Asian Science Citation Index is committed to provide an authoritative, trusted and significant information by the coverage of the most important and influential journals to meet the needs of the global scientific community.  
ASCI Database
308-Lasani Town,
Sargodha Road,
Faisalabad, Pakistan
Fax: +92-41-8815544
Contact Via Web
Suggest a Journal
 
Articles by P Hall
Total Records ( 5 ) for P Hall
  P Hall and J. H. Xue
 

In standard parametric classifiers, or classifiers based on nonparametric methods but where there is an opportunity for estimating population densities, the prior probabilities of the respective populations play a key role. However, those probabilities are largely ignored in the construction of high-dimensional classifiers, partly because there are no likelihoods to be constructed or Bayes risks to be estimated. Nevertheless, including information about prior probabilities can reduce the overall error rate, particularly in cases where doing so is most important, i.e. when the classification problem is particularly challenging and error rates are not close to zero. In this paper we suggest a general approach to reducing error rate in this way, by using a method derived from Breiman’s bagging idea. The potential improvements in performance are identified in theoretical and numerical work, the latter involving both applications to real data and simulations. The method is simple and explicit to apply, and does not involve choice of any tuning parameters.

  F Ferraty , P Hall and P. Vieu
 

We suggest a way of reducing the very high dimension of a functional predictor, X, to a low number of dimensions chosen so as to give the best predictive performance. Specifically, if X is observed on a fine grid of design points t1,..., tr, we propose a method for choosing a small subset of these, say ti1,..., tik, to optimize the prediction of a response variable, Y. The values tij are referred to as the most predictive design points, or covariates, for a given value of k, and are computed using information contained in a set of independent observations (Xi, Yi) of (X, Y). The algorithm is based on local linear regression, and calculations can be accelerated using linear regression to preselect the design points. Boosting can be employed to further improve the predictive performance. We illustrate the usefulness of our ideas through simulations and examples drawn from chemometrics, and we develop theoretical arguments showing that the methodology can be applied successfully in a range of settings.

  P Hall and H. Miller
 

The bootstrap provides effective and accurate methodology for a wide variety of statistical problems which might not otherwise enjoy practicable solutions. However, there still exist important problems where standard bootstrap estimators are not consistent, and where alternative approaches, for example the m-out-of-n bootstrap and asymptotic methods, also face significant challenges. One of these is the problem of constructing confidence intervals or hypothesis tests for extrema of parameters, for example for the maximum of p parameters where each has to be estimated from data. In the present paper we suggest approaches to solving this problem. We use the bootstrap to construct an accurate estimator of the joint distribution of centred parameter estimators, and we base the procedure, either a confidence interval or a hypothesis test, on that distribution estimator. Our methodology is designed so that it errs on the side of conservatism, modulo the small inaccuracy of the bootstrap step.

  M. P Kuligowski , R. Y. Q Kwan , C Lo , C Wong , W. G James , D Bourges , J. D Ooi , L. D Abeynaike , P Hall , A. R Kitching and M. J. Hickey
 

Patients with antineutrophil cytoplasmic antibodies (ANCAs) frequently develop severe vasculitis and glomerulonephritis. Although ANCAs, particularly antimyeloperoxidase (anti-MPO), have been shown to promote leukocyte adhesion in postcapillary venules, their ability to promote adhesion in the glomerular vasculature is less clear. We used intravital microscopy to examine glomerular leukocyte adhesion induced by anti-MPO. In mice pretreated with LPS, 50 µg anti-MPO induced LFA-1–dependent adhesion in glomeruli. In concert with this finding, in mice pretreated with LPS, more than 80% of circulating neutrophils bound anti-MPO within 5 minutes of intravenous administration. However, even in the absence of LPS, more than 40% of circulating neutrophils bound anti-MPO in vivo, a response not seen in MPO–/– mice. In addition, a higher dose of anti-MPO (200 µg) induced robust glomerular leukocyte adhesion in the absence of LPS. The latter response was β2-integrin independent, instead requiring the 4-integrin, which was up-regulated on neutrophils in response to anti-MPO. These data indicate that anti-MPO antibodies bind to circulating neutrophils, and can induce glomerular leukocyte adhesion via multiple pathways. Lower doses induce adhesion only after an infection-related stimulus, whereas higher doses are capable of inducing responses in the absence of an additional inflammatory stimulus, via alternative adhesion mechanisms.

  R. L Milne , J Benitez , H Nevanlinna , T Heikkinen , K Aittomaki , C Blomqvist , J. I Arias , M. P Zamora , B Burwinkel , C. R Bartram , A Meindl , R. K Schmutzler , A Cox , I Brock , G Elliott , M. W. R Reed , M. C Southey , L Smith , A. B Spurdle , J. L Hopper , F. J Couch , J. E Olson , X Wang , Z Fredericksen , P Schurmann , M Bremer , P Hillemanns , T Dork , P Devilee , C. J van Asperen , R. A. E. M Tollenaar , C Seynaeve , P Hall , K Czene , J Liu , Y Li , S Ahmed , A. M Dunning , M Maranian , P. D. P Pharoah , G Chenevix Trench , J Beesley , kConFab Investigators , N. N Antonenkova , I. V Zalutsky , H Anton Culver , A Ziogas , H Brauch , C Justenhoven , Y. D Ko , S Haas , P. A Fasching , R Strick , A. B Ekici , M. W Beckmann , G. G Giles , G Severi , L Baglietto , D. R English , O Fletcher , N Johnson , I dos Santos Silva , J Peto , C Turnbull , S Hines , A Renwick , N Rahman , B. G Nordestgaard , S. E Bojesen , H Flyger , D Kang , K. Y Yoo , D. Y Noh , A Mannermaa , V Kataja , V. M Kosma , M Garcia Closas , S Chanock , J Lissowska , L. A Brinton , J Chang Claude , S Wang Gohrke , C. Y Shen , H. C Wang , J. C Yu , S. T Chen , M Bermisheva , T Nikolaeva , E Khusnutdinova , M. K Humphreys , J Morrison , R Platte , D. F Easton and on behalf of the Breast Cancer Association Consortium
  Background

A recent genome-wide association study identified single-nucleotide polymorphism (SNP) 2q35-rs13387042 as a marker of susceptibility to estrogen receptor (ER)–positive breast cancer. We attempted to confirm this association using the Breast Cancer Association Consortium.

Methods

2q35-rs13387042 SNP was genotyped for 31 510 women with invasive breast cancer, 1101 women with ductal carcinoma in situ, and 35 969 female control subjects from 25 studies. Odds ratios (ORs) were estimated by logistic regression, adjusted for study. Heterogeneity in odds ratios by each of age, ethnicity, and study was assessed by fitting interaction terms. Heterogeneity by each of invasiveness, family history, bilaterality, and hormone receptor status was assessed by subclassifying case patients and applying polytomous logistic regression. All statistical tests were two-sided.

Results

We found strong evidence of association between rs13387042 and breast cancer in white women of European origin (per-allele OR = 1.12, 95% confidence interval [CI] = 1.09 to 1.15; Ptrend = 1.0 x 10–19). The odds ratio was lower than that previously reported (P = .02) and did not vary by age or ethnicity (all P ≥ .2). However, it was higher when the analysis was restricted to case patients who were selected for a strong family history (P = .02). An association was observed for both ER-positive (OR = 1.14, 95% CI = 1.10 to 1.17; P = 10–15) and ER-negative disease (OR = 1.10, 95% CI = 1.04 to 1.15; P = .0003) and both progesterone receptor (PR)–positive (OR = 1.15, 95% CI = 1.11 to 1.19; P = 5 x 10–14) and PR-negative disease (OR = 1.10, 95% CI = 1.06 to 1.15; P = .00002).

Conclusion

The rs13387042 is associated with both ER-positive and ER-negative breast cancer in European women.

 
 
 
Copyright   |   Desclaimer   |    Privacy Policy   |   Browsers   |   Accessibility