Variable selection for financial distress classification using a genetic algorithm

This paper is concerned with the use of a genetic algorithm to select financial ratios for corporate distress classification models. For this purpose, the fitness value associated to a set of ratios is made to reflect the requirements of maximizing the amount of information available for the model and minimizing the collinearity between the model inputs. A case study involving 60 failed and continuing British firms in the period 1997-2000 is used for illustration. The classification model based on ratios selected by the genetic algorithm compares favorably with a model employing ratios usually found in the financial distress literature.

Biomarker discovery and redundancy reduction towards classification using a multi-factorial MALDI-TOF MS T2DM mouse model dataset

Diabetes like many diseases and biological processes is not mono-causal. On the one hand multifactorial studies with complex experimental design are required for its comprehensive analysis. On the other hand, the data from these studies often include a substantial amount of redundancy such as proteins that are typically represented by a multitude of peptides. Coping simultaneously with both complexities (experimental and technological) makes data analysis a challenge for Bioinformatics.

Maternal affective disorder and children’s representation of their families

Children’s perceptions of family relationship are related to their later emotional and social adjustment. This is of particular relevance in the context of family stressors such as maternal affective disorder. This study investigated the effects of maternal postnatal depression and anxiety on children’s family representations. In our sample of postnatally depressed mothers we also explored marital conflict as mediator between maternal psychopathology and children’s representations. Family drawings of 235 4–5 year-old children (93 control, 53 depressed and 89 anxious) were examined. When compared to controls, children of depressed, but not of anxious mothers, were more likely to draw themselves as less prominent than other family members and to represent a dysfunctional family, less likely to represent themselves with a happy face and showed a greater tendency of drawing bizarre pictures. Marital conflict mediated the association between maternal depression and dysfunctionality in drawings.

A typology of internet users based on comparative affective states: evidence from eight countries

Purpose - The role of affective states in consumer behaviour is well established. However, no study to date has empirically examined online affective states as a basis for constructing typologies of internet users and for assessing the invariance of clusters across national cultures. Design/methodology/approach - Four focus groups with internet users were carried out to adapt a set of affective states identified from the literature to the online environment. An online survey was then designed to collect data from internet users in four Western and four East Asian countries. Findings - Based on a cluster analysis, six cross-national market segments are identified and labelled "Positive Online Affectivists", "Offline Affectivists", "On/Off-line Negative Affectivists", "Online Affectivists", "Indistinguishable Affectivists", and "Negative Offline Affectivists". The resulting clusters discriminate on the basis of national culture, gender, working status and perceptions towards online brands. Practical implications - Marketers may use this typology to segment internet users in order to predict their perceptions towards online brands. Also, a standardised approach to e-marketing is not recommended on the basis of affective state-based segmentation. Originality/value - This is the first study proposing affective state-based typologies of internet users using comparable samples from four Western and four East Asian countries.

The role of negative maternal affective states and infant temperament in early interactions between infants with cleft lip and their mothers

OBJECTIVES: The study examined the early interaction between mothers and their infants with cleft lip, assessing the role of maternal affective state and expressiveness and differences in infant temperament. METHODS: Mother-infant interactions were assessed in 25 2-month-old infants with cleft lip and 25 age-matched healthy infants. Self-report and behavioral observations were used to assess maternal depressive symptoms and expressions. Mothers rated infant temperament. RESULTS: Infants with cleft lip were less engaged and their mothers showed more difficulty in interaction than control group dyads. Mothers of infants with cleft lip displayed more negative affectivity, but did not report more self-rated depressive symptoms than control group mothers. No group differences were found in infant temperament. CONCLUSIONS: In order to support the mother's experience and facilitate her ongoing parental role, findings highlight the importance of identifying maternal negative affectivity during early interactions, even when they seem have little awareness of their depressive symptoms.

A brief index of affective job satisfaction

This article responds to criticisms that affective job satisfaction research suffers serious measurement problems: Noncomparable measures; studies conceptualizing job satisfaction affectively but measuring it cognitively; and ad hoc measures lacking systematic development and validation, especially across populations by nationality, job level, and job type. We address these problems through a series of qualitative (total N = 28) and quantitative (total N = 901) studies to systematically develop and validate a short affective job satisfaction measure ultimately deriving from Brayfield and Rothe’s (1951) job satisfaction index. Unlike any previous job satisfaction measure, the resulting four-item Brief Index of Affective Job Satisfaction is overtly affective, minimally cognitive, and optimally brief. The new measure also differs from any previous job satisfaction measure in being comprehensively validated not just for internal consistency reliability, temporal stability, convergent and criterion-related validities, but also for cross-population invariance by nationality, job level, and job type.

Parkinson’s Disease tremor classification – a comparison between Support Vector Machines and neural networks

Deep Brain Stimulation has been used in the study of and for treating Parkinson’s Disease (PD) tremor symptoms since the 1980s. In the research reported here we have carried out a comparative analysis to classify tremor onset based on intraoperative microelectrode recordings of a PD patient’s brain Local Field Potential (LFP) signals. In particular, we compared the performance of a Support Vector Machine (SVM) with two well known artificial neural network classifiers, namely a Multiple Layer Perceptron (MLP) and a Radial Basis Function Network (RBN). The results show that in this study, using specifically PD data, the SVM provided an overall better classification rate achieving an accuracy of 81% recognition.