Robust model selection with flexible trimming

The forward search provides data-driven flexible trimming of a C_p statistic for the choice of regression models that reveals the effect of outliers on model selection. An informed robust model choice follows. Even in small samples, the statistic has a null distribution indistinguishable from an F distribution. Limits on acceptable values of the C_p statistic follow. Two examples of widely differing size are discussed. A powerful graphical tool is the generalized candlestick plot, which summarizes the information on all forward searches and on the choice of models. A comparison is made with the use of M-estimation in robust model choice.     

Bacterial Fibrinolytic Enzyme Coding Sequences from Indonesian Traditional Fermented Foods Isolated Using Metagenomic Approach and Their Expression in Escherichia Coli

Fibrinolytic proteins play an important role in treatment of cardiovascular disease. This study aimed to express coding sequences of new bacterial fibrinolytic protein from Indonesian traditional fermented foods obtained by a PCR-based metagenomic approach and to test their biological activity. New amino acid variations were found in nattokinase (NAT) at several positions i.e. D41N and V192A from dried Tauco, V4F, D41N, and V192A from yellow Oncom but not in Douchy Fibrinolytic Enzyme (DFE) from Terasi. The NAT and DFE recombinant versions were overproduced in Escherichia coli BL21(DE3) using pET16b(+). Sodium Dodecyl Sulfate Polyacrylamide Gel Electrophoresis analysis showed all clones produced mature soluble fibrinolytic proteins of 28 kDa. All recombinant proteins displayed caseinolytic and fibrinolytic activities. In conclusion, metagenomic approach can be applied to obtain and to express coding sequences of new variant bacterial fibrinolytic protein as active soluble mature form in E. coli.     

Using an eye tracker for accurate eye movement artifact correction

We present a new method to correct eye movement artifacts in electroencephalogram (EEG) data. By using an eye tracker, whose data cannot be corrupted by any electrophysiological signals, an accurate method for correction is developed. The eye-tracker data is used in a Kalman filter to estimate which part of the EEG is of ocular origin. The main assumptions for optimal correction are summed and their validity is proven. The eye-tracker-based correction method is objectively evaluated on simulated data of four different types of eye movements and visually evaluated on experimental data. Results are compared to three established correction methods: Regression, Principal Component Analysis, and Second-Order Blind Identification. A comparison of signal to noise ratio after correction by these methods is given in Table II and shows that our method is consistently superior to the other three methods, often by a large margin. The use of a reference signal without electrophysiological influences, as provided by an eye tracker, is essential to achieve optimal eye movement artifact removal.     

Tests in the fan plot for robust, diagnostic transformations in regression

The fan plot of the score statistic for transformation during the forward search is a powerful tool for detecting masked outliers that indicate an incorrect transformation. We use simulation to investigate the distribution of this statistic during the search. Data structures where the normal approximation is, and is not, satisfactory are characterised.     

Ternary rare-earth aluminum systems with copper: A review and a contribution to their assessment

Constitutional data of the R-Cu-Al systems, with R = rare earth, are summarized and discussed. Crystal structures of the phases formed in the binary boundary systems and in the ternary systems are assessed, and the phase equilibria observed in the reported ternary systems are reviewed with special attention given to the isothermal and polythermal sections of the phase diagrams. Some regularities observed in the trends of the constitutional properties of the ternary R-Cu-Al alloys are briefly described.     

Yttria-stabilized zirconia (YSZ) supported Ni–Co alloys (precursor of SOFC anodes) as catalysts for the steam reforming of ethanol

Bioethanol is an attractive fuel for direct internal reforming SOFC (DIR-SOFC). The aim of this work is to investigate the activity of Ni–YSZ, used as precursor for the preparation of SOFC anodes and as catalyst of the ethanol steam reforming reaction. The effect of the addition of cobalt is also studied, as the best performance is given by Ni–Co (25:25)/YSZ catalyst. This achieves total conversion of ethanol around 670 K, at which temperature the H₂ yield is 65%. The addition of Co results in the inhibition of the dehydration reaction as well as of methane production. Furthermore, Co also has an effect on the hydrogen yield, by increasing it and thus apparently favouring methane steam reforming.     

On consistency factors and efficiency of robust S-estimators

We tackle the problem of obtaining the consistency factors of robust S-estimators of location and scale both in regression and multivariate analysis. We provide theoretical results, proving new formulae for their calculation and shedding light on the relationship between these factors and important statistical properties of S-estimators. We also give computational advances, suggesting efficient procedures so that hardly any time is lost for their calculation when computing S-estimates. In addition, when the purpose is to fix the efficiency of the scale estimator, we are able to quantify to what extent the approximate algorithms which are currently available provide an acceptable solution, and when it is necessary to resort to the exact formulae. Finally, even if this paper concentrates on S-estimates and Tukey’s Biweight and optimal loss functions, the main results can be easily extended to calculate the tuning consistency factors for other popular loss function and other robust estimators.