Robust Maximum Association Between Data Sets: The R Package ccaPP

An intuitive measure of association between two multivariate data sets can be defined as the maximal value that a bivariate association measure between any one-dimensional projections of each data set can attain. Rank correlation measures thereby have the advantage that they combine good robustness properties with good efficiency. The software package ccaPP provides fast implementations of such maximum association measures for the statistical computing environment R. We demonstrate how to use package ccaPP to compute the maximum association measures, as well as how to assess their significance via permutation tests.

RoPEUS: A New Robust Algorithm for Static Positioning in Ultrasonic Systems

A well known problem for precise positioning in real environments is the presence of outliers in the measurement sample. Its importance is even bigger in ultrasound based systems since this technology needs a direct line of sight between emitters and receivers. Standard techniques for outlier detection in range based systems do not usually employ robust algorithms, failing when multiple outliers are present. The direct application of standard robust regression algorithms fails in static positioning (where only the current measurement sample is considered) in real ultrasound based systems mainly due to the limited number of measurements and the geometry effects. This paper presents a new robust algorithm, called RoPEUS, based on MM estimation, that follows a typical two-step strategy: 1) a high breakdown point algorithm to obtain a clean sample, and 2) a refinement algorithm to increase the accuracy of the solution. The main modifications proposed to the standard MM robust algorithm are a built in check of partial solutions in the first step (rejecting bad geometries) and the off-line calculation of the scale of the measurements. The algorithm is tested with real samples obtained with the 3D-LOCUS ultrasound localization system in an ideal environment without obstacles. These measurements are corrupted with typical outlying patterns to numerically evaluate the algorithm performance with respect to the standard parity space algorithm. The algorithm proves to be robust under single or multiple outliers, providing similar accuracy figures in all cases.

Depression and socio-economic risk factors: 7-year longitudinal population study

BACKGROUND

Low socio-economic status is associated with a higher prevalence of depression, but it is not yet known whether change in socio-economic status leads to a change in rates of depression.

AIMS

To assess whether longitudinal change in socio-economic factors affects change of depression level.

METHOD

In a prospective cohort study using the annual Belgian Household Panel Survey (1992-1999), depression was assessed using the Global Depression Scale. Socio-economic factors were assessed with regard to material standard of living, education, employment status and social relationships.

RESULTS

A lowering in material standard of living between annual waves was associated with increases in depressive symptoms and caseness of major depression. Life circumstances also influenced depression. Ceasing to cohabit with a partner increased depressive symptoms and caseness, and improvement in circumstances reduced them; the negative effects were stronger than the positive ones.

CONCLUSIONS

The study showed a clear relationship between worsening socio-economic circumstances and depression.

Variable Selection for Logistic Regression Using a Prediction-Focused Information Criterion

In biostatistical practice, it is common to use information criteria as a guide for model selection. We propose new versions of the focused information criterion (FIC) for variable selection in logistic regression. The FIC gives, depending on the quantity to be estimated, possibly different sets of selected variables. The standard version of the FIC measures the mean squared error of the estimator of the quantity of interest in the selected model. In this article, we propose more general versions of the FIC, allowing other risk measures such as the one based on L(p) error. When prediction of an event is important, as is often the case in medical applications, we construct an FIC using the error rate as a natural risk measure. The advantages of using an information criterion which depends on both the quantity of interest and the selected risk measure are illustrated by means of a simulation study and application to a study on diabetic retinopathy.

Evaluation of the vocal performance of children using a voice range profile index

Voice range profiles (VRPs) were analyzed according to 11 frequency, intensity, and morphological characteristics for 94 normal children and 136 children with vocal fold pathologies (ages 6-11 years). Normative data are presented showing marked differences between the groups. Using a specific combination of the child's age, the highest vocal fundamental frequency, the lowest intensity, and the slope of the upper VRP contour, a Voice Range Profile Index for Children (VRPIc) may be constructed using discriminant analysis. It is shown how the VRPIc can be used to screen children for vocal disorder or to quantitatively assess the effectiveness of voice treatment. Since the group means of the VRPIc for healthy and dysphonic children are scaled to +10 and -10, respectively, the VRPIc enables the clinician to rate a child's vocal performance with reference to healthy and dysphonic children in general. The sensitivity and specificity of this method was found to be 90% and 83%, respectively.

Physical and genetic map of the Clostridium acetobutylicum ATCC 824 chromosome

A physical and genetic map of the Clostridium acetobutylicum ATCC 824 chromosome was constructed. The macrorestriction map for CeuI, EagI, and SstII was created by ordering the 38 restriction sites by one- and two-dimensional pulsed-field gel electrophoresis (PFGE) and by using an original strategy based on the CeuI enzyme and indirect end labelling by hybridization on both sides of the CeuI sites with rrs (16S RNA) and 3' rrl (23S RNA) probes. The circular chromosome was estimated to be 4.15 Mb in size, and the average resolution of the physical map is 110 kb. The chromosome contains 11 rrn loci, which are localized on 44% of the chromosome in a divergent transcriptional orientation regarding the presumed location of the replication origin. In addition to these 11 rrn operons, a total of 40 identified genes were mapped by hybridization experiments with genes from C. acetobutylicum and from various other clostridia as probes. The genetic map of C. acetobutylicum was compared to that of the three other endospore-forming bacteria characterized so far: Bacillus subtilis, Clostridium beijerinckii, and Clostridium perfringens. Parodoxically, the chromosomal backbone of C. acetobutylicum showed more similarity to that of B. subtilis than to those of the clostridia.

Test-retest study of the GRBAS scale: influence of experience and professional background on perceptual rating of voice quality

Perceptual evaluation was performed by means of the GRBAS scale for a series of nine pathological voice samples that were presented twice to a group of 23 judges, consisting of experienced and inexperienced otolaryngologists (ENTs) and speech-language pathologists (S/LPs). The time interval between ratings was 14 days. Test-retest reliability was moderate. The best agreement between the observers was obtained for the G (grade) parameter and the worst for the S (strained) parameter. Considering the medians of the GRBAS ratings, no significant influence was measured for level of experience or professional background. Yet, based on means, the results show that professional background has a greater impact on perceptual rating than experience.

Cloning and sequencing of a gene coding for a novel dextransucrase from Leuconostoc mesenteroides NRRL B-1299 synthesizing only alpha (1-6) and alpha (1-3) linkages

The coding region for a Leuconostoc mesenteroides NRRL B-1299 dextransucrase gene (dsrA) was isolated and sequenced. Using a pair of primers designed on the basis of two highly conserved amino-acid (aa) sequences in L. mesenteroides NRRL B-512F dextransucrase and streptococcal glucosyltransferases (GTFs), a fragment of dsrA was amplified by the polymerase chain reaction (PCR). This PCR product was used as an hybridization probe to isolate a 1.8-kb fragment identified as the central region of dsrA. Cleavage by Sac I of this fragment allowed two probes to be obtained to isolate the 5' and the 3' ends of dsrA. The nucleotide sequence of the dsrA gene was determined and found to consist of an open reading frame (ORF) of 4870 base pairs (bp) coding for a 1290-aa protein with an M(r) of 145590. The aa sequence exhibited a high similarity with other GTFs. The two domains previously described in GTFs are conserved in DSRA: an N-terminal conserved domain and a C-terminal domain composed of a series of repeats. Surprisingly, the expected signal peptide was not detected. The entire gene was reconstructed and the activity of DSRA was investigated. The dextran produced appeared to be composed of 85% alpha (1-6) and 15% alpha (1-3) linkages and the oligosaccharides synthesized in the presence of maltose were mainly composed of alpha (1-6) linkages. This enzyme is a novel dextransucrase from L. mesenteroides NRRL B-1299 producing no alpha (1-2) linkages and is the first glucosyltransferase having no signal peptide described.