Alfio Marazzi

Followers

Following

Public Views

Interests

Uploads

Papers by Alfio Marazzi

Variation des durées et ou des coûts réels d'hospitalisation au sein des DRG individuels : revue de la littérature sur l'existence du phénomène et ses causes possibles

Using past experience to optimize audit sampling design

Review of Quantitative Finance and Accounting, 2016

Optimal sampling designs for audit, minimizing the mean squared error of the estimated amount of ... more Optimal sampling designs for audit, minimizing the mean squared error of the estimated amount of the misstatement, are proposed. They are derived from a general statistical model that describes the error process with the help of available auxiliary information. We show that, if the model is adequate, these optimal designs based on balanced sampling with unequal probabilities are more efficient than monetary unit sampling. We discuss how to implement the optimal designs in practice. Monte Carlo simulations based on audit data from the Swiss hospital billing system confirms the benefits of the proposed method.

Le D partement de Statistique de I'Institut Universitaire de M6decine Sociale et Preventive, Lausanne

Soz Praventivmed, 1982

Robust Bayesian estimation for the linear model

Een meta-analyse van acupunctuur tegen chronische pijn

S-plus functions for robust estimators of the parameters of the Gaussian and the Lognormal distributions

We describe a set of S-plus functions for several types of M-estimators for the parameters of the... more We describe a set of S-plus functions for several types of M-estimators for the parameters of the Gaussian and the Lognormal distributions. Beside the usual types of estimators based on Huber's Proposal 2 and the median absolute deviation estimators for the scale parameter, this set of S-plus functions includes the bias robust estimator for partitioned parameters described in Hampel et al. (1986), and the high breakdown point and high efficiency estimator with test for bias proposed by Yohai, Stahel, and Zamar (1991).

ROBETH: A subroutine library for robust statistical procedures

[Drug addiction in the Canton of Vaud: a look at data from the canton police]

Sozial- und Präventivmedizin, 1985

Truncated maximum likelihood regression with censored responses

On the Numerical Solutions of Bounded Influence Regression Problems

COMPSTAT, 1986

Several iterative procedures to solve numerically the problem of robust multiple regression have ... more Several iterative procedures to solve numerically the problem of robust multiple regression have been proposed in Huber (1972), Huber and Dutter (1974) and Dutter (1977a). According to Dutter (1977b), the H-algorithm distinguished itself for its programming simplicity and rapid computation. The H-algorithm was adapted to the problem of bounded influence regression by Marazzi (1980) and introduced in ROBETH. A similar adaptation was also described by Samarov and Welsch (1982) and introduced in TROLL. Experience shows that when high influential leverage points are present the convergence of the H-algorithm is very poor and the reliability of the result is doubtful. In this paper, alternative procedures with better convergence are discussed. These procedures have been implemented in ROBSYS, a conversational package for robust statistical computing (see Marazzi and Randriamiharisoa (1985)).

Title : Generalized Linear Models

Download

Le Département de Statistique de l'Institut Universitaire de Médecine Sociale et Préventive, Lausanne

Sozial- und Präventivmedizin SPM, 1982

Download

Surveillance médicale de personnes exposées au perchloréthylène. Etude dans des pressings

Sozial- und Präventivmedizin SPM, 1983

ZusammenfassungEine Gruppe von 36 Frauen im Kontakt mit Tetrachloroethylen wird mit einem Kontrol... more ZusammenfassungEine Gruppe von 36 Frauen im Kontakt mit Tetrachloroethylen wird mit einem Kontrollkollectiv (36 Verkäuferinnen) verglichen. Der Gesundheitszustand ist allgemein nicht wesentlich verschieden zwischen den beiden Gruppen.SummaryThirty-six women working in pressings and exposed to tetrachloroethylene are compared to a same size group of saleswomen. No serious ill effect could be shown in the exposed population.

Robust regression in biological assay: application to the evaluation of alternative experimental techniques

Experientia, 1988

2 Chappuis, G., and Tixier, G., Etude de la corr61ation existant entre le test NIH et les anticor... more

S-Plus functions for M-estimators of the parameters of the Gamma distribution

Marazzi and Ruffieux (1996) describe an implementation of M-estimators for the Gamma distribution... more Marazzi and Ruffieux (1996) describe an implementation of M-estimators for the Gamma distribution. This report is an appendix describing the corresponding S-plus functions. S-Plus functions This appendix of Marazzi and Ruffieux (1996) describes a set of S-plus functions that compute M-estimates of the parameters of a Gamma distribution. The shrinking com-ponent estimates of the standardized parameters are used aand the estimate α an σ of the shape parameter α and the scale parameter σ are returned. The functions and their purpose are: M.E.gamma M-estimate α an σ. M.L.gamma Maximum likelihood estimate α an σ. AV.ME.gamma Asymptotic covariance matrix of the M-estimates. AV.ML.gamma Asymptotic covariance matrix of the maximum likelihood estimates. Tab.gamma Computation and storage of the matrix A b and the vector c b for several values of α. Crv.gamma Visual check. This function draws the graph of the function S p2 (¯ σ(α), α) that should cross the horizontal axis for α α. A neat inter...

Évaluation De La Satisfaction Des Infirmiers(-Ères) : Développement et Validation D’Un Nouvel Outil D’Analyse

Recherche en soins infirmiers

A new device for the analyses of nurses' satisfaction has been developed and validated on two... more A new device for the analyses of nurses' satisfaction has been developed and validated on two types of general and intensive treatments at the University Hospital in Vaudois, Switzerland. A questionnaire has been elaborated for identifying the variables linked with characteristics of the nurse's work, as well as personal variables of the employer which could have an influence on the level of satisfaction. In identifying the sources of satisfaction and dissatisfaction, it has been possible to propose recommendations and corrective measures in order to improve the level of global satisfaction of the nursing team

Minimax Credibi!ity

Robust Box-Cox Transformations for Simple Regression

Theory and Applications of Recent Robust Methods, 2004

... Robust Box-Cox Transformation 177 Remark 4.2. ... was not relevant, because of the equivarian... more ... Robust Box-Cox Transformation 177 Remark 4.2. ... was not relevant, because of the equivariance of A (An (j/f,..., j/)= Ara (j/i,..., yn)/a). Various parameter sets provided ... 1000 x (mean (AnAo) 2) 0&amp;#x27;5) and the median absolute de-viation with respect to Ao (mde= 1000xmedian (An ...

Robust methods for asymmetric responses and applications to the analysis of hospital costs

Bootstrap tests for robust means of asymmetric distributions with unequal shapes

Computational Statistics & Data Analysis, 2002

Bootstrap procedures for testing equality of robust means in the one-, two-, and multi-sample pro... more Bootstrap procedures for testing equality of robust means in the one-, two-, and multi-sample problems for asymmetrically distributed data with unequal shapes are described. The emphasis is on parametric procedures, but some results are provided for nonparametric procedures as well. In the parametric framework, it is assumed that a model with two parameters, shape and scale, can be used to approximatively describe the populations. Examples are contaminated Lognormal, Weibull, Gamma, and Pareto distributions. Robust estimators of the parameters are supposed to be available; the robust mean is then deÿned as the asymptotic value of the robust estimate of the model mean. In the nonparametric framework, the robust mean is the asymptotic value of some estimate that does not depend on a parametric model, e.g., a trimmed mean. A studentized test statistic is explored with the help of examples on simulated and real data. In order to estimate the null model, criteria for robust constrained model ÿtting, the constraint being the null hypothesis, are introduced and discussed. In the nonparametric case, a robust version of exponential tilting is provided. Parametric, semiparametric, and nonparametric bootstrap schemes for the computation of ÿnite sample distributions are considered. The examples illustrate procedures that can be useful in practice.

Download

Alfio Marazzi

Uploads

Papers by Alfio Marazzi

Log In