University of Portsmouth

About: University of Portsmouth is a education organization based out in Portsmouth, Portsmouth, United Kingdom. It is known for research contribution in the topics: Population & Galaxy. The organization has 5452 authors who have published 14256 publications receiving 424346 citations. The organization is also known as: Portsmouth and Gosport School of Science and Art & Portsmouth and Gosport School of Science and the Arts.

Neural Network Studies. 2. Variable Selection

Abstract: Quantitative structure−activity relationship (QSAR) studies usually require an estimation of the relevance of a very large set of initial variables. Determination of the most important variables allows theoretically a better generalization by all pattern recognition methods. This study introduces and investigates five pruning algorithms designed to estimate the importance of input variables in feed-forward artificial neural network trained by back propagation algorithm (ANN) applications and to prune nonrelevant ones in a statistically reliable way. The analyzed algorithms performed similar variable estimations for simulated data sets, but differences were detected for real QSAR examples. Improvement of ANN prediction ability was shown after the pruning of redundant input variables. The statistical coefficients computed by ANNs for QSAR examples were better than those of multiple linear regression. Restrictions of the proposed algorithms and the potential use of ANNs are discussed.

Critique and review of leader–member exchange theory: Issues of agreement, consensus, and excellence

Abstract: The relationship quality that develops between leaders and those designated as followers is of longstanding interest to researchers and practitioners. The purpose of the present article is to review the more recent developments in the field of leader-member exchange (LMX) theory to identify specific issues related to leader-member agreement and follower consensus that have potentially important theoretical and practical implications. We introduce the concept of LMX excellence, which involves high-quality LMX, high leader-member agreement as well as high group consensus in LMX quality. We outline how leaders and followers' behaviour as well as context can enhance or hinder the development of LMX excellence and conclude with an overview of the practical and theoretical implications as well as future research needs.

The clustering of galaxies in the SDSS-III DR9 Baryon Oscillation Spectroscopic Survey: constraints on primordial non-Gaussianity

Abstract: We analyse the density field of 264 283 galaxies observed by the Sloan Digital Sky Surve (SDSS)-III Baryon Oscillation Spectroscopic Survey (BOSS) and included in the SDSS Data Release 9 (DR9). In total, the SDSS DR9 BOSS data include spectroscopic redshifts for over 400 000 galaxies spread over a footprint of more than 3000 deg^2. We measure the power spectrum of these galaxies with redshifts 0.43 0), is 99.5 per cent. After quantifying and correcting for the systematic bias and including the added uncertainty, we find −45 0) = 91.0 per cent. A more conservative approach assumes that we have only learnt the k dependence of the systematic bias and allows any amplitude for the systematic correction; we find that the systematic effect is not fully degenerate with that of f^(local)_(NL) , and we determine that −82 0) = 68 per cent. This analysis demonstrates the importance of accounting for the impact of Galactic foregrounds on f^(local)_(NL) measurements. We outline the methods that account for these systematic biases and uncertainties. We expect our methods to yield robust constraints on f^(local)_(NL) for both our own and future large-scale structure investigations.

Risk-adjusted prediction of operative mortality in oesophagogastric surgery with O-POSSUM.

Abstract: Introduction: The present study was designed to develop a dedicated oesophagogastric model for the prediction of risk-adjusted postoperative mortality in upper gastrointestinal surgery (O-POSSUM). Methods: Using 1042 patients undergoing oesophageal (n = 538) or gastric (n = 504) surgery between 1994 and 2000 the Portsmouth predictor equation for mortality (P-POSSUM) scoring system was compared with a standard logistic regression O-POSSUM model and a multilevel O-POSSUM model using the following independent factors: age, physiological status, mode of surgery, type of surgery and histological stage. Results: The overall mortality rate was 12·0 per cent (elective mortality rate 9·4 per cent and emergency mortality rate 26·9 per cent). P-POSSUM overpredicted mortality (14·5 per cent), particularly in the elective group of patients. The multilevel model offered higher discrimination than the single-level O-POSSUM and P-POSSUM models (area under receiver–operator characteristic curve 79·7 versus 74·6 and 74·3 per cent). When observed to expected outcomes were evaluated, the multilevel O-POSSUM model was found to offer better calibration (Hosmer–Lemeshow χ2 statistic 10·15 versus 10·52 and 28·80). Conclusion: The multilevel O-POSSUM model provided an accurate risk-adjusted prediction of death from oesophageal and gastric surgery for individual patients. In conjunction with a multidisciplinary approach to patient management, the model may be used in everyday practice for perioperative counselling of patients and their carers. Copyright © 2004 British Journal of Surgery Society Ltd. Published by John Wiley & Sons, Ltd.