Association Models for Multi-Dimensional Cross-Classifications of Ordinal Variables

Models are formulated for describing associations among ordinal variables in multidimensional tables.Uniform association and uniform interaction models occur as special cases in which equal-interval scores are assigned to levels of the variables.The models described are extensions of ones proposed by Goodman (1979).     

The Identifiability of Dependent Competing Risks Models Induced by Bivariate Frailty Models

In this paper, we propose to use a special class of bivariate frailty models to study dependent censored data. The proposed models are closely linked to Archimedean copula models. We give sufficient conditions for the identifiability of this type of competing risks models. The proposed conditions are derived based on a property shared by Archimedean copula models and satisfied by several well‐known bivariate frailty models. Compared with the models studied by Heckman and Honoré and Abbring and van den Berg, our models are more restrictive but can be identified with a discrete (even finite) covariate. Under our identifiability conditions, expectation–maximization (EM) algorithm provides us with consistent estimates of the unknown parameters. Simulation studies have shown that our estimation procedure works quite well. We fit a dependent censored leukaemia data set using the Clayton copula model and end our paper with some discussions. © 2014 Board of the Foundation of the Scandinavian Journal of Statistics     

The complexity of school and neighbourhood effects and movements of pupils on school differences in models of educational achievement

Summary.  Traditional studies of school differences in educational achievement use multilevel modelling techniques to take into account the nesting of pupils within schools. However, educational data are known to have more complex non-hierarchical structures. The potential importance of such structures is apparent when considering the effect of pupil mobility during secondary schooling on educational achievement. Movements of pupils between schools suggest that we should model pupils as belonging to the series of schools that are attended and not just their final school. Since these school moves are strongly linked to residential moves, it is important to explore additionally whether achievement is also affected by the history of neighbourhoods that are lived in. Using the national pupil database, this paper combines multiple membership and cross-classified multilevel models to explore simultaneously the relationships between secondary school, primary school, neighbourhood and educational achievement. The results show a negative relationship between pupil mobility and achievement, the strength of which depends greatly on the nature and timing of these moves. Accounting for pupil mobility also reveals that schools and neighbourhoods are more important than shown by previous analysis. A strong primary school effect appears to last long after a child has left that phase of schooling. The additional effect of neighbourhoods, in contrast, is small. Crucially, the rank order of school effects across all types of pupil is sensitive to whether we account for the complexity of the multilevel data structure.     

Linear Transformations of Linear Mixed-Effects Models

A number of articles have discussed the way lower order polynomial and interaction terms should be handled in linear regression models. Only if all lower order terms are included in the model will the regression model be invariant with respect to coding transformations of the variables. If lower order terms are omitted, the regression model will not be well formulated. In this paper, we extend this work to examine the implications of the ordering of variables in the linear mixed-effects model. We demonstrate how linear transformations of the variables affect the model and tests of significance of fixed effects in the model. We show how the transformations modify the random effects in the model, as well as their covariance matrix and the value of the restricted log-likelihood. We suggest a variable selection strategy for the linear mixed-effects model.     

Equivalence of Certain Chi-Squared Test Statistics

In likelihood analysis of categorized data, it is well known that within a restricted class of log-linear models the likelihood kernels for multinomial and product multinomial sampling distributions are identical. In practical terms the estimation procedure for one is appropriate for the other. There does not appear to be a widespread realization that a similar result holds for a wide class of the Grizzle, Starmer, and Koch (1969) weighted least squares techniques. In this report such a fundamental relationship is explicitly presented and illustrated through two analyses of Bartlett's (1935) data.     

Bayesian emulation of complex multi-output and dynamic computer models

Computer models are widely used in scientific research to study and predict the behaviour of complex systems. The run times of computer-intensive simulators are often such that it is impractical to make the thousands of model runs that are conventionally required for sensitivity analysis, uncertainty analysis or calibration. In response to this problem, highly efficient techniques have recently been developed based on a statistical meta-model (the emulator) that is built to approximate the computer model. The approach, however, is less straightforward for dynamic simulators, designed to represent time-evolving systems. Generalisations of the established methodology to allow for dynamic emulation are here proposed and contrasted. Advantages and difficulties are discussed and illustrated with an application to the Sheffield Dynamic Global Vegetation Model, developed within the UK Centre for Terrestrial Carbon Dynamics.     

Multi-state Models in Epidemiology

I first discuss the main assumptions which can be made for multi-state models: the time-homogeneity and semi-Markov assumptions, the problem of choice of the time scale, the assumption of homogeneity of the population and also assumptions about the way the observations are incomplete, leading to truncation and censoring. The influence of covariates and different durations and time-dependent variables are synthesized using explanatory processes, and a general additive model for transition intensities presented. Different inference approaches, including penalized likelihood, are considered. Finally three examples of application in epidemiology are presented and some references to other works are given.     

A class of log-linear models with constrained marginal distributions

Summary In the log-linear model for bivariate probability functions the conditional and joint probabilities have a simple form. This property make the log-linear parametrization useful when modeling these probabilities is the focus of the investigation. On the contrary, in the log-linear representation of bivariate probability functions, the marginal probabilities have a complex form. So the log-linear models are not useful when the marginal probabilities are of particular interest. In this paper the previous statements are discussed and a model obtained from the log-linear one by imposing suitable constraints on the marginal probabilities is introduced. This work was supported by a M.U.R.S.T. grant.     

A class of beta regression models with multiplicative log-normal measurement errors

In this article, we propose a beta regression model with multiplicative log-normal measurement errors. Three estimation methods are presented, namely, naive, calibration regression, and pseudo likelihood. The nuisance parameters are estimated from a system of estimation equations using replicated data and these estimates are used to propose a pseudo likelihood function. A simulation study was performed to assess some properties of the proposed methods. Results from an example with a real dataset, including diagnostic tools, are also reported.     

Accent on Teaching Materials: Notices and Reviews of Important Teaching Materials

In contrast to the analysis of variance of fully fixed or fully random component models, the analysis of variance of mixed models is fraught with potential pitfalls. It is fortunate that there are simple rules for the correct analysis of balanced data; in the case of unbalanced data there are no simple results. The potential pitfalls in the path of a correct analysis are well-known. Despite this, some computer packages still report incorrect results for the balanced model and some textbooks gloss over or ignore some of these pitfalls.     

Logistic与分类树模型变量筛选的比较——基于信用卡邮寄业务响应率分析

基于信用卡邮寄业务响应率分析来讨论Logistic模型和分类树模型在变量选取上的区别,并尝试从几个不同角度去解释两类模型变量筛选差异的原因。笔者认为没有绝对占优势的方法,需要结合具体场景和模型的特点来选择合适的模型。分类树模型在训练集上容易过度拟合,对单个变量的影响很敏感,在进行危险因素分析时结果更能强调危险因素,对孤立点的识别率很高。Logistic模型容易受到解释变量依存关系的影响,加上分类变量的影响容易过多地选入变量或者因子,对孤立点敏感,对噪点不敏感。判别函数的差异是变量筛选差异的关键因素。     

The Performance of Gaussian and non Gaussian dynamic models in assessing market risk: The Implications for risk management

The developing markets are more volatile, unstable illiquid, and more prone to the external shocks. The non Gaussian VaR model gives more accurate risk models than Gaussian VaR models. Hence, the purpose of this study is to test if and how non Gaussian VaR models are comparatively better fit for risk modeling of developing markets than the Gaussian VaR models. The study measures the market risk for the daily closing price of Karachi Stock Exchange 100 index over the period of 2004–2016. The evaluation of VaR models suggests that non Gaussian dynamic model outperformed the Gaussian VaR models in developing markets.     

Confidence intervals and tests on the variance ratio in random models with two variance components

The LM test is modified to test any value of the ratio of two variance components in a mixed effects linear model with two variance components. The test is exact, so it can be used to construct exact confidence intervals on this ratio.Exact Neyman-Pearson (NP) tests on the variance ratio are described.Their powers provide attainable upper bounds on powers of tests on the variance ratio.Efficiencies of LM tests, which include ANOVA tests, and NP tests are compared for unbalanced, random, one-way ANOVA models.Confidence intervals corresponding to LM tests and NP tests are described.     

Statistical Analysis of Heat Waves in the State of Victoria in Australia

The recent blistering heat waves of 2009 in the state of Victoria in Australia were so unprecedented in terms of duration and intensity that society was largely unprepared. These heat waves caused serious health, social and economic problems. In this paper, the daily maximum temperatures at ten selected stations are studied. Auto‐regressive integrated moving‐average models are used to prewhiten the time series. Uncorrelated, non‐normal and heavy‐tailed residuals are analyzed by means of a new skew t‐mixture distribution. The number of mixture components is effectively determined by an innovative penalisation procedure. It is shown that the resulting skew t‐mixture models provide an acceptable fit in all cases. Possible future temperature patterns are obtained through simulation. It is forecast that the average duration of high temperature episodes will increase by two to three days per year and a new eight‐year high temperature level is very likely in the coming few years. The relationship between heavy tail behaviour of the fitted distribution and heat waves is noteworthy.     

Joint modeling of multivariate censored longitudinal and event time data with application to the Genetic Markers of Inflammation Study

The Genetic Markers of Inflammation Study (GenIMS) was conceived to investigate the role of severe sepsis, which is typically defined as system-wide multi-organ failure, on survival. One major hypothesis for this systemic collapse, and reduction in survival, is a cascade of pro-inflammatory and anti-inflammatory cytokines. In this paper, we devised a novel joint modeling strategy to evaluate the joint effect of longitudinal anti-inflammatory marker IL-6 and pro-inflammatory marker IL-10 on 90-day survival. We found that, on average, patients with high initial values of both IL-6 and IL-10, that tend to increase over time, are associated with a reduction in survival expectancy and that accounting for their assumed correlation was justified.     

Influence Diagnostics of Semiparametric Nonlinear Reproductive Dispersion Models

This article proposes a semiparametric nonlinear reproductive dispersion model (SNRDM) which is an extension of nonlinear reproductive dispersion model and semiparametric regression model. Maximum penalized likelihood estimators (MPLEs) of unknown parameters and nonparametric functions in SNRDMs are presented. Some novel diagnostic statistics such as Cook distance and difference deviance for parametric and nonparametric parts are developed to identify influence observations in SNRDMs on the basis of case-deletion method, and some formulae readily computed with the MPLEs algorithm for diagnostic measures are given. The equivalency of case-deletion models and mean-shift outlier models in SNRDM is investigated. A simulation study and a real example are used to illustrate the proposed diagnostic measures.     

Bayesian networks and the assessment of universities' value added

A broad literature focused on the effectiveness of tertiary education. In classical models, a performance indicator is regressed on a set of characteristics of the individuals and fixed effects at the institution level. The FE coefficients are interpreted as the pure value added of the universities. The innovative contribution of the present paper resides in the use of Bayesian network (BN) analysis to assess the effectiveness of tertiary education. The results of an empirical study focused on Italian universities are discussed, to present the use of BN as a decision support tool for policy-making purposes.     

Collapsibility of contingency tables based on conditional models

Strict collapsibility and model collapsibility are two important concepts associated with the dimension reduction of a multidimensional contingency table, without losing the relevant information. In this paper, we obtain some necessary and sufficient conditions for the strict collapsibility of the full model, with respect to an interaction factor or a set of interaction factors, based on the interaction parameters of the conditional/layer log-linear models. For hierarchical log-linear models, we present also necessary and sufficient conditions for the full model to be model collapsible, based on the conditional interaction parameters. We discuss both the cases where one variable or a set of variables is conditioned. The connections between the strict collapsibility and the model collapsibility are also pointed out. Our results are illustrated through suitable examples, including a real life application.     

Computational aspects of the EM algorithm for spatial econometric models with missing data

Maximum likelihood (ML) estimation with spatial econometric models is a long-standing problem that finds application in several areas of economic importance. The problem is particularly challenging in the presence of missing data, since there is an implied dependence between all units, irrespective of whether they are observed or not. Out of the several approaches adopted for ML estimation in this context, that of LeSage and Pace [Models for spatially dependent missing data. J Real Estate Financ Econ. 2004;29(2):233–254] stands out as one of the most commonly used with spatial econometric models due to its ability to scale with the number of units. Here, we review their algorithm, and consider several similar alternatives that are also suitable for large datasets. We compare the methods through an extensive empirical study and conclude that, while the approximate approaches are suitable for large sampling ratios, for small sampling ratios the only reliable algorithms are those that yield exact ML or restricted ML estimates.