Multiple Imputation by Ordered Monotone Blocks With Application to the Anthrax Vaccine Research Program

Multiple imputation (MI) has become a standard statistical technique for dealing with missing values. The CDC Anthrax Vaccine Research Program (AVRP) dataset created new challenges for MI due to the large number of variables of different types and the limited sample size. A common method for imputing missing data in such complex studies is to specify, for each of J variables with missing values, a univariate conditional distribution given all other variables, and then to draw imputations by iterating over the J conditional distributions. Such fully conditional imputation strategies have the theoretical drawback that the conditional distributions may be incompatible. When the missingness pattern is monotone, a theoretically valid approach is to specify, for each variable with missing values, a conditional distribution given the variables with fewer or the same number of missing values and sequentially draw from these distributions. In this article, we propose the “multiple imputation by ordered monotone blocks” approach, which combines these two basic approaches by decomposing any missingness pattern into a collection of smaller “constructed” monotone missingness patterns, and iterating. We apply this strategy to impute the missing data in the AVRP interim data. Supplemental materials, including all source code and a synthetic example dataset, are available online.     

Secure collaborative supply chain planning and inverse optimization – The JELS model

It is a well-acknowledged fact that collaboration between different members of a supply chain yields a significant potential to increase overall supply chain performance. Sharing private information has been identified as prerequisite for collaboration and, at the same time, as one of its major obstacles. One potential avenue for overcoming this obstacle is Secure Multi-Party Computation (SMC). SMC is a cryptographic technique that enables the computation of any (well-defined) mathematical function by a number of parties without any party having to disclose its input to another party. In this paper, we show how SMC can be successfully employed to enable joint decision-making and benefit sharing in a simple supply chain setting. We develop secure protocols for implementing the well-known “Joint Economic Lot Size (JELS) Model” with benefit sharing in such a way that none of the parties involved has to disclose any private (cost and capacity) data. Thereupon, we show that although computation of the model’s outputs can be performed securely, the approach still faces practical limitations. These limitations are caused by the potential of “inverse optimization”, i.e., a party can infer another party’s private data from the output of a collaborative planning scheme even if the computation is performed in a secure fashion. We provide a detailed analysis of “inverse optimization” potentials and introduce the notion of “stochastic security”, a novel approach to assess the additional information a party may learn from joint computation and benefit sharing. Based on our definition of “stochastic security” we propose a stochastic benefit sharing rule, develop a secure protocol for this benefit sharing rule, and assess under which conditions stochastic benefit sharing can guarantee secure collaboration.     

基于空间自回归模型的缺失值插补方法

本文研究来自于区域的截面数据中缺失值的插补问题,讨论了当数据中存在空间相关时,空间自回归模型的建立以及利用其对缺失值进行插补的方法,并根据实际数据,通过建立模型给出插补结果。     

Capturing incomplete information in resource allocation problems through numerical patterns

We look at the problem of optimizing complex operations with incomplete information where the missing information is revealed indirectly and imperfectly through historical decisions. Incomplete information is characterized by missing data elements governing operational behavior and unknown cost parameters. We assume some of this information may be indirectly captured in historical databases through flows characterizing resource movements. We can use these flows or other quantities derived from these flows as “numerical patterns” in our optimization model to reflect some of the incomplete information. We develop our methodology for representing information in resource allocation models using the concept of pattern regression. We use a popular goodness-of-fit measure known as the Cramer–Von Mises metric as the foundation of our approach. We then use a hybrid approach of solving a cost model with a term known as the “pattern metric” that minimizes the deviations of model decisions from observed quantities in a historical database. We present a novel iterative method to solve this problem. Results with real-world data from a large freight railroad are presented.     

An update on primitive ternary complementary pairs

In two recent papers we overhauled the theory of ternary complementary pairs, focusing on questions relating to the possible weights of pairs, and special pairs from which all others can be derived, which we call “primitive.”Of particular interest at this time is a new refinement of the concept of primitivity, which necessitates some revisions to our tables. In this article we report on the state of the art with respect to primitive pairs and elaborate on some conjectures in light of new data.30 new primitive pairs are given; the status of 12 previously “primitive” pairs is changed to “imprimitive.”     

Model,properties and imputation method of missing SNP genotype data utilizing mutual information

Mutual information can be used as a measure for the association of a genetic marker or a combination of markers with the phenotype. In this paper, we study the imputation of missing genotype data. We first utilize joint mutual information to compute the dependence between SNP sites, then construct a mathematical model in order to find the two SNP sites having maximal dependence with missing SNP sites, and further study the properties of this model. Finally, an extension method to haplotype-based imputation is proposed to impute the missing values in genotype data. To verify our method, extensive experiments have been performed, and numerical results show that our method is superior to haplotype-based imputation methods. At the same time, numerical results also prove joint mutual information can better measure the dependence between SNP sites. According to experimental results, we also conclude that the dependence between the adjacent SNP sites is not necessarily strongest.     

Nonmonotone systems decomposable into monotone systems with negative feedback

Motivated by the work of Angeli and Sontag [Monotone control systems, IEEE Trans. Automat. Control 48 (2003) 1684-1698] and Enciso and Sontag [On the global attractivity of abstract dynamical systems satisfying a small gain hypothesis, with applications to biological delay systems, Discrete Continuous Dynamical Systems, to appear] in control theory, we show that certain finite and infinite dimensional semi-dynamical systems with “negative feedback” can be decomposed into a monotone “open-loop” system with “inputs” and a decreasing “output” function. The original system is reconstituted by “plugging the output into the input”. Employing a technique of Gouzé [A criterion of global convergence to equilibrium for differential systems with an application to Lotka-Volterra systems, Rapport de Recherche 894, INRIA] and Cosner [Comparison principles for systems that embed in cooperative systems, with applications to diffusive Lotka-Volterra models, Dynam. Cont., Discrete Impulsive Systems 3 (1997) 283-303] of imbedding the system into a larger symmetric monotone system, we are able to obtain information on the asymptotic behavior of solutions, including existence of positively invariant sets and global convergence.     

Computation of the invariant measure for a Lévy driven SDE: Rate of convergence

We study the rate of convergence of some recursive procedures based on some “exact” or “approximate” Euler schemes which converge to the invariant measure of an ergodic SDE driven by a Lévy process. The main interest of this work is to compare the rates induced by “exact” and “approximate” Euler schemes. In our main result, we show that replacing the small jumps by a Brownian component in the approximate case preserves the rate induced by the exact Euler scheme for a large class of Lévy processes.     

The affect heuristic

This paper introduces a theoretical framework that describes the importance of affect in guiding judgments and decisions. As used here, “affect” means the specific quality of “goodness” or “badness” (i) experienced as a feeling state (with or without consciousness) and (ii) demarcating a positive or negative quality of a stimulus. Affective responses occur rapidly and automatically—note how quickly you sense the feelings associated with the stimulus word “treasure” or the word “hate”. We argue that reliance on such feelings can be characterized as “the affect heuristic”. In this paper we trace the development of the affect heuristic across a variety of research paths followed by ourselves and many others. We also discuss some of the important practical implications resulting from ways that this heuristic impacts our daily lives.     

A new rating system for duplicate bridge

We propose a new way to rate individual duplicate bridge players, which we believe is superior to the masterpoint system currently used by the American Contract Bridge League. This method measures only a player’s current skill level, and not how long or how frequently he has played. It is based on simple ideas from the theory of statistics and from linear algebra, and should be easy to implement.One particular issue which can occur within any system proposing to rate individual players using results earned by partnerships is what we call the “nonuniqueness problem”. This refers to the occasional inability for data to distinguish who is the “good player” and who is the “bad player” within particular partnerships. We prove that under our system this problem disappears if either (a) a certain “partnership graph” has no bipartite components, or if (b) every player is required to participate in at least one individual game.Finally, we present some data from a bridge club in Reno, NV. They show that even if (a) and (b) do not hold, our system will provide (unique) ratings for most players.     

When not to analyze data: Decision making on missing responses in dual scaling

In exploratory data analysis, handling of missing responses requires special considerations because of the absence of a model for them. This study investigates effects of missing responses on dual scaling results, in particular a practical decision rule when to and not to impute for missing responses. More specifically, three questions are asked: when to discard a subject, when to exclude a variable, and when to stop data analysis entirely. The decision rule is based on the concept of substantial discrepancy in the scaling outcome between the best and worst imputations for missing responses. This problem is discussed in the context of the current knowledge on missing responses in data analysis.     

本刊英文版Vol.37(2021),No.12论文摘要（英文）

<正>Empirical Likelihood of Quantile Difference with Missing Response When High-dimensional Covariates Are Present Cui Juan KONG Han Ying LIANG Abstract We,in this paper,investigate two-sample quantile difference by empirical likelihood method when the responses with high-dimensional covariates of the two populations are missing at random.In particular,based on sufficient dimension reduction technique,we construct three empirical log-likelihood ratios for the quantile difference between two samples by using inverse probability weighting imputation,regression imputation as well as augmented inverse probability weighting imputation,respectively,and prove their asymptotic distributions.     

An Imputation Method for Missing Data in Compositional Based on Epanechnikov Kernel

Kernel function method has been successfully used for the estimation of a variety of function. By using the kernel function theory, an imputation method based on Epanechnikov kernel and its modification were proposed to solve the problem that missing data in compositional caused the failures of existing statistical methods and the k-nearest imputation didn't consider the different contributions of the k nearest samples when it used them to estimated the missing data. The experimental results illustrate that the modified imputation method based on Epanechnikov kernel get a more accurate estimation than k-nearest imputation for compositional data.     

New affine measures of symmetry for convex bodies

Grünbaum introduced measures of symmetry for convex bodies that measure how far a given convex body is from a centrally symmetric one. Here, we introduce new measures of symmetry that measure how far a given convex body is from one with “enough symmetries”.To define these new measures of symmetry, we use affine covariant points. We give examples of convex bodies whose affine covariant points are “far apart”. In particular, we give an example of a convex body whose centroid and Santaló point are “far apart”.     

A comparison of different quantity discount pricing policies in a two-echelon channel with stochastic and asymmetric demand information

In this paper, we study quantity discount pricing policies in a channel of one manufacturer and one retailer. The paper assumes that the channel faces a stochastic price-sensitive demand but the retailer can privately observe the realization of an uncertain demand parameter. The problem is analyzed as a Stackelberg game in which the manufacturer declares quantity discount pricing schemes to the retailer and then the retailer follows by selecting the retail price and associated quantity. Proposed in the paper are four quantity-discount pricing policies: “regular quantity discount”; “fixed percentage discount”; “incremental volume discount” and “fixed marginal-profit-rate discount”. Optimal solutions are derived, and numerical examples are presented to illustrate the efficiency of each discount policy.     

分数填补下两总体分位数差异的经验似然置信区间

设有两个非参数总体,其样本数据不完全,用分数填补法补足缺失数据,得到两总体的"完全"样本数据,在此基础上构造两总体分位数差异的经验似然置信区间.模拟结果显示,分数填补法可以得到更加精确的置信区间.     

Effects of missing data in credit risk scoring. A comparative analysis of methods to achieve robustness in the absence of sufficient data

The 2004 Basel II Accord has pointed out the benefits of credit risk management through internal models using internal data to estimate risk components: probability of default (PD), loss given default, exposure at default and maturity. Internal data are the primary data source for PD estimates; banks are permitted to use statistical default prediction models to estimate the borrowers’ PD, subject to some requirements concerning accuracy, completeness and appropriateness of data. However, in practice, internal records are usually incomplete or do not contain adequate history to estimate the PD. Current missing data are critical with regard to low default portfolios, characterised by inadequate default records, making it difficult to design statistically significant prediction models. Several methods might be used to deal with missing data such as list-wise deletion, application-specific list-wise deletion, substitution techniques or imputation models (simple and multiple variants). List-wise deletion is an easy-to-use method widely applied by social scientists, but it loses substantial data and reduces the diversity of information resulting in a bias in the model's parameters, results and inferences. The choice of the best method to solve the missing data problem largely depends on the nature of missing values (MCAR, MAR and MNAR processes) but there is a lack of empirical analysis about their effect on credit risk that limits the validity of resulting models. In this paper, we analyse the nature and effects of missing data in credit risk modelling (MCAR, MAR and NMAR processes) and take into account current scarce data set on consumer borrowers, which include different percents and distributions of missing data. The findings are used to analyse the performance of several methods for dealing with missing data such as likewise deletion, simple imputation methods, MLE models and advanced multiple imputation (MI) alternatives based on MarkovChain-MonteCarlo and re-sampling methods. Results are evaluated and discussed between models in terms of robustness, accuracy and complexity. In particular, MI models are found to provide very valuable solutions with regard to credit risk missing data.     

随机缺失数据下样本分位数估计

分位数的估计在生物医学、社会经济调查等领域有着广泛的应用,然而在实际问题的研究中,往往由于各种人为或不可控因素造成数据收集不完全.本文在随机缺失(MAR)假设条件下,利用非参数核补法和局部多重插补法给出了响应变量缺失时样本分位数的估计,并利用经验过程等理论证明了由这两种方法得到的分位数估计的大样本性质,同时,使用重抽样方法给出了估计的渐近方差的估计,模拟结果验证了这两种方法的有效性.文章所提两种方法的优点在于:首先,所提出的缺失修正方法不需要对缺失概率的模型做任何假设;其次,方法亦适用于其他有关参数不可微的估计目标函数;最后,方法很容易地推广到一般M估计的情况,并可以对多个分位数同时进行估计.     

The additive model affected by missing completely at random in the covariate

Summary  The main purpose of this paper is a comparison of several imputation methods within the simple additive modelty =f(x) + ε where the independent variableX is affected by missing completely at random. Besides the well-known complete case analysis, mean imputation plus random noise, single imputation and two kinds of nearest neighbor imputations are used. A short introduction to the model, the missing mechanism, the inference, the imputation methods and their implementation is followed by the main focus—the simulation experiment. The methods are compared within the experiment based on the sample mean squared error, estimated variances and estimated biases off(x) at the knots.     

A local proof for the characterization of Young measures generated by sequences in BV

This work presents a new proof of the recent characterization theorem for generalized Young measures generated by sequences in BV by Kristensen and Rindler (2010) [14]. The present argument is based on a localization technique together with a local Hahn–Banach argument in novel function spaces combined with an application of Alberti's Rank-One Theorem. This strategy avoids employing a relaxation theorem as in the previously known proof, and the new tools introduced in its course should prove useful in other contexts as well. In particular, we introduce “homogeneous” Young measures, separately at regular and singular points, which exhibit rather different behavior than the classical homogeneous Young measures. As an application, we show how for BV-Young measures with an “atomic” part one can find a generating sequence respecting this structure.