválasztási modell becslése Cox-regresszióval (Parameter estimation for multinomial discrete choice model using Cox-regression)

Considering the so-called "multinomial discrete choice" model the focus of this paper is on the estimation problem of the parameters. Especially, the basic question arises how to carry out the point and interval estimation of the parameters when the model is mixed i.e. includes both individual and choice-specific explanatory variables while a standard MDC computer program is not available for use. The basic idea behind the solution is the use of the Cox-proportional hazards method of survival analysis which is available in any standard statistical package and provided a data structure satisfying certain special requirements it yields the MDC solutions desired. The paper describes the features of the data set to be analysed.

Trading between perceived risks and benefits related to biosimilar biological treatment in Crohn’s disease; discrete choice experiment among gastroenterologists

Objective: The objective of the study is to explore preferences of gastroenterologists for biosimilar drugs in Crohn’s Disease and reveal trade-offs between the perceived risks and benefits related to biosimilar drugs. Method: Discrete choice experiment was carried out involving 51 Hungarian gastroenterologists in May, 2014. The following attributes were used to describe hypothetical choice sets: 1) type of the treatment (biosimilar/originator) 2) severity of disease 3) availability of continuous medicine supply 4) frequency of the efficacy check-ups. Multinomial logit model was used to differentiate between three attitude types: 1) always opting for the originator 2) willing to consider biosimilar for biological-naïve patients only 3) willing to consider biosimilar treatment for both types of patients. Conditional logit model was used to estimate the probabilities of choosing a given profile. Results: Men, senior consultants, working in IBD center and treating more patients are more likely to willing to consider biosimilar for biological-naïve patients only. Treatment type (originator/biosimilar) was the most important determinant of choice for patients already treated with biologicals, and the availability of continuous medicine supply in the case biological-naïve patients. The probabilities of choosing the biosimilar with all the benefits offered over the originator under current reimbursement conditions are 89% vs 11% for new patients, and 44% vs 56% for patients already treated with biological. Conclusions: Gastroenterologists were willing to trade between perceived risks and benefits of biosimilars. The continuous medical supply would be one of the major benefits of biosimilars. However, benefits offered in the scenarios do not compensate for the change from the originator to the biosimilar treatment of patients already treated with biologicals.

Understanding Immigrants' Travel Behavior in Florida: Neighborhood Effects and Behavioral Assimilation

The goal of this study was to develop Multinomial Logit models for the mode choice behavior of immigrants, with key focuses on neighborhood effects and behavioral assimilation. The first aspect shows the relationship between social network ties and immigrants’ chosen mode of transportation, while the second aspect explores the gradual changes toward alternative mode usage with regard to immigrants’ migrating period in the United States (US). Mode choice models were developed for work, shopping, social, recreational, and other trip purposes to evaluate the impacts of various land use patterns, neighborhood typology, socioeconomic-demographic and immigrant related attributes on individuals’ travel behavior. Estimated coefficients of mode choice determinants were compared between each alternative mode (i.e., high-occupancy vehicle, public transit, and non-motorized transport) with single-occupant vehicles. The model results revealed the significant influence of neighborhood and land use variables on the usage of alternative modes among immigrants. Incorporating these indicators into the demand forecasting process will provide a better understanding of the diverse travel patterns for the unique composition of population groups in Florida.

Bayesian Inference in Large-scale Problems

Many modern applications fall into the category of "large-scale" statistical problems, in which both the number of observations n and the number of features or parameters p may be large. Many existing methods focus on point estimation, despite the continued relevance of uncertainty quantification in the sciences, where the number of parameters to estimate often exceeds the sample size, despite huge increases in the value of n typically seen in many fields. Thus, the tendency in some areas of industry to dispense with traditional statistical analysis on the basis that "n=all" is of little relevance outside of certain narrow applications. The main result of the Big Data revolution in most fields has instead been to make computation much harder without reducing the importance of uncertainty quantification. Bayesian methods excel at uncertainty quantification, but often scale poorly relative to alternatives. This conflict between the statistical advantages of Bayesian procedures and their substantial computational disadvantages is perhaps the greatest challenge facing modern Bayesian statistics, and is the primary motivation for the work presented here.

Two general strategies for scaling Bayesian inference are considered. The first is the development of methods that lend themselves to faster computation, and the second is design and characterization of computational algorithms that scale better in n or p. In the first instance, the focus is on joint inference outside of the standard problem of multivariate continuous data that has been a major focus of previous theoretical work in this area. In the second area, we pursue strategies for improving the speed of Markov chain Monte Carlo algorithms, and characterizing their performance in large-scale settings. Throughout, the focus is on rigorous theoretical evaluation combined with empirical demonstrations of performance and concordance with the theory.

One topic we consider is modeling the joint distribution of multivariate categorical data, often summarized in a contingency table. Contingency table analysis routinely relies on log-linear models, with latent structure analysis providing a common alternative. Latent structure models lead to a reduced rank tensor factorization of the probability mass function for multivariate categorical data, while log-linear models achieve dimensionality reduction through sparsity. Little is known about the relationship between these notions of dimensionality reduction in the two paradigms. In Chapter 2, we derive several results relating the support of a log-linear model to nonnegative ranks of the associated probability tensor. Motivated by these findings, we propose a new collapsed Tucker class of tensor decompositions, which bridge existing PARAFAC and Tucker decompositions, providing a more flexible framework for parsimoniously characterizing multivariate categorical data. Taking a Bayesian approach to inference, we illustrate empirical advantages of the new decompositions.

Latent class models for the joint distribution of multivariate categorical, such as the PARAFAC decomposition, data play an important role in the analysis of population structure. In this context, the number of latent classes is interpreted as the number of genetically distinct subpopulations of an organism, an important factor in the analysis of evolutionary processes and conservation status. Existing methods focus on point estimates of the number of subpopulations, and lack robust uncertainty quantification. Moreover, whether the number of latent classes in these models is even an identified parameter is an open question. In Chapter 3, we show that when the model is properly specified, the correct number of subpopulations can be recovered almost surely. We then propose an alternative method for estimating the number of latent subpopulations that provides good quantification of uncertainty, and provide a simple procedure for verifying that the proposed method is consistent for the number of subpopulations. The performance of the model in estimating the number of subpopulations and other common population structure inference problems is assessed in simulations and a real data application.

In contingency table analysis, sparse data is frequently encountered for even modest numbers of variables, resulting in non-existence of maximum likelihood estimates. A common solution is to obtain regularized estimates of the parameters of a log-linear model. Bayesian methods provide a coherent approach to regularization, but are often computationally intensive. Conjugate priors ease computational demands, but the conjugate Diaconis--Ylvisaker priors for the parameters of log-linear models do not give rise to closed form credible regions, complicating posterior inference. In Chapter 4 we derive the optimal Gaussian approximation to the posterior for log-linear models with Diaconis--Ylvisaker priors, and provide convergence rate and finite-sample bounds for the Kullback-Leibler divergence between the exact posterior and the optimal Gaussian approximation. We demonstrate empirically in simulations and a real data application that the approximation is highly accurate, even in relatively small samples. The proposed approximation provides a computationally scalable and principled approach to regularized estimation and approximate Bayesian inference for log-linear models.

Another challenging and somewhat non-standard joint modeling problem is inference on tail dependence in stochastic processes. In applications where extreme dependence is of interest, data are almost always time-indexed. Existing methods for inference and modeling in this setting often cluster extreme events or choose window sizes with the goal of preserving temporal information. In Chapter 5, we propose an alternative paradigm for inference on tail dependence in stochastic processes with arbitrary temporal dependence structure in the extremes, based on the idea that the information on strength of tail dependence and the temporal structure in this dependence are both encoded in waiting times between exceedances of high thresholds. We construct a class of time-indexed stochastic processes with tail dependence obtained by endowing the support points in de Haan's spectral representation of max-stable processes with velocities and lifetimes. We extend Smith's model to these max-stable velocity processes and obtain the distribution of waiting times between extreme events at multiple locations. Motivated by this result, a new definition of tail dependence is proposed that is a function of the distribution of waiting times between threshold exceedances, and an inferential framework is constructed for estimating the strength of extremal dependence and quantifying uncertainty in this paradigm. The method is applied to climatological, financial, and electrophysiology data.

The remainder of this thesis focuses on posterior computation by Markov chain Monte Carlo. The Markov Chain Monte Carlo method is the dominant paradigm for posterior computation in Bayesian analysis. It has long been common to control computation time by making approximations to the Markov transition kernel. Comparatively little attention has been paid to convergence and estimation error in these approximating Markov Chains. In Chapter 6, we propose a framework for assessing when to use approximations in MCMC algorithms, and how much error in the transition kernel should be tolerated to obtain optimal estimation performance with respect to a specified loss function and computational budget. The results require only ergodicity of the exact kernel and control of the kernel approximation accuracy. The theoretical framework is applied to approximations based on random subsets of data, low-rank approximations of Gaussian processes, and a novel approximating Markov chain for discrete mixture models.

Data augmentation Gibbs samplers are arguably the most popular class of algorithm for approximately sampling from the posterior distribution for the parameters of generalized linear models. The truncated Normal and Polya-Gamma data augmentation samplers are standard examples for probit and logit links, respectively. Motivated by an important problem in quantitative advertising, in Chapter 7 we consider the application of these algorithms to modeling rare events. We show that when the sample size is large but the observed number of successes is small, these data augmentation samplers mix very slowly, with a spectral gap that converges to zero at a rate at least proportional to the reciprocal of the square root of the sample size up to a log factor. In simulation studies, moderate sample sizes result in high autocorrelations and small effective sample sizes. Similar empirical results are observed for related data augmentation samplers for multinomial logit and probit models. When applied to a real quantitative advertising dataset, the data augmentation samplers mix very poorly. Conversely, Hamiltonian Monte Carlo and a type of independence chain Metropolis algorithm show good mixing on the same dataset.

A Bayesian Dirichlet-Multinomial Test for Cross-Group Differences

Testing for differences within data sets is an important issue across various applications. Our work is primarily motivated by the analysis of microbiomial composition, which has been increasingly relevant and important with the rise of DNA sequencing. We first review classical frequentist tests that are commonly used in tackling such problems. We then propose a Bayesian Dirichlet-multinomial framework for modeling the metagenomic data and for testing underlying differences between the samples. A parametric Dirichlet-multinomial model uses an intuitive hierarchical structure that allows for flexibility in characterizing both the within-group variation and the cross-group difference and provides very interpretable parameters. A computational method for evaluating the marginal likelihoods under the null and alternative hypotheses is also given. Through simulations, we show that our Bayesian model performs competitively against frequentist counterparts. We illustrate the method through analyzing metagenomic applications using the Human Microbiome Project data.

The effect of alcohol consumption on household income in Ireland

This paper presents a study of the effects of alcohol consumption on household income in Ireland using the Slán National Health and Lifestyle Survey 2007 dataset, accounting for endogeneity and selection bias. Drinkers are categorised into one of four categories based on the recommended weekly drinking levels by the Irish Health Promotion Unit; those who never drank, non-drinkers, moderate and heavy drinkers. A multinomial logit OLS Two Step Estimate is used to explain individual's choice of drinking status and to correct for selection bias which would result in the selection into a particular category of drinking being endogenous. Endogeneity which may arise through the simultaneity of drinking status and income either due to the reverse causation between the two variables, income affecting alcohol consumption or alcohol consumption affecting income, or due to unobserved heterogeneity, is addressed. This paper finds that the household income of drinkers is higher than that of non-drinkers and of those who never drank. There is very little difference between the household income of moderate and heavy drinkers, with heavy drinkers earning slightly more. Weekly household income for those who never drank is €454.20, non-drinkers is €506.26, compared with €683.36 per week for moderate drinkers and €694.18 for heavy drinkers.

A mixed logit model for predicting exit choice during building evacuations.

Knowledge on human behaviour in emergency is crucial to increase the safety of buildings and transportation systems. Decision making during evacuations implies different choices, of which one of the most important concerns the escape route. The choice of a route may involve local decisions between alternative exits from an enclosed environment. This work investigates the influence of environmental (presence of smoke, emergency lighting and distance of exit) and social factors (interaction with evacuees close to the exits and with those near the decision-maker) on local exit choice. This goal is pursued using an online stated preference survey carried out making use of non-immersive virtual reality. A sample of 1,503 participants is obtained and a Mixed Logit Model is calibrated using these data. The model shows that presence of smoke, emergency lighting, distance of exit, number of evacuees near the exits and the decision-maker, and flow of evacuees through the exits significantly affect local exit choice. Moreover, the model points out that decision making is affected by a high degree of behavioural uncertainty. Our findings support the improvement of evacuation models and the accuracy of their results, which can assist in designing and managing building and transportation systems. The main contribution of this work is to enrich the understanding of how local exit choices are made and how behavioural uncertainty affects these choices.