170,297 research outputs found
Rate of convergence in the strong law of large numbers for a class of U-statistics and von Mises statistics
No full textFor the class of U-statistics based on multidimensionally indexed random variables introduced in Christofides (1987), an improved rate of convergence in the strong law of large numbers is obtained using martingale inequalities and other results. In addition, the same rate of convergence is obtained for the class of associated von Mises statistics.U-statistics V-statistics Multidimensionally indexed martingales Strong law of large numbers
Rate of convergence in the strong law of large numbers for U-statistics based on a multidimensionally indexed array of random variables
No full textU-statistics based on a multidimensionally indexed array of random variables were introduced in Christofides (1987). In this paper, the rate of convergence in the strong law of large numbers for this class of U-statistics is obtained using martingale inequalities.U-statistics multidimensionally indexed martingales
Estimation of Complex Population Parameters Under the Randomized Response Theory
No full textWhen a sensitive quantitative variable is under study and the Randomized Response Theory is adopted, a great deal of literature has been devoted to the estimation of the population mean (or total) or - at most - simple functions of population totals. However, in many real surveys the main interest might rely on the estimation of a complex parameter, usually a nonlinear combination of population totals. Hence, in order to face with this problem, we suppose to collect data by means of the well-known unrelated question method proposed by Greenberg et al. (1971), and under the design-based framework, we propose to handle such a complex parameter as a population functional by suitably extending the linearization approach proposed by Deville (1999). The considered strategy permits to obtain parameter estimation by means of the substitution method based on the empirical functional, and to achieve the corresponding variance estimator. Some selected illustrative examples are provided mostly concerning the estimation of two inequality indices, namely the Gini concentration index and the Atkinson index, widely discussed in the social and economic literature
Graph Guessing Games and Non-Shannon Information Inequalities
No full textGuessing games for directed graphs were introduced by Riis [12] for studying multiple unicast network coding problems. In a guessing game, the players toss generalised dice and can see some of the other outcomes depending on the structure of an underlying digraph. They later guess simultaneously the outcome of their own die. Their objective is to find a strategy which maximises the probability that they all guess correctly. The performance of the optimal strategy for a graph is measured by the guessing number of the digraph.
In [3], Christofides and Markstrom studied guessing numbers of undirected graphs and defined a strategy which they conjectured to be optimal. One of the main results of this paper is a disproof of this conjecture.
The main tool so far for computing guessing numbers of graphs is information theoretic inequalities. The other main result of the paper is that Shannon's information inequalities, which work particularly well for a wide range of graph classes, are not sufficient for computing the guessing number.
Finally we pose a few more interesting questions some of which we can answer and some which we leave as open problems
Self/Paid-Employment, Public/Private Sector Selection, and Wage Differentials
No full textWe use Probit models to account for the double selection problem of choice between, on the one hand, self and paid employment and, on the other, employment in the public and private sector. These models provide corrections for sample selection in wage equations for paid employees in the public and private sectors. Using amodified version of the Oaxaca and Ransom (1994) procedure, we decompose the wage gap between the public and private sectors into a portion attributable to differences in characteristics, the public sector advantage, the private sector disadvantage and unobserved selection effects. Rich data for the Republic of Cyprus, a thriving economy with institutional features reminiscent of a developing economy, help determine the choice of type (self/paid) and sector (public/private) of employment. The human capital model describes the wage determination process satisfactorily. The size and distribution of public sector rents between men and women are similar to those in North America and are bracketed by results for developing countries. JEL Classification: J31, J45, O52 Keywords: Public/private sector, self/paid employment, selection, wage decomposition, country institutions ∗ We are indebted to the Social Sciences and Humanities Research Council of Canada, the University of Cyprus, and the University of Guelph (where Christofides is an Adjunct Professor) for financial support, to two anonymous referees, Co-editor P. Kuhn, P. Lyssiotou and S. Matsis for helpful comments, and to E. Ioannidou, P. Nearchou, and C. Pittalis for outstanding research assistance. Louis Christofides isamemberofCESifoandCLLRNet. 1
Exponential inequalities for N-demimartingales and negatively associated random variables
No full textInternational audienceThe class of N-demimartingales generalizes in a natural way the concept of negative association and includes as special cases martingales with respect to the natural choice of -algebras. For this class of random variables, a number of maximal and other inequalities were obtained by [Christofides, T.C., 2003. Maximal inequalities for N-demimartingales. Archives of Inequalities and Applications 50, 397–408] and [Prakasa Rao, B.L.S., 2004. On some inequalities for N-demimartingales. J. Indian Soc. Agricultural Statist. 57, 208–216, Prakasa Rao, B.L.S., 2007. On some maximal inequalities for demisubmartingales and N-demisupermartingales. J. Inequal. Pure Appl. Math. 8, 17]. In this paper we prove Azuma's inequality for N-demimartingales and as a corollary we obtain an exponential inequality for negatively associated random variables
Going Beyond Counting First Authors in Author Co-citation Analysis
No full textThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Improving diabetes conventional therapy via machine learning modeling
No full textGlucose is a major source of energy for the human body and it is essential that blood glucose levels are maintained within a safe range. Type 1 Diabetes (T1D) is a metabolic disorder characterized by the deficiency of insulin, a hormone which is secreted by the pancreas and is responsible for blood glucose regulation. Thus, T1D patients need exogenous insulin injections to keep the blood glucose level within a safe range. However, the post-prandial (PP) glucose regulation remains a challenging issue for diabetes treatment. In order to improve PP glucose concentrations, a data-driven modeling approach to adjust the meal-related insulin dose is proposed. Specifically, an individualized regression model able to correct the meal bolus computed with the conventional therapy is developed in order to handle the inter-patient variability characterising T1D patients that may affect PP glucose regulation. Moreover, the proposed approach exploits specific models for different day periods on the basis of the intra-day variability of insulin sensitivity. The individualized therapy is validated both on nominal and perturbed scenarios by using the UVA/PADOVA simulator, which is accepted by the FDA as a substitute for pre-clinical animal trials, and the results of a case study are reported
Exponential inequalities for N-demimartingales and negatively associated random variables
No full textThe class of N-demimartingales generalizes in a natural way the concept of negative association and includes as special cases martingales with respect to the natural choice of [sigma]-algebras. For this class of random variables, a number of maximal and other inequalities were obtained by [Christofides, T.C., 2003. Maximal inequalities for N-demimartingales. Archives of Inequalities and Applications 50, 397-408] and [Prakasa Rao, B.L.S., 2004. On some inequalities for N-demimartingales. J. Indian Soc. Agricultural Statist. 57, 208-216; Prakasa Rao, B.L.S., 2007. On some maximal inequalities for demisubmartingales and N-demisupermartingales. J. Inequal. Pure Appl. Math. 8, 17]. In this paper we prove Azuma's inequality for N-demimartingales and as a corollary we obtain an exponential inequality for negatively associated random variables.
Mitomycin C in highly myopic eyes - Author reply
No full textOphthalmology. 2005 Feb;112(2):208-18; discussion 219.
Mitomycin C modulation of corneal wound healing after photorefractive keratectomy in highly myopic eyes.
Gambato C, Ghirlando A, Moretto E, Busato F, Midena E.
SourceRefractive Surgery Service and Antimetabolite Therapy Research Unit, Department of Ophthalmology, University of Padova, Padova, Italy.
Abstract
PURPOSE: To evaluate the role of topical mitomycin C in corneal wound healing (CWH) after photorefractive keratectomy (PRK) in highly myopic eyes.
DESIGN: Prospective, double-masked, randomized clinical trial.
PARTICIPANTS: Seventy-two eyes of 36 patients affected by high (>7 diopters) myopia.
METHODS: In each patient, one eye was randomly assigned to PRK with intraoperative topical 0.02% mitomycin C application, and the fellow eye was treated with a placebo. Postoperatively, mitomycin C-treated eyes received artificial tears (3 times daily, tapered in 3 months), whereas the fellow eye was treated with fluorometholone sodium 2% and artificial tears (3 times daily, tapered in 3 months).
MAIN OUTCOME MEASURES: Uncorrected visual acuity (UCVA) and best-corrected visual acuity (BCVA), contrast sensitivity, manifest refraction, and biomicroscopy. Contrast sensitivity was determined using the Pelli-Robson chart. Corneal confocal microscopy documented CWH.
RESULTS: Mean follow-up was 18 months (range, 12-36). No side effects or toxic effects were documented. At 12-month follow-up examination, UCVAs (logarithm of the minimum angle of resolution) were 0.4+/-0.48 and 0.5+/-0.53 (P = .03) in mitomycin C-treated eyes and corticosteroid-treated eyes, respectively. At 1 year, corneal haze developed in 20% of corticosteroid-treated eyes, versus 0% of mitomycin C-treated eyes. At 12, 24, and 36 months, corneal confocal microscopy showed activated keratocytes and extracellular matrix significantly more evident in untreated eyes (Ps = 0.004, 0.024, and 0.046, respectively).
CONCLUSION: Topical intraoperative application of 0.02% mitomycin C can reduce haze formation in highly myopic eyes undergoing PRK.
Comment in
Ophthalmology. 2006 Feb;113(2):357; author reply 357-8
- …
