1,721,095 research outputs found
A partitioned Single Functional Index Model
No full textGiven a functional regression model with scalar response, the aim is to present a methodology in order to approximate in a semi-parametric way the unknown regression operator through a single index approach, but taking possible structural changes into account. Our paper presents this methodology and illustrates its behaviour both on simulated and real curves datasets. It appears, from an example of interest in spectrometry, that the method provides a nice exploratory tool both for analyzing structural changes in the spectrum and for visualizing the most informative directions, still keeping good predictive power. Even if the main objective of this work is to discuss applied issues of the method, asymptotic behaviour is shortly described
Evaluating the complexity of some families of functional data
Full text linkIn this paper we study the complexity of a functional data set drawn from particular processes by means of a two-step approach. The first step considers a new graphical tool for assessing to which family the data belong: the main aim is to detect whether a sample comes from a monomial or an exponential family. This first tool is based on a nonparametric kNN estimation of small ball probability. Once the family is specified, the second step consists in evaluating the extent of complexity by estimating some specific indexes related to the assigned family. It turns out that the developed methodology is fully free from assumptions on model, distribution as well as dominating measure. Computational issues are carried out by means of simulations and finally the method is applied to analyse some financial real curves dataset
Mean estimation with data missing at random for functional covariables
Full text linkIn a missing-data setting, we want to estimate the mean of a scalar outcome, based on a sample in which an explanatory variable is observed for every subject while responses are missing by happenstance for some of them. We consider two kinds of estimates of the mean response when the explanatory variable is functional. One is based on the average of the predicted values and the second one is a functional adaptation of the Horvitz-Thompson estimator. We show that the infinite dimensionality of the problem does not affect the rates of convergence by stating that the estimates are root-n consistent, under missing at random (MAR) assumption. These asymptotic features are completed by simulated experiments illustrating the easiness of implementation and the good behaviour on finite sample sizes of the method. This is the first paper emphasizing that the insensitiveness of averaged estimates, well known in multivariate non-parametric statistics, remains true for an infinite-dimensional covariable. In this sense, this work opens the way for various other results of this kind in functional data analysis.Fil: Ferraty, Frédéric. Universite Paul Sabatier. Institut de Mathematiques de Toulouse; FranciaFil: Sued, Raquel Mariela. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Cálculo; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Vieu, Philippe. Universite Paul Sabatier. Institut de Mathematiques de Toulouse; Franci
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe 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
Methodological Contributions in Semiparametric Regression Models for Functional Data
Full text link[Abstract]
This doctoral thesis is dedicated to functional regression for scalar response. In particular,
we focus on functional semiparametric models, which combine the practical
advantages of parametric and nonparametric approaches, surpassing both methodologies.
Accordingly, several semiparametric models involving a functional singleindex
component were studied from a theoretical and practical perspective. First,
for the functional single-index model (FSIM) and the semi-functional partial linear
single-index model (SFPLSIM), we provide uniform consistency results (over all
parameters involved) for kernel- and k-Nearest-Neighbours-based statistics related
to the estimation of the semiparametric component. Second, for the sparse semifunctional
partial linear single-index model (SSFPLSIM), we develop a variable selection
procedure in the linear component based on penalized least squares (PLS).
The good behaviour of this method is theoretically assured (rates of convergence of
the estimators are obtained, as well as asymptotic behaviour of the variable selection
procedure). Third, the SSFPLSIM is adapted to the case in which covariates
with linear e ect come from the discretization of a curve. For this new model, the
multi-functional partial linear single-index model (MFPLSIM), the variable selection
problem was also studied. Consequently, two new algorithms were proposed (providing
theoretical results that ensure their good performance) to solve the ine ciency
of the PLS method when it is directly applied to the MFPLSIM. For all the models
and procedures mentioned above, theoretical results are accompanied by both simulation
studies and real data applications which illustrate the good performance of
the proposed methodology in practice.[Resumo]
Esta tese está adicada ao estudo da regresión funcional con variable resposta escalar.
En particular, centrámonos en modelos funcionais semi-paramétricos, os cales combinan
as vantaxes prácticas dos enfoques paramétrico e non-paramétrico, superando
a ambas metodoloxías. Desta maneira, estudáronse, tanto dende o punto de vista
te orico como dende a perspectiva pr actica, varios modelos semi-param etricos que
involucran unha compoñente funcional single-index. En primeiro lugar, para o functional
single-index model (FSIM) e para o semi-functional partial linear single-index
model (SFPLSIM) establecemos resultados de consistencia uniforme (sobre todos
os parámetros involucrados) para os estatísticos de tipo núcleo e tipo k-veciños-máis-próximos relacionados coa estimación da compoñente semi-paramétrica do modelo.
En segundo lugar, para o sparse semi-functional partial linear single-index
model (SSFPLSIM) desenvolvemos un procedemento de selección de variables na
compoñente linear baseado en mínimos cadrados penalizados (PLS, iniciais de penalized
least squares). O bo comportamento deste método asegurouse dende o punto
de vista teórico (obtendo taxas de converxencia dos estimadores, así como o comportamento
asintótico do procedemento de selección de variables). En terceiro lugar,
o SSFPLSIM adaptouse ao escenario no cal as covariables con efecto linear proveñen
da discretización dunha curva. Para este novo modelo, o multi-functional partial
linear single-index model (MFPLSIM), estudouse tamén o problema da selección de
variables e propuxéronse dous novos algoritmos (dos que aseguramos teoricamente
o seu bo comportamento) para resolver a inefi cacia do método PLS cando se aplica
directamente ao MFPLSIM. Para todos os modelos e procedementos citados, os resultados
teóricos acompañáronse de estudos de simulación e aplicacións a datos reais
que ilustran o bo comportamento na práctica da metodoloxía presentada.[Resumen]
Esta tesis está dedicada al estudio de la regresión funcional con variable respuesta
escalar. En particular, nos centramos en modelos funcionales semi-paramétricos, los
cuales combinan las ventajas prácticas de los enfoques paramétrico y no-paramétrico,
superando a ambas metodologías. De esta forma, se estudiaron, tanto desde el punto
de vista teórico como desde la perspectiva práctica, varios modelos semi-paramétricos
que involucran una componente funcional single-index. En primer lugar, para el functional
single-index model (FSIM) y para el semi-functional partial linear single-index
model (SFPLSIM) establecemos resultados de consistencia uniforme (sobre todos los
parámetros involucrados) para los estadísticos de tipo núcleo y de tipo k-vecinos-más-próximos relacionados con la estimación de la componente semi-paramétrica del
modelo. En segundo lugar, para el sparse semi-functional partial linear single-index
model (SSFPLSIM) desarrollamos un procedimiento de selección de variables en la
componente linear basado en mínimos cuadrados penalizados (PLS, iniciales de penalized
least squares). El buen comportamiento de este método se ha asegurado desde
el punto de vista teórico (obteniendo tasas de convergencia de los estimadores, así
como el comportamiento asintótico del procedimiento de selección de variables). En
tercer lugar, el SSFPLSIM se ha adaptado al escenario en el cual las covariables con
efecto linear provienen de la discretización de una curva. Para este nuevo modelo,
el multi-functional partial linear single-index model (MFPLSIM), se ha estudiado
también el problema de selección de variables y se propusieron dos nuevos algoritmos
(de los que aseguramos teóricamente su buen comportamiento) para resolver la
ine ficiencia del método PLS cuando se aplica directamente al MFPLSIM. Para todos
los modelos y procedimientos citados, los resultados teóricos se acompañaron de estudios
de simulación y aplicaciones a datos reales que ilustran el buen comportamiento
en la práctica de la metodología presentada.Xunta de Galicia; ED481A-2018/191Xunta de Galicia; ED431G/01 2016-2019Xunta de Galicia; ED431G2019/01Xunta de Galicia; ED431C 2016-015Xunta de Galicia; ED431C2020-014This research has been partially supported by the Spanish Ministerio de Economía y Competitividad (MINECO) under Grants MTM2014-52876-R and MTM2017-82724-R, by the Spanish Ministerio de Ciencia e Innovación (MICINN) under Grant PID2020-113578RB-I00, by the Xunta de Galicia through Centro Singular de Investigación de Galicia accreditation under Grants ED431G/01 2016-2019 and ED431G 2019/01 and through the Grupos de Referencia Competitiva under Grants ED431C 2016-015 and ED431C2020-014 and in part by the European Union (European Regional Development Fund-ERDF). The author particularly thanks the contracts financed by the research group MODES (from May 1, 2017 to August 31, 2017) and by the CITIC (from September 1, 2017 to May 30, 2018) and the PhD contract financed by the Xunta de Galicia and the European Union (European Social Fund-ESF), the reference of which is ED481A-2018/191 (from May 31, 2018). Some results of this thesis have been obtained during a stay of the author at the Universit ́e Paul Sabatier, Toulouse (from March 13, 2019 to June 12, 2019), financed by the Xunta de Galicia, with reference ED481A-2018/19
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
