Handling Missing Values with Regularized Iterative Multiple Correspondence Analysis

A common approach to deal with missing values in multivariate exploratory data analysis consists in minimizing the loss function over all non-missing elements, which can be achieved by EM-type algorithms where an iterative imputation of the missing values is performed during the estimation of the axes and components. This paper proposes such an algorithm, named iterative multiple correspondence analysis, to handle missing values in multiple correspondence analysis (MCA). The algorithm, based on an iterative PCA algorithm, is described and its properties are studied. We point out the overfitting problem and propose a regularized version of the algorithm to overcome this major issue. Finally, performances of the regularized iterative MCA algorithm (implemented in the R-package named missMDA) are assessed from both simulations and a real dataset. Results are promising with respect to other methods such as the missing-data passive modified margin method, an adaptation of the missing passive method used in Gifi’s Homogeneity analysis framework.     

Forecasting models in the manufacturing processes and operations management: Systematic literature review

The purpose of this paper is to present the result of a systematic literature review regarding the application and development of forecasting models in the industrial context, especially the context of manufacturing processes and operations management. The study was conducted considering the preparation of an established research protocol to know, discuss, and analyze the main approaches adopted by researchers in the field. To achieve this objective, we analyzed 354 recent papers published in periodicals between 2008 and 2018. This paper makes three main contributions to the field: (i) it presents an updated portfolio of prediction models in the industrial context, providing a reference point for researchers and industrial managers; (ii) it presents a characterization of the field of study through the identification of publication vehicles, frequency, and the principal authors and countries related to the development of research on the theme; (iii) it proposes a unified framework, listing the characteristics of the prediction models with their respective application contexts, identifying the current research directions to provide theoretical aids for the development of new approaches to forecasting in industry. The results of this study provide an empirical base for further discussions on studies that focus on forecasting in the industrial context.     

Carapace ontogeny of the bromeliad dwelling ostracod Elpidium bromeliarum Müller, 1880 (Crustacea: Ostracoda)

Ostracods have discontinuous development, marked by ecdyses, and determinate growth. Ontogenetic studies have suggested a pattern of nine postembryonic stages (eight juvenile phases and the adult) for the main freshwater ostracod superfamilies Cypridoidea, Cytheroidea and Darwinuloidea. However, cases of a supposed extra moult in the adult stage have been proposed for some ostracod species, which would amount to 10 postembryonic growth stages. One such example is Elpidium bromeliarum Müller, 1880, a cytheroidean that inhabits tank-bromeliads. The present study is aimed at investigating the ontogenetic development of E. bromeliarum using width and length measurements, as well as carapace and appendage morphology in order to test the existing hypothesis of an additional growth stage in adults of this species. Our results revealed nine postembryonic growth stages (eight juvenile and the adult), with sexual dimorphism beginning its expression in the last juvenile stage. Thus, the ontogenetic development of E. bromeliarum agrees with the overall pattern observed for podocopid ostracods and the hypothesis of 10 postembryonic growth stages was not corroborated. We argue that the inability to differentiate juveniles from adults, or different species from one another, may have misled to the assumption of an additional moult in E. bromeliarum.     

Rip it up and start again: The rejection of a characterization of a phenomenon

In this paper, I investigate the nature of empirical findings that provide evidence for the characterization of a scientific phenomenon, and the defeasible nature of this evidence. To do so, I explore an exemplary instance of the rejection of a characterization of a scientific phenomenon: memory transfer. I examine the reason why the characterization of memory transfer was rejected, and analyze how this rejection tied to researchers’ failures to resolve experimental issues relating to replication and confounds. I criticize the presentation of the case by Harry Collins and Trevor Pinch, who claim that no sufficient reason was provided to abandon research on memory transfer. I argue that skeptics about memory transfer adopted what I call a defeater strategy, in which researchers exploit the defeasibility of the evidence for a characterization of a phenomenon.     

CCDC39 is required for assembly of inner dynein arms and the dynein regulatory complex and for normal ciliary motility in humans and dogs

Primary ciliary dyskinesia (PCD) is an inherited disorder characterized by recurrent infections of the upper and lower respiratory tract, reduced fertility in males and situs inversus in about 50% of affected individuals (Kartagener syndrome). It is caused by motility defects in the respiratory cilia that are responsible for airway clearance, the flagella that propel sperm cells and the nodal monocilia that determine left-right asymmetry. Recessive mutations that cause PCD have been identified in genes encoding components of the outer dynein arms, radial spokes and cytoplasmic pre-assembly factors of axonemal dyneins, but these mutations account for only about 50% of cases of PCD. We exploited the unique properties of dog populations to positionally clone a new PCD gene, CCDC39. We found that loss-of-function mutations in the human ortholog underlie a substantial fraction of PCD cases with axonemal disorganization and abnormal ciliary beating. Functional analyses indicated that CCDC39 localizes to ciliary axonemes and is essential for assembly of inner dynein arms and the dynein regulatory complex.     

Recessive LAMC3 mutations cause malformations of occipital cortical development

The biological basis for regional and inter-species differences in cerebral cortical morphology is poorly understood. We focused on consanguineous Turkish families with a single affected member with complex bilateral occipital cortical gyration abnormalities. By using whole-exome sequencing, we initially identified a homozygous 2-bp deletion in LAMC3, the laminin γ3 gene, leading to an immediate premature termination codon. In two other affected individuals with nearly identical phenotypes, we identified a homozygous nonsense mutation and a compound heterozygous mutation. In human but not mouse fetal brain, LAMC3 is enriched in postmitotic cortical plate neurons, localizing primarily to the somatodendritic compartment. LAMC3 expression peaks between late gestation and late infancy, paralleling the expression of molecules that are important in dendritogenesis and synapse formation. The discovery of the molecular basis of this unusual occipital malformation furthers our understanding of the complex biology underlying the formation of cortical gyrations.     

Large-scale analysis of the regulatory architecture of the mouse genome with a transposon-associated sensor

We present here a Sleeping Beauty-based transposition system that offers a simple and efficient way to investigate the regulatory architecture of mammalian chromosomes in vivo. With this system, we generated several hundred mice and embryos, each with a regulatory sensor inserted at a random genomic position. This large sampling of the genome revealed the widespread presence of long-range regulatory activities along chromosomes, forming overlapping blocks with distinct tissue-specific expression potentials. The presence of tissue-restricted regulatory activities around genes with widespread expression patterns challenges the gene-centric view of genome regulation and suggests that most genes are modulated in a tissue-specific manner. The local hopping property of Sleeping Beauty provides a dynamic approach to map these regulatory domains at high resolution and, combined with Cre-mediated recombination, allows for the determination of their functions by engineering mice with specific chromosomal rearrangements.     

Lack of Na+,K+-ATPase expression in intercalated cells may be compensated by Na+-ATPase: A study on MDCK – C11 cells

The lack of Na⁺,K⁺-ATPase expression in intercalated cells (IC) is an intriguing condition due to its fundamental role in cellular homeostasis. In order to better understand this question we compared the activities of Na⁺,K⁺-ATPase and Na⁺-ATPase in two MDCK cell clones: the C11, with IC characteristics, and the C7, with principal cells (PC) characteristics. The Na⁺,K⁺-ATPase activity found in C11 cells is far lower than in C7 cells and the expression of its β-subunit is similar in both cells. On the other hand, a subset of C11 without α-subunit expression has been found. In C11 cells the Na⁺-ATPase activity is higher than that of the Na⁺,K⁺-ATPase, and it is increased by medium alkalinization, suggesting that it could account for the cellular Na⁺-homeostasis. Although further studies are necessary for a better understanding of these findings, the presence of Na⁺-ATPase may explain the adequate survival of cells that lack Na⁺,K⁺-ATPase. Received 09 July 2008; received after revision 03 August 2008; accepted 12 August 2008     

Yield Curve Forecasting with the Burg Model

We introduce a versatile and robust model that may help policymakers, bond portfolio managers and financial institutions to gain insight into the future shape of the yield curve. The Burg model forecasts a 20‐day yield curve, which fits a pth‐order autoregressive (AR) model to the input signal by minimizing (least squares) the forward and backward prediction errors while constraining the autoregressive parameters to satisfy the Levinson–Durbin recursion. Then, it uses an infinite impulse response prediction error filter. Results are striking when the Burg model is compared to the Diebold and Li model: the model not only significantly improves accuracy, but also its forecast yield curves stick to the shape of observed yield curves, whether normal, humped, flat or inverted. Copyright © 2016 John Wiley & Sons, Ltd.