Approximate Conditional Inference in Logistic and Loglinear Models

Abstract

Recently developed small-sample asymptotics provide nearly exact inference for parametric statistical models. One approach is via approximate conditional and marginal inference, respectively, in multiparameter exponential families and regression-scale models. Although the theory is well developed, these methods are under-used in practical work. This article presents a set of S-Plus routines for approximate conditional inference in logistic and loglinear regression models. It represents the first step of a project to create a library for small-sample inference which will include methods for some of the most widely used statistical models. Details of how the methods have been implemented are discussed. An example illustrates the code.     

Visualizing parameters from loglinear models

Summary  This paper presents a graphical display for the parameters resulting from loglinear models. Loglinear models provide a method for analyzing associations between two or several categorical variables and have become widely accepted as a tool for researchers during the last two decades. An important part of the output of any computer program focused on loglinear models is that devoted to estimation of parameters in the model. Traditionally, this output has been presented using tables that indicate the values of the coefficients, the associated standard errors and other related information. Evaluation of these tables can be rather tedious because of the number of values shown as well as their rather complicated structure, mainly when the analyst needs to consider several models before reaching a model with a good fit. Therefore, a graphical display summarizing tables of parameters could be of great help in this situation. In this paper we put forward an interactive dynamic graphical display that could be used in such fashion.     

Residual-Based Shadings for Visualizing (Conditional) Independence

Residual-based shadings for enhancing mosaic and association plots to visualize independence models for contingency tables are extended in two directions: (a) perceptually uniform Hue-Chroma-Luminance (HCL) colors are used and (b) the result of an associated significance test is coded by the appearance of color in the visualization. For obtaining (a), a general strategy for deriving diverging palettes in the perceptually based HCL space is suggested. As for (b), cutoffs that control the appearance of color are computed in a data-driven way based on the conditional permutation distribution of maximum-type test statistics. The shadings are first established for the case of independence in two-way tables and then extended to more general independence models for multiway tables, including in particular conditional independence models.     

用对数线性模型比较香港居民在超市与便利店的购买行为

对于抽样调查比较香港居民在超市与便利店的购买行为所得的配对设计的方列联表数据，用对数线性模型进行分析。     

Markov Bases of Binary Graph Models

This paper is concerned with the topological invariant of a graph given by the maximum degree of a Markov basis element for the corresponding graph model for binary contingency tables. We describe a degree four Markov basis for the model when the underlying graph is a cycle and generalize this result to the complete bipartite graph K_2,n. We also give a combinatorial classification of degree two and three Markov basis moves as well as a Buchberger-free algorithm to compute moves of arbitrary given degree. Finally, we compute the algebraic degree of the model when the underlying graph is a forest.AMS Subject Classification: 05C99, 13P10, 62Q05.     

Visualizing Online Auctions

Online auctions have been the subject of many empirical research efforts in the fields of economics and information systems. These research efforts are often based on analyzing data from Web sites such as eBay.com which provide public information about sequences of bids in closed auctions, typically in the form of tables on HTML pages. The existing literature on online auctions focuses on tools like summary statistics and more formal statistical methods such as regression models. However, there is a clear void in this growing body of literature in developing appropriate visualization tools. This is quite surprising, given that the sheer amount of data that can be found on sites such as eBay.com is overwhelming and can often not be displayed informatively using standard statistical graphics. In this article we introduce graphical methods for visualizing online auction data in ways that are informative and relevant to the types of research questions that are of interest. We start by using profile plots that reveal aspects of an auction such as bid values, bidding intensity, and bidder strategies. We then introduce the concept of statistical zooming (STAT-zoom) which can scale up to be used for visualizing large amounts of auctions. STAT-zoom adds the capability of looking at data summaries at various time scales interactively. Finally, we develop auction calendars and auction scene visualizations for viewing a set of many concurrent auctions. The different visualization methods are demonstrated using data on multiple auctions collected from eBay.com.     

Generalized Odds Ratios for Visual Modeling

The problem of displaying interaction effects graphically has been studied for a long time. This article shows how mosaic plots can be applied to visualize interaction effects in categorical data. This idea leads to a graphical approach for model selection based on a classical backward selection.     

Decomposition of Covariate-Dependent Graphical Models with Categorical Data

Graphical models are wildly used to describe conditional dependence relationships among interacting random variables. Among statistical inference problems of a graphical model, one particular interest is utilizing its interaction structure to reduce model complexity. As an important approach to utilizing structural information, decomposition allows a statistical inference problem to be divided into some sub-problems with lower complexities. In this paper, to investigate decomposition of covariate-dependent graphical models, we propose some useful definitions of decomposition of covariate-dependent graphical models with categorical data in the form of contingency tables. Based on such a decomposition, a covariate-dependent graphical model can be split into some sub-models, and the maximum likelihood estimation of this model can be factorized into the maximum likelihood estimations of the sub-models. Moreover, some sufficient and necessary conditions of the proposed definitions of decomposition are studied.     

The Plot-Data Interface in Statistical Graphics

Abstract

Statistical software systems include modules for manipulating data sets, model fitting, and graphics. Because plots display data, and models are fit to data, both the model-fitting and graphics modules depend on the data. Today's statistical environments allow the analyst to choose or even build a suitable data structure for storing the data and to implement new kinds of plots. The multiplicity problem caused by many plot varieties and many data representations is avoided by constructing a plot-data interface. The interface is a convention by which plots communicate with data sets, allowing plots to be independent of the actual data representation. This article describes the components of such a plot-data interface. The same strategy may be used to deal with the dependence of model-fitting procedures on data.     

Visualization of Categorical Response Models: From Data Glyphs to Parameter Glyphs

The multinomial logit model is the most widely used model for nominal multi-category responses. One problem with the model is that many parameters are involved, and another that interpretation of parameters is much harder than for linear models because the model is nonlinear. Both problems can profit from graphical representations. We propose to visualize the effect strengths by star plots, where one star collects all the parameters connected to one term in the linear predictor. In simple models, one star refers to one explanatory variable. In contrast to conventional star plots, which are used to represent data, the plots represent parameters and are considered as parameter glyphs. The set of stars for a fitted model makes the main features of the effects of explanatory variables on the response variable easily accessible. The method is extended to ordinal models and illustrated by several datasets. Supplementary materials are available online.     

An interactive approach for Bayesian network learning using domain/expert knowledge

Using domain/expert knowledge when learning Bayesian networks from data has been considered a promising idea since the very beginning of the field. However, in most of the previously proposed approaches, human experts do not play an active role in the learning process. Once their knowledge is elicited, they do not participate any more. The interactive approach for integrating domain/expert knowledge we propose in this work aims to be more efficient and effective. In contrast to previous approaches, our method performs an active interaction with the expert in order to guide the search based learning process. This method relies on identifying the edges of the graph structure which are more unreliable considering the information present in the learning data. Another contribution of our approach is the integration of domain/expert knowledge at different stages of the learning process of a Bayesian network: while learning the skeleton and when directing the edges of the directed acyclic graph structure.     

Schemata, Distributions and Graphical Models in Evolutionary Optimization

In this paper the optimization of additively decomposed discrete functions is investigated. For these functions genetic algorithms have exhibited a poor performance. First the schema theory of genetic algorithms is reformulated in probability theory terms. A schema defines the structure of a marginal distribution. Then the conceptual algorithm BEDA is introduced. BEDA uses a Boltzmann distribution to generate search points. From BEDA a new algorithm, FDA, is derived. FDA uses a factorization of the distribution. The factorization captures the structure of the given function. The factorization problem is closely connected to the theory of conditional independence graphs. For the test functions considered, the performance of FDA—in number of generations till convergence—is similar to that of a genetic algorithm for the OneMax function. This result is theoretically explained.     

CARTscans: A Tool for Visualizing Complex Models

We present CARTscans, a graphical tool that displays predicted values across a fourdimensional subspace. We show how these plots are useful for understanding the structure and relationships between variables in a wide variety of models, including (but not limited to) regression trees, ensembles of trees, and linear regressions with varying degrees of interactions. In addition, the common visualization framework allows diverse complex models to be visually compared in a way that illuminates the similarities and differences in the underlying methods, facilitates the choice of a particular model structure, and provides a useful check for implausible predictions of future observations in regions with little or no data.     

Spatial Regression Models,Response Surfaces,and Process Optimization

Abstract

Spatial regression models are developed as a complementary alternative to second-order polynomial response surfaces in the context of process optimization. These models provide estimates of design variable effects and smooth, data-faithful approximations to the unknown response function over the design space. The predicted response surfaces are driven by the covariance structures of the models. Several structures, isotropic and anisotropic, are considered and connections with thin plate splines are reviewed. Estimation of covariance parameters is achieved via maximum likelihood and residual maximum likelihood. A feature of the spatial regression approach is the visually appealing graphical summaries that are produced. These allow rapid and intuitive identification of process windows on the design space for which the response achieves target performance. Relevant design issues are briefly discussed and spatial designs, such as the packing designs available in Gosset, are suggested as a suitable design complement. The spatial regression models also perform well with no global design, for example with data obtained from series of designs on the same space of design variables. The approach is illustrated with an example involving the optimization of components in a DNA amplification assay. A Monte Carlo comparison of the spatial models with both thin plate splines and second-order polynomial response surfaces for a scenario motivated by the example is also given. This shows superior performance of the spatial models to the second-order polynomials with respect to both prediction over the complete design space and for cross-validation prediction error in the region of the optimum. An anisotropic spatial regression model performs best for a high noise case and both this model and the thin plate spline for a low noise case. Spatial regression is recommended for construction of response surfaces in all process optimization applications.     

奥运临时超市选址的优化模型

首先依据问卷调查的数据,分析了年龄结构、购物需求、出行、用餐方式之间的关系,然后进一步用逐步回归方法找出了对顾客消费额影响较大的因素为年龄结构、性别结构.以此为依据测算出20个商区的人流量的百分比分布,其中人流量最大的节点依次为:A6,B6,C4.对于各商区的人流量先折换成实际购物的标准人,然后以此作为超市规模的确定标准建模求解,建立以商业营利最大为目标,超市分布均衡及满足购物需求为约束的整数规划的选址模型,确定了在不同超市规模下,A、B、C三区应拥有的超市个数及各超市的具体所在.     

Models and people: An alternative view of the emergent properties of computational models

Computer models can help humans gain insight into the functioning of complex systems. Used for training, they can also help gain insight into the cognitive processes humans use to understand these systems. By influencing humans understanding (and consequent actions) computer models can thus generate an impact on both these actors and the very systems they are designed to simulate. When these systems also include humans, a number of self‐referential relations thus emerge which can lead to very complex dynamics. This is particularly true when we explicitly acknowledge and model the existence of multiple conflicting representations of reality among different individuals. Given the increasing availability of computational devices, the use of computer models to support individual and shared decision making could potentially have implications far wider than the ones often discussed within the Information and Communication Technologies community in terms of computational power and network communication. We discuss some theoretical implications and describe some initial numerical simulations. © 2015 Wiley Periodicals, Inc. Complexity 21: 202–213, 2016     

Visualizing the Relationship between Two Time Series by Hierarchical Smoothing Models

Abstract

Let x(t_i), y(t_i) be two time series such that y(t_i) = μ(t_i, x) + ε_i, where μ is a smooth function and ε_i is a zero mean stationary process. Which model may be assumed for μ depends on the subject specific context. This article was motivated by questions raised in the context of musical performance theory. The general problem is to understand the relationship between the symbolic structure of a music score and its performance. Musical structure typically consists of a hierarchy of global and local structures. This motivates the definition of hierarchical smoothing models (or HISMOOTH models) that are characterized by a hierarchy of bandwidths b ₁ > b ₂ > … > b_M and a vector of coefficients β ∈ R^M. The expected value μ(t_i x) = E[y(t_i)‖x] is equal to a weighted sum of smoothed versions of x. The “errors” ε_i are modeled by a Gaussian process that may exhibit long memory. More generally, we may observe a collection of time series y_r (r = 1, …, N) that are related to a common time series x by y_r(t_i) = μ _r(t_i, x) + ε_{r, i} where ε _r are independent error processes. For repeated time series, HISMOOTH models lead to a visual and formal classification into clusters that can be interpreted in terms of the relationship to x. An analysis of tempo curves from 28 performances of Schumann's “Träumerei” op. 15/7 illustrates the method. In particular, similarities and differences of “melodic styles” can be identified.     

基于时序图模型结构估计的股票联动研究

我国股市个股价格同时上涨或同时下跌的联动现象极为普遍,传统上使用向量自回归、协整、有向非循环图等方法主要用于少量股票或市场之间的联动性研究,不适于直接对大规模个股之间的联动关系进行研究。文章关注大规模时序图模型结构建立及估计方法,通过将ADL方法引入SPACE算法,提出了可以估计高维低样时序图模型的ADL-SPACE算法;设计模拟实验考察了算法中惩罚参数λ值的设置对于节点自回归相关性捕获的有效性;在实证研究中,文章使用了ADL-SPACE算法对个股联动研究了三方面的内容:1.基于个股联动的代表性行业之间的联动性;2.设计了我国A股市场中行业联动强度,对行业内外联动性进行综合评价和分析;3.采用一阶滞后个股基于时序图模型结果构造了投资组合,模拟显示收益预期表现良好。以上研究均表明时序SPACE图模型方法在大规模股票的联动探测中有较好的应用前景。