# Anne PhilippeUniversity of Nantes | UNIV Nantes · Jean Leray Mathematics Lab

Anne Philippe

phd

## About

154

Publications

32,911

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

2,031

Citations

Introduction

Présidente de la Société Française de Statistique SFdS

Additional affiliations

September 2005 - present

September 1997 - August 2005

## Publications

Publications (154)

We study the effect of observing a stationary process at irregular time points via a renewal process. We establish a sharp difference in the asymptotic behaviour of the self-normalized sample mean of the observed process depending on the renewal process. In particular, we show that if the renewal process has a moderate heavy tail distribution then...

Deep-sea pollen records from the Western European margin show that during the Last Glacial period (115-27 ka), regional vegetation oscillated between steppe and open forest in response to the millennial scale climate variability, Dansgaard-Oeschger (D-O) cycles and Heinrich events (HE), and that the magnitude of the forest expansions during D-O war...

From a continuous-time long memory stochastic process, a discrete-time randomly sampled one is drawn using a renewal sampling process. We establish the existence of the spectral density of the sampled process, and we give its expression in terms of that of the initial process. We also investigate different aspects of the statistical inference on th...

Today, UV filters are found as contaminants in a variety of biological fluids and environment, e.g. in vegetable crops and surface water. This is because UV filters are widely used in everyday products. In this context, we focused this study on cosmetic products, in order to assess the importance of this source of contamination. The study of 742 co...

Determining the impact of climatic variations on past human cultural changes is a difficult task due to the chronological uncertainties inherent to the dating methods applied to archaeological and paleoclimatic archives, and by the different temporal resolution of both archives.
Here, we present two high-resolution pollen-based palaeoenvironmental...

Deep-sea and terrestrial records allow to document the amplitude, timing and duration of the oceanic and vegetation responses to orbital and millennial-scale changes, in particular during North Atlantic cooling events (Heinrich events, HEs) in Western Europe during the Last Glacial Period (~115- 27 ka).
We propose a multiproxy study based on two de...

BayLum' is an R-package that facilitates the application of Bayesian models to the field of OSL dating. Here we present two recent feature updates to 'BayLum', significantly reducing computation time and improving general use. The first feature allows users to parallelize the computations involved in the MCMC sampling of values, while the second in...

A Third Neanderthal Individual from La Ferrassie • 99 ABSTRACT The Paleolithic site of La Ferrassie (SW France) has been extensively studied since its discovery during the 19th century. In addition to a large sequence including Middle and Upper Paleolithic layers, the site has yielded two very complete adult Neanderthal skeletons, five partial imma...

Today, UV filters are found as contaminants in a variety of biological fluids and environment, e.g. in vegetable crops and surface water. This is because UV filters are widely used in everyday products. In this context, we focused this study on cosmetic products. The study of 742 cosmetic products, excluding actual sunscreen products, but including...

Most archaeological and palaeo-environmental archives are preserved in specific environments (buried sediments, rock shelters, cave environments). Hence, the information we can obtain is usually incomplete, and lacking spatial and morphological significance. Studying landscape evolution can help us to understand the location and distribution of pas...

Evaluating synchronies between climate and cultural changes is a prerequisite for addressing the possible effect of environmental changes on human populations. Searching for synchronies during the Middle-Upper Paleolithic transition (ca. 48–36 ka) is hampered by the limits of radiocarbon dating techniques and the large chronological uncertainties a...

In nature, each mineral grain (quartz or feldspar) receives a dose rate (Dr) specific to its environment. The dose-rate distribution therefore reflects the micro-dosimetric context of grains of similar size. If all the grains were well bleached at deposition, this distribution is assumed to correspond, within uncertainties, with the distribution of...

Yumidong (Corn Cave) is a newly discovered Paleolithic site in the Three Gorges region of central China. Numerous Paleolithic artifacts have been excavated from the sedimentary deposits of the cave in association with faunal remains attributed to the Middle-Late Pleistocene Ailuropoda-Stegodon fauna of southern China. To establish the chronology of...

The coastal site of Beg-er-Vil (Brittany, France) has yielded remains of a dwelling site from the Mesolithic period, dating back to ca. 8000 years ago. These archaeological remains were covered by a marine sand dune. Among the research questions raised by recent excavations, the timing of the dune formation with respect to the human occupations is...

North African coastal Middle Stone Age (MSA) sites are key to study the development and expansion of early H. sapiens. El Mnasra cave on the Atlantic coast of Morocco (Témara region) is a crucial site associated with MSA archaeological materials considered advanced cognitive hallmarks of behavioural innovation, such as numerous Nassariidae perforat...

Carpooling is an integral component in smart carbon-neutral cities, in particular to facilitate home-work commuting. We study an innovative carpooling service which offers stochastic passenger-driver matching. Stochastic matching is when a passenger makes a carpooling request, and then waits for the first driver from a population of drivers who are...

A Bayesian analysis is proposed using an extension of g-priors for moderated mediation models. For this choice of priors, an explicit form of the marginal distribution is obtained. Testing procedure on the existence of direct, indirect and moderated effects are constructed using Bayes factor approach. This methodology is applied to analyze the asso...

In human sciences, mediation refers to a causal phenomenon in which the effect of an exposure variable X on an outcome Y can be decomposed into a direct effect and an indirect effect via a third variable M. In mediation models, the natural direct effect and the natural indirect effect are among the parameters of interest. For this model, we propose...

In nature, any mineral grain (quartz or feldspar) receives a dose-rate (Dr) specific to its environment. The dose-rate distributions, therefore, reflect the micro-dosimetric context of grains of similar size. If all the grains have been well bleached at deposition, this distribution corresponds, within uncertainties, to the distribution of equivale...

This paper proposes a Bayesian analysis using an extension of g-priors for moderated mediation models. For this choice of priors, an explicit form of the marginal distribution is obtained. Testing procedure on the existence of direct, indirect and moderated effects are constructed using Bayes factor approach. This methodology is applied to analyze...

The event model was proposed by Lanos and Philippe (2018) to combine measurements in the context of archaeological chronological dating. We extend this model to luminescence dating and define a new strategy to detect outliers from the hyperparameters of the event model. This procedure is applied to the combination of Gaussian measurements and lumin...

From a continuous-time long memory stochastic process, a discrete-time randomly sampled one is drawn. We investigate the second-order properties of this process and establish some time-and frequency-domain asymptotic results. We mainly focus on the case when the initial process is Gaussian. The challenge being that, although marginally remains Gaus...

Objective:
Spray formulations are currently under development in the field of topical photoprotection. Such forms are characterized by their high fluidity, a property that is obtained by the presence of alcohol in the formula. The purpose of this work was to study the influence of ethanol in sunscreens on the photoprotective efficacy as well as th...

This article focuses on the estimation of the stability index and scale parameter of stable random variables. We study an estimator based on log-moments,. The main advantage of this estimator is that it has a simple closed-form expression. This allows us to prove an almost sure convergence result as well as a central limit theorem. We show how to i...

Statistical analysis has become increasingly important in optically stimulated luminescence (OSL) dating since it has become possible to measure signals at the single-grain scale. The accuracy of large chronological datasets can benefit from the inclusion, in chronological modelling, of stratigraphic constraints and shared systematic errors. Recent...

The Chauvet cave (UNESCO World Heritage site, France) is located in the Ardèche Gorge, a unique physical and cultural landscape. Its setting within the gorge—overlooking a meander cutoff containing a natural arch called the Pont d’Arc—is also remarkable. Investigating possible associations between sites’ physical and cultural settings, chronologies...

This paper investigates second order properties of a stationary continuous time process after random sampling. While a short memory process always gives rise to a short memory one, we prove that long-memory can disappear when the sampling law has very heavy tails. Despite the fact that the normality of the process is not maintained by random sampli...

This paper presents a new algorithm for statistical inference and analysis of spatial patterns assumed to be realisations of Gibbs point processes. This approach has a general character and it contributes to the existing methods based on Approximate Bayesian Computation, by providing control properties of the proposed solution. Results on simulated...

This article focuses on the estimation of the stability index and scale parameter of stable random variables. While there is a sizable literature on this topic, no precise theoretical results seem available. We study an estimator based on log-moments, which always exist for such random variables. The main advantage of this estimator is that it has...

Distinguishing long memory behaviour from nonstationarity can be very difficult as in both cases the sample autocovariance function decays very slowly. Available stationarity tests either do not include long memory or fare poorly in terms of empirical size, especially near the boundary between long memory and nonstationarity. We propose a parameter...

Statistical analysis has become increasingly important in the field of OSL dating since it has become possible to measure signals at the single grain scale. The accuracy of large chronological datasets can benefit from the inclusion, in chronological modelling, of stratigraphic constraints and shared systematic errors. Recently, a number of Bayesia...

Carpooling is an integral component in smart carbon-neutral cities, in particular to facilitate homework commuting. We study an innovative carpooling service developed by the start-up Ecov which specialises in homework commutes in peri-urban and rural regions. When a passenger makes a carpooling request, a designated driver is not assigned as in a...

We propose new statistical tools to analyze and to estimate archeological phases from the posterior distribution of a sequence of dates. All the functions are implemented in the R package ArchaeoPhases. The required inputs are simulated samples from the posterior distribution of the dates. Such Markov Chains Monte Carlo samples are provided, for in...

Increase in rainfall during the early Holocene has been reported from different regions of Indian subcontinent, although the magnitude shows spatial variability with lower change in higher rainfall regions and vice versa. While the early-Holocene rainfall records are available from lowland areas of the Indian sub-continent, the record is poorly doc...

We construct an asymptotically normal estimator β˜N for the tail index β of a distribution on (0,1) regularly varying at x=1, when its N independent realizations are not directly observable. The estimator β˜N is a version of the tail index estimator of Goldie and Smith (1987) [Goldie CM, Smith RL. 1987. The Quarterly Journal of Mathematics 38: 45–7...

Quelques exemples d'application de la statistique bayésienne en lien avec la datation

This paper develops a new global optimisation method that applies to a family of criteria that are not entirely known. This family includes the criteria obtained from the class of posteriors that have nor-malising constants that are analytically not tractable. The procedure applies to posterior probability densities that are continuously differen-t...

A frequency-domain statistic is introduced to test for stationarity versus stochastic or deterministic trend in a time series context. Telling long memory behaviour apart from the presence of a trend can be very tedious as has been shown in the literature. Not many tests are available, and we mainly compare our test to the time-domain one introduce...

In human sciences, mediation designates a particular causal phenomenon where the effect of a variable X on another variable Y passes (par-tially or entirely) through a third variable M. The parameters of interest in mediation models are the direct effect of X on Y and the indirect effect of X on Y through M. We use a Bayesian framework to estimate...

The present paper obtains a complete description of the limit distributions of sample covariances in N × n panel data when N and n jointly increase, possibly at different rate. The panel is formed by N independent samples of length n from random-coefficient AR(1) process with the tail distribution function of the random coefficient regularly varyin...

A new frequency-domain test statistic is introduced to test for short memory versus long memory. We provide its asymptotic distribution under the null hypothesis and show that it is consistent under any long memory alternative. Some simulation studies show that this test is more robust than various standard tests in terms of empirical size when the...

A Note on the Bayesian Modeling of the Stratigraphic Chronology of Canímar Abajo, Cuba – ERRATUM - Anne Philippe, Marie-Anne Vibet

Non-parametric Mediation Analysis for direct effect
with categorial outcomes

We introduce a new R package ‘BayLum’ devoted to the analysis of OSL data and to construct chronological models in a Bayesian framework. Our contribution presents a summary of the statistical models, and introduces the main functions implemented in the package.

All the methods used for the in vitro measurement of the SPF, the universal indicator of sunscreens efficiency, rely on a spectrophotometric analysis. What can vary about the experimental protocol used is mainly the substrate and the type of spectrophotometer chosen. We decided to work with polymethylmetacrylate plates that we analyzed using two sp...

We propose a robust event date model to estimate the date of a target event by a combination of individual dates obtained from archaeological artifacts assumed to be contemporaneous. These dates are affected by errors of different types: laboratory and calibration curve errors, irreducible errors related to contaminations, and taphonomic disturbanc...

We implement a Bayesian statistical analysis of the chronology of Canímar Abajo in Cuba in order to estimate two episodes of burial activity and the period of time corresponding to the hiatus between them. We show that by using simple Bayesian modeling, conclusions can easily be reached by the analysis of the marginal posterior distribution of each...

We implement a Bayesian statistical analysis of the chronology of Canímar Abajo in Cuba in order to estimate two episodes of burial activity and the period of time corresponding to the hiatus between both of them. We show that using a simple Bayesian modelling, conclusions can easily be reached by the analysis of the marginal posterior distribution...

We propose a robust event date model aiming to estimate the date of a target event by the combination of individual dates obtained from archaeological artifacts assumed to be contemporaneous. These dates are affected by errors of different types: laboratory and calibration curve errors, irreducible errors related to contaminations, taphonomic distu...

It is well-known that random-coefficient AR(1) process can have long memory depending on the index β of the tail distribution function of the random coefficient, if it is a regularly varying function at unity. We discuss estimation of β from panel data comprising N random-coefficient AR(1) series, each of length T. The estimator of β is constructed...

Optically Stimulated Luminescence (OSL) is commonly used to date the last exposure of grains extracted from sediments to sunlight. However, it is frequent that some of the measured grains were not sufficiently exposed to light before burial. Such samples are said to be poorly bleached. We propose a new statistical model based on a Bayesian approach...

This paper presents an original ABC algorithm, ABC Shadow, that can be applied to sample posterior densities that are continuously differentiable. The proposed algorithm solves the main condition to be fulfilled by any ABC algorithm, in order to be useful in practice. This condition requires enough samples in the parameter space region, induced by...

Bayesian analysis of luminescence data and 14C age estimate.
Bayesian models are based on the following publications:
Combes, B. & Philippe, A. (2017) <doi: 10.1016/j.quageo.2017.02.003> and Combes et al (2015) <doi: 10.1016/j.quageo.20 This includes, amongst others, data import, export, application of age models and palaeo-
dose model.

This paper presents some innovative methods for modeling discrete scale invariant (DSI) processes and evaluation of corresponding parameters. For the case where the absolute value of the increments of DSI processes are in general increasing, we consider some moving sample variance of the increments and present some heuristic algorithm to characteri...

In connection with the future Seine-North Europe Canal (Seine-Scheldt), a large-scale rescue archaeological survey was conducted at Havrincourt (northern France) between 2008 and 2011. The discovery of several levels of Palaeolithic flint artefacts embedded in a relatively thick loess sequence (ca 6–7 m) preserved on a gentle slope facing North-Eas...

Luminescence ages are calculated by dividing an absorbed dose by the dose rate to which the natural dosimeter has been exposed. In practice, one measures an equivalent dose, De; in the absence of an alpha dose contribution, this should be indistinguishable from the dose absorbed in nature. Here we first review the relationship between absorbed dose...

Nous présentons un modèle de statistique bayésienne permettant de construire une chronologie d’événements archéologiques. Ce type de modélisation permet d’intégrer à la fois des datations archéométriques, par exemple un âge radiocarbone, et l’ensemble des connaissances a priori telles que des dates historiques ou les relations stratigraphiques obse...

We give a practical introduction to the package ArchaeoPhases using published data modelled by Oxcal and comment the statistical results.

Many dating techniques include significant error terms which are not independent between samples to date. This is typically the case in Optically Stimulated Luminescence (OSL) dating where the conversion from characteristic equivalent doses to the corresponding ages using the annual dosimetry data includes error terms that are common to all produce...

We propose new statistical tools to analyze and to estimate archeological phases from the posterior distribution of a sequence of dates. All the functions are implemented in the R package RChronoModel. The required inputs are simulated samples from the posterior distribution of the dates. Such MCMC samples are provided, for instance, by ChronoModel...

A function named textitanalyse_baSAR() was written using the statistical programming language textbfR and its code is now available within thetextbfR package 'Luminescence'. The function allows the application of the Bayesian hierarchical model 'baSAR' proposed by Combés et al. (2015) and comes with additional features to analyse luminescence data...

Measuring the infrared radiofluorescence (IR-RF) signal of K-feldspars, which is thought to be not affected by any anomalous fading potentially provides a promising alternative dating approach to the more studied IR and pIRIR signals. Here we report a series of experiments aimed at characterising the IR-RF signal, which led us to propose an improve...

The R package 'RChronoModel' gives a list of functions developped in order to treat the output of the MCMC algorithm computed with the softwares ChronoModel or Oxcal, especially regarding phases. We give a practical introduction to the package 'RChronoModel' using published data and comment the statistical results. We also introduce our new web app...