Search

This paper outlines the development and use of a tool suite developed by the NCI Agency to provide situational awareness and decision support during the current Covid-19. The tool suite was developed to understand how Covid-19 could impact the provision of communication and information services (CIS) to NATO, and so understand where risks to NATO operational functions might occur. The tool suite combines open source data on instances of Covid-19 globally along with internal information about the impact of Covid-19 on NCI Agency staff and the services they deliver to the NATO enterprise. It supports business impact assessments due to Covid-19; showing trends, age demographics, and providing early indications of critical services that may be affected, sites that may be affected, etc. The tool suite is an example of data science techniques supporting data driven decision making within a military organization.

This study addresses the following question: For a given managerial, firm, and industry setting, which individual metrics are effective for making marketing-mix decisions that improve perceived performance outcomes? We articulate the key managerial takeaways based on testing a multi-stage behavioral framework that links decision context, metrics selection, and performance outcomes. Our statistical model adjusts for potential endogeneity bias in estimating metric effectiveness due to selection effects and differs from past literature in that managers can strategically choose metrics based on their ex-ante expected effectiveness. The key findings of our analysis of 439 managers making 1287 decisions are that customer-mindset marketing metrics such as awareness and willingness to recommend are the most effective metrics for managers to employ while financial metrics such as target volume and net present value are the least effective. However, relative to financial metrics, managers are more uncertain about the ex-ante effectiveness of customer-mindset marketing metrics, which attenuates their use. A second study on 142 managers helps provide detailed underlying rationale for these key results. The implications of metric effectiveness for dashboards and automated decision systems based on machine learning systems are discussed.

This paper showcases the challenges in design, fabrication, and installation of glass projects. The modus operandi of an engineer working with glass is presented and the rationale behind the decisions explained. The first section discusses the motivations in several projects. The life cycle phases of the projects are outlined. The second chapter introduces the importance of conceptual design and generation of options on an all-glass staircase project example. Communication of the design intent is outlined in the third chapter, supported with graphical communication extracted from our recent project of a feature wall and glass elevator. The paper concludes with a brief discussion on procurement and construction phases with primary focus on the recently finished Coal Drops Yard in London. Final remarks on the structural glass design experience are presented in the conclusions.

Glass structures have been increasingly utilised in modern construction for decades with load-bearing walls or facades as the most common elements. However, the use of glass beams has recently been given more attention but its application as load-bearing elements has been limited by the low tensile resistance, its brittle behaviour during failure and concerns of its performance in case of fire. Parts of these aspects can be covered by using Timber-Glass composites beams, with timber flanges and a glass web. Previous research and practical application show high potential for this type of composites in ambient temperatures but its performance in fire has not yet been assessed and thus not completely understood. This study describes what to our knowledge is the first full scale fire resistance tests of Timber-Glass composites beams. These tests results are also analysed using finite-element simulations in order to understand the mechanisms of failure during the tests. It was shown that adding a timber flange to a glass web can have severe complications for the fire resistance, however, there are many possible ways to circumvent these issues.

The use of glass as a structural material has increased in the built environment over the last decades. Despite the large number of research projects and studies, it still poses difficulties in structural design. This particularly applies to the behaviour of glass in fire and under elevated temperatures since the available data on temperature dependent mechanical and thermal properties of glass is still limited. This contribution provides a brief overview of material properties of glass at elevated temperature and elaborates on current requirements for the fire safety included in standards.

Bayesian nonparametric regression requires prior distributions on the space of smooth functions. Gaussian process priors provide a natural model for the nonparametric smooth functions. The mean of the Gaussian process is the prior mean; the variance controls the trade-off between the prior mean and data; and the correlation determines the smoothness of the sample paths. This chapter presents the spectral analysis of Gaussian processes. Spectral analysis decomposes the Gaussian process into a lower-dimensional, linear model that is simpler to estimate. Hierarchical Bayes priors on the spectral coefficients determine the covariance structure of the Gaussian process and the amount of smoothing. The Bayesian analysis estimates the hyperparameters for the smoothing prior and avoids cross-validation. The spectral analysis facilitates extending the model to include shape constraints and nonnormal likelihoods. The chapter illustrates estimating these models with the R library bsamGP .

Despite the proliferation of big data and quantitative information available for marketing decisions, surprisingly, we know little about which metrics marketers use for their decisions or how marketers make trade-offs between such metrics. To overcome this gap, we first propose a model based on over 200 interviews conducted and a multi-disciplinary literature review of managerial metric preferences. Second, we obtain responses from 563 managers with authority on over $1 million marketing budgets who selected metrics to include in 1,126 idealized build-your-own (BYO) conjoint choice marketing budget dashboards, and rank-ordered these metrics for 2,252 decision tasks. Finally, we estimate managers’ preferences by proposing a random utility model that combines the BYO choice and ranking tasks to correct for selection effects. We find systematic differences in metric utility based on type of marketing decision and detect substantial heterogeneity in preferences among managers. From this, we develop an understanding of contextual drivers of preferences for metric use, offering several important managerial takeaways.

This paper provides an introductory, mostly nontechnical exposition of recent Deep Learning concepts, as relevant to NATO information processing requirements. A baseline case of learning confidentiality classification rules for NATO documents is described, originally performed by applying classical machine learning methods. In the course of the investigation described in this paper, the classical approaches have been complemented by Deep Learning experiments. These experiments shed some light on the potential advantages of using Deep Learning approaches for NATO document processing and beyond.

This paper offers practical guidance to engineers using finite-element analysis software packages for the design of modern glass structures. The target audience is structural engineers with a knowledge of typical structural materials but who are less experienced in glass. The principles of typical modelling procedures are discussed, and the specific techniques of sub-modelling and sub-structuring are introduced. Issues that are particular to the behaviour of statically loaded structural glass are addressed, including interaction with supporting structure, evaluating composite action in laminates and lateral buckling of slender elements. The primarily academic, more advanced modelling techniques of adaptive meshing, rezoning, using birth and death elements, and probabilistic analysis are introduced. The potential power of these techniques in the field of structural glass is presented. Finally, suggested methods for result verification are presented. These include both pre-processor and post-processor methods. Real project examples are used to illustrate discussion points throughout the paper.

Discrete-choice experiments are commonly used to measure subjects’ preference structures and are often preferred to other measurement methods because they better align with actual choice behavior and avoid some of the well-documented biases inherent in alternative elicitation methods. A limitation of discrete-choice methods is the loss of inter-subject comparability because preference estimates are invariant to linear transformations necessitating indentifying constraints that remove a common, between-subjects utility scale. This constraint limits the application of discrete-choice results to situations where within-subject comparisons are meaningful. They enable one to sort options for each subject but not to sort subjects according to the relative intensity of their preferences. This paper uses auxiliary data to recover a common preference scale for between-subject comparisons. The model combines discrete-choice data with ratings data while adjusting for response biases due to method effects. The joint model moves the identification constraints from the sub-model for the discrete-choice data to the sub-model for the ratings data. The proposed methodology is complementary to willingness-to-pay computations when studies lack price or its economic foundation is untenable.

I wish to congratulate the authors on their comparison of the newly proposed generalized multinomial logit (GMNL) of Fiebig et al. [1], henceforth ‘FKLW,’ with the widely-used, latent class or finite mixture model of Kamakura and Russell [2]. Both models use the same logistic regression likelihood for product choice but differ in their distributions for individual parameter heterogeneity. I am agnostic about the ‘best’ model for parameter heterogeneity. Ultimately, it is an empirical issue. When models are nested, the smaller model may be preferred because of its simplicity. Conversely, even when the smaller model has better AIC or BIC, a practitioner may choose the larger model if it provides useful information for marketing strategy. When models are not nested, as in this paper, comparisons beyond fit are more nuanced because the models have different foundations and implications. Academics who propose new models tend to be more focused on improved fit, while practitioners tend to look for new models that extend the set of functional problems that can be addressed. Aitchison and Bennet [3] introduced the probit model for product choice based on maximizing random ‘enjoyment,’ which has normal distributions. Partly because of limitations in computing power at the time and partly because of lack of visibility among economist, this work was superseded by the logistic random utility model of McFadden [4]. The random utility for subject i , product j , and choice occasion t is

Analysts fitting a hierarchical Bayesian model must specify the distribution of heterogeneity. There are several distributions to choose from, including the multivariate normal, mixture of normals, Dirichlet processes priors, and so forth. Although significant progress has been made, estimating the models and obtaining measures for model selection remain ongoing areas of research for more flexible distributions of heterogeneity. As a result, the multivariate normal remains the default choice for many researchers and software packages. This article proposes model-checking statistics that signal the adequacy of the multivariate normal assumption for the distribution of heterogeneity; these methods do not require the analyst to fit alternative models. The authors use posterior predictive model checking to determine whether a discrepancy exists between the individual-level parameters and those implied by the assumed distribution of heterogeneity. In simulated and real data sets, the results show that these statistics are useful for identifying when the multivariate normal distribution is adequate, when there is a departure in the tails of the distribution, and when a multimodal distribution of heterogeneity may be more appropriate.

The majority of brand extensions reportedly fail, suggesting the need for methodologies that allow for better strategic prediction of categories into which a brand should extend or license. Prior literature suggests that brand extensions are likely to be more successful if a brand extends into another category into which its existing brand associations and imagery “fit” better and if the extending brand is “atypical” (if it possesses associations and imagery that are broad and abstract rather than tied too closely to the brand's original product category). The authors develop a methodology in this study to estimate brand and category personality structures, using a Bayesian factor model that separates the two by means of brand-level and category-level random effects. This methodology leads to measures of a brand's fit and atypicality. The authors illustrate and validate the model on two nationally representative data sets on brand personalities in three categories (jeans, magazines, and cars) and investigate the brand extension and licensing implications of the results obtained with the model.

Marketers often analyze multinomial choice from a set of branded products to learn about demand. Given a set of brands to study, we analyze three reasons why choices from strict subsets of the brands can contain more statistical information about demand than choices from all the brands in the study. First, making choices from smaller subsets is easier, so it is possible to use more choice-tasks when the choice data comes from a choice-based conjoint questionnaire. Second, choices from subsets of brands better identify and more accurately estimate the covariance structure of unobserved utility shocks associated with brands. Third, subsets automatically balance the brand-shares when some of the brands are less popular than others. We demonstrate these three "benefits of subsets" using a mixture of analytical results and numerical simulations, and provide implications for the design of choice-based conjoint analyses. We find that the optimal subset-size depends on the model, the number of brands in the study, and the designer's resource constraint. Besides showing that subsets can be beneficial, we also provide a simulation methodology that helps designers pick the best subset-size for their setting.

Informative priors that reflect the structure of the model can improve estimation when data are sparse, while “standard,” noninformative priors can have unintended consequences. First, the authors discuss selecting informative priors for variances and introduce a conjugate prior for covariance matrices. The proposed prior is more flexible than the inverse Wishart without increasing computations. Second, the authors investigate the impact of priors for the covariance of parameter heterogeneity when the predictor variables are qualitative. Estimates of the omitted effects are spurious with the standard prior. The authors propose an effects prior that treats all effects symmetrically. Third, the authors consider willingness to pay. These ratio estimators magnify uncertainty in the price coefficients and can give unreasonable values for price-insensitive consumers. The authors show that estimation of willingness to pay can be greatly improved by restricting the parameters without distorting them. In ...

Research in managerial and executive leadership recognizes the importance of behavioral complexity, particularly for addressing the competing demands and roles expected of managerial leaders. Though some empirical research on behavioral complexity exists, further progress requires a more rigorous instrument to measure behavioral repertoire. We design an elaborated, multi-dimensional instrument based on the Competing Values Framework (CVF). To examine the underlying conceptual structure and remove measurement error, we test this second-order measurement model using structural equation modeling (SEM). We also test the spatial relationship of the factors using a Bayesian circumplex model. Our data largely support the theoretical structure and stringent demands of the CVF model as applied to this instrument. Finally, we test the instrument's ability to predict managerial effectiveness and find that higher overall ability is correlated with greater overall performance. With this new instrument, we suggest the modification and addition of roles associated with the CVF model.

Bayesian model selection depends on the integrated likelihood of the data given the model. Newton and Raftery’s harmonic mean estimator (HME) is simple to implement by computing the likelihood of the data at MCMC draws from the posterior distribution. Alternative methods in the literature require additional simulations or more extensive computations. In theory HME is consistent but can have an infinite variance. In practice, the computed HME often is simulation pseudo-biased. This article identifies the source of the pseudo-bias and recommends several algorithms for adjusting the HME to remove it. The pseudo-bias can be substantial and can negatively affect HME’s ability to select the correct model in Bayesian model selection. The pseudo-bias often causes the computed HME to overestimate the integrated likelihood, and the amount of pseudo-bias tends to be larger for more complex models. When the computed HME errs, it tends to select models that are too complex. Simulation studies of linear and logistic re...

Choice-based conjoint analysis is a popular marketing research technique to learn about consumers' preferences and to make market share forecasts under various scenarios for product offerings. Managers expect these forecasts to be “realistic” in terms of being able to replicate market shares at some prespecified or “base-case” scenario. Frequently, there is a discrepancy between the recovered and base-case market share. This paper presents a Bayesian decision theoretic approach to incorporating base-case market shares into conjoint analysis via the loss function. Because defining the base-case scenario typically involves a variety of management decisions, we treat the market shares as constraints on what are acceptable answers, as opposed to informative prior information. Our approach seeks to minimize the adjustment of parameters by using additive factors from a normal distribution centered at 0, with a variance as small as possible, but such that the market share constraints are satisfied. We specify an appropriate loss function, and all estimates are formally derived via minimizing the posterior expected loss. We detail algorithms that provide posterior distributions of constrained and unconstrained parameters and quantities of interest. The methods are demonstrated using discrete choice models with simulated data and data from a commercial market research study. These studies indicate that the method recovers base-case market shares without systematically distorting the preference structure from the conjoint experiment.

Rating transition matrices for corporate bond issuers are often based on fitting a discrete time Markov chain model to homogeneous cohorts. Literature has documented that rating migration matrices can differ considerably depending on the characteristics of the issuers in the pool used for estimation. However, it is also well known in the literature that a continuous time Markov chain gives statistically superior estimates of the rating migration process. It remains to verify and quantify the issuer heterogeneity in rating migration behavior using a continuous time Markov chain. We fill this gap in the literature. We provide Bayesian estimates to mitigate the problem of data sparsity. Default data, especially when narrowing down to issuers with specific characteristics, can be highly sparse. Using classical estimation tools in such a situation can result in large estimation errors. Hence we adopt Bayesian estimation techniques. We apply them to the Moodys corporate bond default database. Our results indicate strong country and industry effects on the determination of rating migration behavior. Using the CreditRisk+ framework, and a sample credit portfolio, we show that ignoring issuer heterogeneity can give erroneous estimates of Value-at-Risk and a misleading picture of the risk capital. This insight is consistent with some recent findings in the literature. Therefore, given the upcoming Basel II implementation, understanding issuer heterogeneity has important policy implications.

Modern businesses routinely capture data on millions of observations across subjects, brand SKUs, time periods, predictor variables, and store locations, thereby generating massive high-dimensional datasets. For example, Netflix has choice data on billions of movies selected, user ratings, and geodemographic characteristics. Similar datasets emerge in retailing with potential use of RFIDs, online auctions (e.g., eBay), social networking sites (e.g., mySpace), product reviews (e.g., ePinion), customer relationship marketing, internet commerce, and mobile marketing. We envision massive databases as four-way VAST matrix arrays of Variables × Alternatives × Subjects × Time where at least one dimension is very large. Predictive choice modeling of such massive databases poses novel computational and modeling issues, and the negligence of academic research to address them will result in a disconnect from the marketing practice and an impoverishment of marketing theory. To address these issues, we discuss and identify the challenges and opportunities for both practicing and academic marketers. Thus, we offer an impetus for advancing research in this nascent area and fostering collaboration across scientific disciplines to improve the practice of marketing in information-rich environment.

Shoppers of multi-channel retailers often place orders using different channels on different shopping occasions. The differential use of channels is related to both basket composition and channel characteristics, such as the ability of the channel to provide additional information that resolves uncertainty about the purchase. In this paper, we examine the impact of basket composition on the choice among direct channels. We develop a two-stage, shopping cost model with two, latent states. Given a shopping basket, the shopper first decides if she needs additional information about items in the basket. If she is uncertain about the items in the basket meeting her needs, she uses an information rich channel, such as the retailer's website or call center, and risk reduction costs become salient in addition to the other shopping costs. If she does not require additional information, she places her order by choosing among all available channels, and she may incur a welfare loss from making a purchase that does not optimally meet her needs. We operationalize welfare loss with Shannon information and various metrics based on purchase history. Our empirical setting is a data set from a catalog retailer that offers multiple direct channels. Our estimates show that basket composition impacts channel choice. Large baskets shift to the Internet channel, suggesting that the Internet channel has lower ordering costs. High-risk baskets shift to call centers and this suggests that the call center has lower risk reduction costs. Collectively these estimates provide evidence for the notion of channel specialization—some channels are better at addressing certain shopping costs compared to others. Our estimates also show that electronic self-service channels have high initial access costs and a significant learning curve compared to the call center suggesting that these channels might be better suited to heavy users. We use the estimated model to quantify the value of channels, to identify categories that need risk reduction, and to segment and target shoppers for Internet ordering based on basket size and the potential to accumulate experience.

Multivariate economic and business data frequently suffer from a missing data phenomenon that has not been sufficiently explored in the literature: both the independent and dependent variables for one or more dimensions are absent for some of the observational units. For example, in choice based conjoint studies, not all brands are available for consideration on every choice task. In this case, the analyst lacks information on both the response and predictor variables because the underlying stimuli, the excluded brands, are absent. This situation differs from the usual missing data problem where some of the independent variables or dependent variables are missing at random or by a known mechanism, and the “holes” in the data-set can be imputed from the joint distribution of the data. When dimensions are absent, data imputation may not be a well-poised question, especially in designed experiments. One consequence of absent dimensions is that the standard Bayesian analysis of the multi-dimensional covariances structure becomes difficult because of the absent dimensions. This paper proposes a simple error augmentation scheme that simplifies the analysis and facilitates the estimation of the full covariance structure. An application to a choice-based conjoint experiment illustrates the methodology and demonstrates that naive approaches to circumvent absent dimensions lead to substantially distorted and misleading inferences.

This paper presents a hierarchical Bayes circumplex model for ordinal ratings data. The circumplex model was proposed to represent the circular ordering of items in psychological testing by imposing inequalities on the correlations of the items. We provide a specification of the circumplex, propose identifying constraints and conjugate priors for the angular parameters, and accommodate theory-driven constraints in the form of inequalities. We investigate the performance of the proposed MCMC algorithm and apply the model to the analysis of value priorities data obtained from a representative sample of Dutch citizens.

The emergence of Bayesian methodology has facilitated respondent-level conjoint models, and deriving utilities from choice experiments has become very popular among those modeling product line decisions or new product introductions. This review begins with a paradox of why experimental choices should mirror market behavior despite clear differences in content, structure and motivation. It then addresses ways to design the choice tasks so that they are more likely to reflect market choices. Finally, it examines ways to model the results of the choice experiments to better mirror both underlying decision processes and potential market choices.

Abstract We report on a case of parthenogenesis in the varanid lizard Varanus panoptes. Parthenogenesis was observed in a female kept alone for three years. A clutch was deposited from which a single egg could be secured and incubated. Incubation was successful and a male specimen hatched. Obviously the newborn was produced without contribution of a father. After the unisexual reproduction, the mother was kept with males and bisexual reproduction was observed, too. We performed DNA Fingerprinting and showed that the parthenogen and its mother exhibit almost identical DNA patterns. The bisexually produced offspring has only a subset of bands in common with the mother and another subset in common with the father. Thus DNA Fingerprinting is in accordance with our observations and confims parthenogenesis.We compare our results with existing cytological models of parthenogenesis and point out the following: 1. The mode of parthenogenesis described here is facultative, as the mother was able to reproduce in the bisexual mode as well. 2. The parthenogen is male and hence not a clone of the mother. 3. Almost complete heredity of maternal Fingerprint markers. All these points considered our case seem to fit to no known model of parthenogenesis exactly. But an additional recombination could result homogamety (would explain the sex of the parthenogen) while expressing almost all maternal bands.

Abstract The European pond turtle, Emys orbicularis, is a wide ranging species, distributed from Northwest Africa over a large part of Europe and Asia Minor to the Caspian and Aral Seas. For 106 pond turtles from France mtDNA sequence variation has been assessed, using a 1031 bp portion of the mitochondrial cytochrome b gene. Three of nine haploclades currently known from the entire species' range were found in France. One clade (II) is represented with four very similar haplotypes, differing by one mutation, and the two other clades (V, VI) are represented with one haplotype each. A syntopic occurrence of clades II and V is reported for the first time for the Camargue. Besides, clade II occurs in the French regions Aquitaine, Centre-Val de Loire, and Rhône-Alpes. Outside of France, it is found mainly in the catchment areas of the Danube and Oder rivers and in the Balkans. Haploclade V, which is also known from the Apennine peninsula, Sardinia, and the northern Mediterranean coast of Spain, is restricted in France to Corsica and the Provence-Alpes-Côte d'Azur region. A single individual bearing a haplotype of an Iberian and North African clade (VI) was found in Aquitaine near Pau. This could indicate gene flow between the Iberian peninsula and West France, if the specimen is native. The distribution of the distinct haploclades in France probably reflects Holocene range expansions, especially of haploclade II turtles. In the postglacial, haploclade II terrapins arrived from the east and spread over the Rhône corridor to the Mediterranean coast. In the southern Rhône area they met and hybridized with haploclade V turtles. Further research is needed to clarify whether this hybridization is a locally restricted phenomenon.

In this paper, we highlight properties of Bayesian models in which the prior puts positive mass on all Kullback–Leibler neighborhoods of all densities. These properties are concerned with model choice via the Bayes factor, density estimation and the maximization of expected utility for decision problems. In four illustrations we focus on the Bayes factor and show that whatever models are being compared, the [log(Bayes factor)]/[sample size] converges to a non-random number which has a nice interpretation. A parametric versus semiparametric model comparison provides a fifth illustration.

A 900bp fragment of mitochondrial cytochrome b was sequenced from 63 specimens of the arboreal agamid lizard genus Acanthosaura from Vietnam, Laos, Myanmar (Burma), Thailand and Malaysia, representing all four currently recognized species. A hypothesis of maternal relationships was generated based on a maximum parsimony analysis of 44 different haplotypes. Pseudocalotes and Calotes were used as outgroup taxa. The genealogical analyses of the cytochrome b sequences recovered four lineages represented by A. armata, A. capra, A. crucigera, and A. lepidogaster. A fifth lineage consisted of one specimen from Ngoc Linh, Vietnam that was considered to be A. lepidogaster; however, recognizing it as such would render A. lepidogaster paraphyletic. Acanthosaura crucigera consisted of two clades. One of these clades contains cysteine in a portion of its cytochrome b, and is the sister group of all other species of Acanthosaura. In turn, the second clade of A. crucigera formed the sister group of A. armata, A. capra, and A. lepidogaster. A clade containing A. armata, A. capra and the sample from Ngoc Linh, Vietnam was the sister group to A. lepidogaster.

This article proposes a semiparametric model, which consists of parametric and nonparametric components, for density estimation. The parametric component represents the researcher's a priori beliefs about a likely family of density functions. The nonparametric component, which is modeled by a logistic–Gaussian process, allows the predictive distribution to deviate from the parametric family if it is inadequate. Bayesian hypothesis testing is used to examine the adequacy of the parametric model relative to the flexible alternative provided by the semiparametric model. The article presents a Markov chain Monte Carlo algorithm that efficiently handles the large number of parameters.

We consider customer influences on market structure, arguing that market structure should explain the extent to which any given set of market offerings are substitutes or complements. We describe recent additions to the market structure analysis literature and identify promising directions for new research in market structure analysis. Impressive advances in data collection, statistical methodology and information technology provide unique opportunities for researchers to build market structure tools that can assist “real-time” marketing decision-making.

Probability plays a central role in quantifying risk and uncertainty. In contrast to the laws of probability, which are well established, there are several different interpretations of probability. This article traces the major positions of the frequency, subjective, and logical schools, and summarizes the implications of these approaches for risk professionals. The article concludes that despite profoundly different interpretations and consequences, current industry demands require professionals to be facile in using different approaches to probability. Keywords: Bayes nets; Bayes' theorem; coherence; exchangeability; expected utility; logical probability; relative frequency; subjective probability; theory of rational choice

In order to elucidate the phylogenetic relationships in European ratsnakes of the genus Elaphe , we analyzed a 597 bp part of the mitochondrial cytochrome b gene of eight West Eurasian and one East Asian species. Lampropeltis served as outgroup. Maximum parsimony and maximum likelihood suggest the existence of four lineages: 1) E. scalaris ; 2) the E. longissima species group comprising E. longissima , E. lineata , E. situla , E. hohenackeri , and E. persica ; 3) E. quatuorlineata and 4) E. dione as a sister group to 3). Elaphe scalaris is basal and shows no closer affiliation with any other analyzed species. The Middle Eastern E. persica and E. hohenackeri appear basal within the E. longissima group. Elaphe lineata differs by 8% nucleotide substitutions from E. longissima , supporting the hypothesis that both taxa represent distinct species. Elaphe situla is associated with Elaphe longissima and E. lineata . Three analyzed subspecies of E. quatuorlineata are represented by distinct haplotypes. The extent of divergence gives reason to assign species status to the taxon sauromates . Besides, we found two very distinct haplotypes within the range of E. (q.) sauromates , indicating the existence of a third, so far unidentified, species within the E. quatuorlineata complex. The East Asian E. porphyracea clusters with the E. longissima group. This, as well as comparisons with supplementary sequences of Asian Elaphe species, document the multiple origins of European Elaphe . Um die phylogenetischen Beziehungen europaischer Kletternattern der Gattung Elaphe zu erhellen, sequenzierten und analysierten wir ein 597 Nukleotide messendes Stuck des mitochondrialen Cytochrom b Gens von acht west-eurasischen und einer ostasiatischen Art. Lampropeltis diente als Ausengruppe. Maximum parsimony und maximum likelihood Berechnungen zeigen die Existenz von vier genetischen Linien auf: a) E. scalaris ; b) die E. longissima Artengruppe mit E. longissima , E. lineata, E. situla, E. hohenackeri , und E. persica ; c) E. quatuorlineata und d) E. dione als Schwestergruppe zu c). Elaphe scalaris nimmt eine basale Position ein und scheint mit keiner untersuchten Art naher verwandt zu sein. Die westasiatischen Arten E. persica und E. hohenackeri sind die Schwestergruppe zu E. longissima, E. lineata und E. situla . Elaphe lineata unterscheidet sich durch 8% Nukleotidaustausche von E. longissima , wodurch der Artstatus von E. lineata unterstutzt wird. Elaphe longissima, E. lineata und E. situla bilden eine Abstammungsgemeinschaft. Auch die Haplotypen der drei untersuchten E. quatuorlineata -Unterarten unterscheiden sich so stark, das Artstatus fur das Taxon sauromates zu fordern ist. Daruberhinaus fanden wir im Gebiet von E. (q.) sauromates zwei stark unterschiedliche Haplotypen, die die Existenz einer dritten bislang unidentifizierten Art nahelegen. Die ostasiatische E. porphyracea scheint der E. longissima -Gruppe nahe zu stehen. Dies, sowie der Vergleich mit erganzenden Sequenzdaten asiatischer Elaphe -Arten, belegt den mehrfachen Ursprung europaischer Elaphe .

We present an hierarchical Bayes approach to modeling parameter heterogeneity in generalized linear models. The model assumes that there are relevant subpopulations and that within each subpopulation the individual-level regression coefficients have a multivariate normal distribution. However, class membership is not known a priori, so the heterogeneity in the regression coefficients becomes a finite mixture of normal distributions. This approach combines the flexibility of semiparametric, latent class models that assume common parameters for each sub-population and the parsimony of random effects models that assume normal distributions for the regression parameters. The number of subpopulations is selected to maximize the posterior probability of the model being true. Simulations are presented which document the performance of the methodology for synthetic data with known heterogeneity and number of sub-populations. An application is presented concerning preferences for various aspects of personal computers.

The phylogeny and phylogeography of Emys orbicularis was inferred from mitochondrial nucleotide sequences of the cytochrome b gene analysed by DNA sequencing and RNA heteroduplex analysis. Within the family Emydidae the monotypic genus Emys is affiliated with the nearctic taxa Emydoidea blandingii and Clemmys marmorata. The analysis of 423 individuals of E. orbicularis, originating throughout its distribution range, revealed a remarkable intraspecific differentiation in 20 different haplotypes with distinct geographical ranges. Maximum parsimony analysis produced a star-like phylogeny with seven main lineages which may reflect separations in the late Pliocene. The haplotype distribution examined by partial Mantel tests and analysis of molecular variance revealed a substantial effect of glacial periods. This historical perspective suggests the existence of multiple glacial refugia and considerable Holocene range expansion which was modulated by climatic traits. Further support is gained for the occurrence of long-term parapatry in glacial refugia.

Summary This paper presents the Bayesian analysis of a semiparametric regression model that consists of parametric and nonparametric components. The nonparametric component is represented with a Fourier series where the Fourier coefficients are assumed a priori to have zero means and to decay to 0 in probability at either algebraic or geometric rates. The rate of decay controls the smoothness of the response function. The posterior analysis automatically selects the amount of smoothing that is coherent with the model and data. Posterior probabilities of the parametric and semiparametric models provide a method for testing the parametric model against a non-specific alternative. The Bayes estimator’s mean integrated squared error compares favourably with the theoretically optimal estimator for kernel regression.

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.

A nonacceptable claim (NAC) is an insurance claim for an unnecessary hospital stay. This study establishes a statistical model that predicts the NAC rate. The model supplements current insurer programs that rely on detailed audits of patient medical records. Hospital discharge claim records are used as inputs in the statistical model to predict retrospectively the probability that a hospital admission is nonacceptable. A full Bayesian hierarchical logistic regression model is used with regression coefficients that are random across the primary diagnosis codes. The model provides better fits and predictions than standard methods that pool across primary diagnosis codes.

We define sources of heterogeneity in consumer utility functions related to individual differences in response tendencies, drivers of utility, form of the consumer utility function, perceptions of attributes, state dependencies, and stochasticity. A variety of alternative modeling approaches are reviewed that accommodate subsets of these various sources including clusterwise regression, latent structure models, compound distributions, random coefficients models, etc. We conclude by defining a number of promising research areas in this field.

The drive to satisfy customers in narrowly defined market segments has led firms to offer wider arrays of products and services. Delivering products and services with the appropriate mix of features for these highly fragmented market segments requires understanding the value that customers place on these features. Conjoint analysis endeavors to unravel the value or partworths, that customers place on the product or service's attributes from experimental subjects' evaluation of profiles based on hypothetical products or services. When the goal is to estimate the heterogeneity in the customers' partworths, traditional estimation methods, such as least squares, require each subject to respond to more profiles than product attributes, resulting in lengthy questionnaires for complex, multiattributed products or services. Long questionnaires pose practical and theoretical problems. Response rates tend to decrease with increasing questionnaire length, and more importantly, academic evidence indicates that long questionnaires may induce response biases. The problems associated with long questionnaires call for experimental designs and estimation methods that recover the heterogeneity in the partworths with shorter questionnaires. Unlike more popular estimation methods, Hierarchical Bayes (HB) random effects models do not require that individual-level design matrices be of full rank, which leads to the possibility of using fewer profiles per subject than currently used. Can this theoretical possibility be practically implemented? This paper tests this conjecture with empirical studies and mathematical analysis. The random effects model in the paper describes the heterogeneity in subject-level partworths or regression coefficients with a linear model that can include subject-level covariates. In addition, the error variances are specific to the subjects, thus allowing for the differential use of the measurement scale by different subjects. In the empirical study, subjects' responses to a full profile design are randomly deleted to test the performance of HB methods with declining sample sizes. These simple experiments indicate that HB methods can recover heterogeneity and estimate individual-level partworths, even when individual-level least squares estimators do not exist due to insufficient degrees of freedom. Motivated by these empirical studies, the paper analytically investigates the trade-off between the number of profiles per subject and the number of subjects on the statistical accuracy of the estimators that describe the partworth heterogeneity. The paper considers two experimental designs: each subject receives the same set of profiles, and subjects receive different blocks of a fractional factorial design. In the first case, the optimal design, subject to a budget constraint, uses more subjects and fewer profiles per subject when the ratio of unexplained, partworth heterogeneity to unexplained response variance is large. In the second case, one can maintain a given level of estimation accuracy as the number of profiles per subject decreases by increasing the number of subjects assigned to each block. These results provide marketing researchers the option of using shorter questionnaires for complex products or services. The analysis assumes that response quality is independent of questionnaire length and does not address the impact of design factors on response quality. If response quality and questionnaire length were, in fact, unrelated, then marketing researchers would still find the paper's results useful in improving the efficiency of their conjoint designs. However, if response quality were to decline with questionnaire length, as the preponderance of academic research indicates, then the option to use shorter questionnaires would become even more valuable.