Aurélie Albert

Multiple-group Logistic Regression Diagnostics

SUMMARY The regression diagnostics introduced by Pregibon for the dichotomous logistic model are extended to multiple groups viewed as a multivariate generalized linear model. We develop diagnostics which measure the influence of each observation on the performance of the estimated classification rule, thus highlighting possible multivariate outlying and/or influential observations. As an illustration, the diagnostics are applied to enzyme data from liver disease patients. It is shown that multivariate regression diagnostics constitute an indispensable tool for the practitioner to construct appropriate polychotomous logistic models.

The history of Belgian assisted reproduction technology cycle registration and control: a case study in reducing the incidence of multiple pregnancy

STUDY QUESTION What is the effect of a legal limitation of the number of embryos that can be transferred in an assisted reproductive technology (ART) cycle on the multiple delivery rate? SUMMARY ANSWER The Belgian national register shows that the introduction of reimbursement of ART laboratory costs in July 2003, and the imposition of a legal limitation of the number of embryos transferred in the same year, were associated with a >50% reduction of the multiple pregnancy rate from 27 to 11% between 2003 and the last assessment in 2010, without any reduction of the pregnancy rate per cycle. WHAT IS KNOWN ALREADY Individual Belgian IVF centres have published their results since the implementation of the law, and these show a decrease in the multiple pregnancy rate on a centre by centre basis. However, the overall national picture remains unpublished. STUDY DESIGN, SIZE, DURATION Cohort study from 1990 to 2010 of all ART cycles in Belgium (2685 cycles in 1990 evolving to 19 110 cycles in 2010), with a retrospective analysis from 1990 to 2000 and prospective online data collection since 2001. PARTICIPANTS/MATERIALS, SETTING, METHODS Registration evolved from paper written reports per centre to a compulsory online registration of all ART cycles. From 2001 up to mid-2009, data were collected from Excel spread sheets or MS Access files into an MS Access database. Since mid-2009, data collection is done via a remote and secured web-based system (www.belrap.be) where centres can upload their data and get immediate feedback about missing data, errors and inconsistencies. MAIN RESULTS AND THE ROLE OF CHANCE National Belgian registration data show that reimbursement of IVF laboratory costs in July 2003, coupled to a legal limitation in the number of embryos transferred in utero, were associated with a 50% reduction of the multiple pregnancy rate from 27 to 11% without reduction of the pregnancy rate per cycle, and with an increase in the number of fresh and frozen ART cycles due to improved access to treatment. LIMITATIONS, REASONS FOR CAUTION There is potential underreporting of complications of ART treatment, pregnancy outcome and neonatal health. WIDER IMPLICATIONS OF THE FINDINGS Over the 20 years of registration, the pregnancy rate has remained constant, despite the reduction in the number of embryos transferred, optimization of laboratory procedures and stimulation protocols, introduction of quality systems and implementation of the EU Tissue Directive over the period 2004-2010. STUDY FUNDING/COMPETING INTEREST(S) No external funding was sought for this study. None of the authors has any conflict of interest to declare.

Multiple group logistic discrimination

Among the many possible approaches suggested for statistical discrimination, the logistic method can be classified midway between fully distributional solutions, of which the assumption of multivariate normality is a classical example[16l, and the distribution-free techniques, using, for instance, kernel or nearest-neighbor methods[l,32]. Therefore it is often called a partially parametric or partially distributional method[l l]. This central position of the logistic model makes it one of the most attractive and widely used tools for solving regression and discrimination problems. Indeed, since there are fewer distributional assumptions than for fully parametric models, the logistic method is applicable to a larger family of multivariate distributions involving both discrete and continuous variables. Moreover, in spite of its wide applicability and generality, the method remains feasible and easy to use, in contrast with nonparametric methods. This paper is intended to review the basic ideas and principles of logistic discrimination[415,22-25] and also to bring additional results to some of the queries raised by Professor Anderson before his death. We restrict our attention to discrimination between qualitatively distinct groups and do not envisage the case where groups are quantitatively distinct or ordered[3,12,14]. We dedicate this paper to our friend and mentor, the late Professor J. A. Anderson, for his fundamental contribution to discriminant analysis and for his continuous support of our research efforts.

Influence of Food Resources on the Ranging Pattern of Northern Pig-tailed Macaques (Macaca leonina)

Food availability may influence primates’ home range size and use. Understanding this relationship may facilitate the design of conservation strategies. We aimed to determine how fruit availability influences the ranging patterns of a group of northern pig-tailed macaques (Macaca leonina) living around the visitor center of Khao Yai National Park, Thailand. We predicted that macaques would increase their range during low fruit abundance periods to gather high-quality food and that they would go where there are more fruits or more fruits of particular species. We also predicted that human food, linked to human presence, would attract the macaques. We followed the macaques and recorded their diet and movements within their home range. We superimposed a grid on kernels defining the monthly home range surface to compare spatially macaques’ travel and the availability of fruits measured on botanical transects. Our results showed that the macaques increased their monthly home range in March, probably to obtain newly available fruits. During high fruit abundance seasons, they spent more time near particular fruit species. In August and September, although fruits became rare again, macaques kept their home range large, perhaps to find enough fruits as supplies dwindled. Finally, from October to February, they decreased their monthly home range size while consuming human food, a high-quality item. In conclusion, the macaques used several ranging strategies according to fruit availability. However, we think that, without human food, macaques would tend to increase their range during low fruit abundance periods, as predicted.

Finding good acoustic features for parrot vocalizations: The feature generation approach

A crucial step in the understanding of vocal behavior of birds is to be able to classify calls in the repertoire into meaningful types. Methods developed to this aim are limited either because of human subjectivity or because of methodological issues. The present study investigated whether a feature generation system could categorize vocalizations of a bird species automatically and effectively. This procedure was applied to vocalizations of African gray parrots, known for their capacity to reproduce almost any sound of their environment. Outcomes of the feature generation approach agreed well with a much more labor-intensive process of a human expert classifying based on spectrographic representation, while clearly out-performing other automated methods. The method brings significant improvements in precision over commonly used bioacoustical analyses. As such, the method enlarges the scope of automated, acoustics-based sound classification.

Estimation of error rate in multiple group logistic discrimination. The approximate leaving-one-out method

We present an approximate leaving-one-out technique for estimating the error rate in logistic discrimination. The new measure is based on the one-step approximation of a(i), the maximum likelihood estimate of the parameter vector based on the sample without the ith case. Some inequalities between the resubstitution error rate, the approximate and exact leaving-one-out error rates for the multiple group logistic model are investigated. Monte-Carlo simulations assess the adequacy of the approximate leaving-one-out method as an estimate of the actual error rate. The usefulness of this approach is demonstrated by means of two medical examples.

Testing the proportional odds assumption in multiply imputed ordinal longitudinal data

A popular choice when analyzing ordinal data is to consider the cumulative proportional odds model to relate the marginal probabilities of the ordinal outcome to a set of covariates. However, application of this model relies on the condition of identical cumulative odds ratios across the cut-offs of the ordinal outcome; the well-known proportional odds assumption. This paper focuses on the assessment of this assumption while accounting for repeated and missing data. In this respect, we develop a statistical method built on multiple imputation (MI) based on generalized estimating equations that allows to test the proportionality assumption under the missing at random setting. The performance of the proposed method is evaluated for two MI algorithms for incomplete longitudinal ordinal data. The impact of both MI methods is compared with respect to the type I error rate and the power for situations covering various numbers of categories of the ordinal outcome, sample sizes, rates of missingness, well-balanced and skewed data. The comparison of both MI methods with the complete-case analysis is also provided. We illustrate the use of the proposed methods on a quality of life data from a cancer clinical trial.