Search results for " quantile regression"

Penalized regression and clustering in high-dimensional data

The main goal of this Thesis is to describe numerous statistical techniques that deal with high-dimensional genomic data. The Thesis begins with a review of the literature on penalized regression models, with particular attention to least absolute shrinkage and selection operator (LASSO) or L1-penalty methods. L1 logistic/multinomial regression models are used for variable selection and discriminant analysis with a binary/categorical response variable. The Thesis discusses and compares several methods that are commonly utilized in genetics, and introduces new strategies to select markers according to their informative content and to discriminate clusters by offering reduced panels for popul…

Further considerations on a new indicator for higher education student performance

2016

Il presente lavoro si inserisce nel dibattito internazionale sul sistema di voto universitario e sulla sua sintesi come misura della performance di uno studente. Partendo dalla nuova misura proposta in Adelfio et al. (2014), in questo breve articolo si pone l’enfasi sull’importanza della scelta della misura opportuna, soprattutto nella individuazione delle possibili determinanti della performance, utile nella scelte delle opportune politiche di intervento sulla performance della carriera dello studente. Per richiamare il nuovo indicatore proposto e per fare il confronto con quello esistente, si `e fatto riferimento ai Sistema Universitario italiano. This paper joins the international debate…

Interactions, spillovers de connaissance et croissance des économies modernes. Faut-il préférer la globalisation ou la proximité géographique ?

2009

Globalisation and metropolisation in modern economies induce some locational strategies of knowledge based activities towards cities and deeply increase trade and move of ideas across cities. In that context, we study the way knowledge spillovers have influenced the economic growth of 82 European Metropolises over the 1990-2005 period. We model knowledge spillovers across cities according to three specific interaction patterns depending either on geography or on global advanced services or thought a combination of these patterns. We show that the mixed pattern matters the best for economic growth of cities in Europe.

Growth curves of sorghum roots via quantile regression with P-splines

2014

Plant roots are a major pool of total carbon in the planet and their dynamics are directly relevant to greenhouse gas balance. Composted wastes are increasingly used in agriculture for environmental and economic reasons and their role as a substitute for traditional fertilizers needs to be tested on all plant components. Here we propose a regression quantile approach based on P-splines to assess, quantify and compare the root growth patterns in two treatment groups respectively undergoing compost and traditional fertilization.

Analysis of the determinants of entrepreneurial intention: the case of Burkina Faso

2018

International audience; In this study, we propose to analyze students' entrepreneurial intention, drawing on Lazear's (2004) self-selection model. This model captures the role of "human capital" in employment assignment and emphasizes the importance of the variety of skills in the individual's entrepreneurial orientation. For this purpose, we have a database collected in 2017 from over 1000 students at Ouaga I and Ouaga II universities in Burkina Faso. The results of estimates obtained using the quantile regression method show a positive and significant effect of the diversity of skills on the intention score, mainly at the median level. Even if the effect is not strong, this result support…

A new approach for clustering of effects in quantile regression

2017

In this paper we aim at nding similarities among the coefficients from a multivariate regression. Using a quantile regression coefficients modeling, the effect of each covariate, given a response (also multivariate) is a curve in the multidimensional space of the percentiles. Collecting all the curves, describing the effects of each covariate on each response variable, we could be able to assess if only one or more covariates have same effects on different responses.

A penalized approach to covariate selection through quantile regression coefficient models

2019

The coefficients of a quantile regression model are one-to-one functions of the order of the quantile. In standard quantile regression (QR), different quantiles are estimated one at a time. Another possibility is to model the coefficient functions parametrically, an approach that is referred to as quantile regression coefficients modeling (QRCM). Compared with standard QR, the QRCM approach facilitates estimation, inference and interpretation of the results, and generates more efficient estimators. We designed a penalized method that can address the selection of covariates in this particular modelling framework. Unlike standard penalized quantile regression estimators, in which model selec…

NEIGHBORHOOD EFFECTS IN SPATIAL HOUSING VALUE MODELS. THE CASE OF THE METROPOLITAN AREA OF PARIS (1999)

2009

In hedonic housing models, the spatial dimension of housing values are traditionally processed by the impact of neighborhood variables and accessibility variables. In this paper we show that spatial effects might remain once neighborhood effects and accessibility have been controlled for. We notably stress on three sides of neighborhood effects: social capital, social status and social externalities and consider the accessibility to the primary economic center as describing the urban spatial trend. Using spatial econometrics specifications of the hedonic equation, we estimate whether spatial effects impact the housing values. Our empirical case concerns the Metropolitan Area (MA) of Paris i…

Urban segregation and unemployment: A case study of the urban area of Marseille – Aix-en-Provence (France)

2018

International audience; In this paper, we study the effects of the spatial organization of the urban area of Marseille – Aix-en-Provence on unemployment there. More specifically, differences in the characteristics of the residential population induce urban stratification with the result that urban structure may affect the probability of employment. In order to evaluate the effects of spatial structure on unemployment, we implement a spatial probit model to reveal the employment probabilities of young adults still living with their parents. Our results support the hypothesis that living in or near a deprived neighborhood decreases the probability of employment.

Productivity analysis of Latvian companies using ORBIS database

2021

International audience; This research study uses ORBIS microdata at the company level to analyse productivity of 167 thousand economically active Latvian companies over 2011-2018. The aim of the study is twofold-to find factors consistently associated with productivity at the company level; and to recommend possible criteria for companies to receive a state support (from the view of enhancing aggregate productivity in the long term). Our research results show that productivity of Latvian companies is positively related to their size, age, as well as location closer to Riga and other big cities. However, there is a substantial within-group variation in productivity between companies. Multiva…