La collecte de l'information. Pour qui ? Pourquoi ? Comment ?

in Notes de Statistique et d'Informatique (2012), (3), 7

Etat des dépenses en viande par les ménages belges en 2008

Conference (2012, May)

Evolution des dépenses alimentaires en produits d'origine animale des ménages wallons

Poster (2012, March 07)

Tables de contingence à trois dimensions : aspects théoriques, applications et analogie avec l'analyse de la variance à trois critères de classification

in Notes de Statistique et d'Informatique (2012), (1), 19

For contingency table, concepts of independence are not so easy to understand in statistical practice. So, theoretical aspects of the log-linear model are described and applied to a three levels example ... [more ▼]

For contingency table, concepts of independence are not so easy to understand in statistical practice. So, theoretical aspects of the log-linear model are described and applied to a three levels example; an analogy with analysis of variance is also established. [less ▲]

Inférence statistique et critères de qualité de l'ajustement en régression logistique binaire

in Notes de Statistique et d'Informatique (2011), (5), 32

The principles of statistical inference based on the maximum likelihood function are described and applied to binary logistic regression. Several goodness of fit statistics are also given. These topics ... [more ▼]

The principles of statistical inference based on the maximum likelihood function are described and applied to binary logistic regression. Several goodness of fit statistics are also given. These topics are illustrated by an example processed by Minitab and SAS softwares. [less ▲]

Macros Minitab pour le choix d'une transformation pour la normalisation de variables

in Notes de Statistique et d'Informatique (2011), (3),

Macros are proposed to Minitab users for transforming data to normality. The following transformations are examined : log transformation, Box et Cox transformation with lambda equal to -2, -1, -0,5, 0,5 ... [more ▼]

Macros are proposed to Minitab users for transforming data to normality. The following transformations are examined : log transformation, Box et Cox transformation with lambda equal to -2, -1, -0,5, 0,5 and 2, Box et Cox transformation with maximum likelihood estimation of lambda and transformations using the Johnson system of distributions. Two examples are given. [less ▲]

Gembloux Agricultural University : ICT learning

Scientific conference (2009)

Etat des lieux des outils TICE de la FUSAGx.

La mesure de l'exactitude d'un récepteur GPS

in XYZ (2008), 115

A method is proposed to determine the accuracy of a GPS receiver. This accuracy consists of the trueness of the receiver (absence of systematic error) and its precision (effect of unavoidable accidental ... [more ▼]

A method is proposed to determine the accuracy of a GPS receiver. This accuracy consists of the trueness of the receiver (absence of systematic error) and its precision (effect of unavoidable accidental errors). This method consists in using the GPS receiver to perform, at different dates, the measurement of coordinates of some stations of known coordinates. The discrepancies between the coordinated measured and the “known” coordinates of these stations are submitted to an two-way analysis of variance. This one permits to verify if accidental errors are or not independent of the dates and stations of measurement. Th results of this analysis of variance allow the value the precision of the receiver therefore. The also [less ▲]

Sur l'erreur résiduelle obtenue en régression linéaire multiple.

Scientific conference (2007)

The residual error is one of the most used criteria for the choice of regression model. The large majority of the criteria for model selection are also functions of the usual variance estimate for a ... [more ▼]

The residual error is one of the most used criteria for the choice of regression model. The large majority of the criteria for model selection are also functions of the usual variance estimate for a regression model, as Akaike criterion information [Akaike, 1973] and Mallows’ criterion [Mallows, 1964]. The effectiveness of these criteria to approach the theoretical model is related to the good estimate of the theoretical residual error of the model. This efficiency is often limited by the sample size used for the estimates. The choice of a invalid model can have bad consequences on the objective of the research in particular on the forecasts, interpretations and the conclusions. We studied by Monte Carlo simulation the effects of the data structure on the quality of the residual error obtained in multiple linear regression. The results showed that the estimator is a good estimator when the model is established without selection of variables, but becomes biased when the model results from a selection of variables. Colinearity between the explanatory variables and the index which measure the importance of the variables in the true model do not have an influence on the quality of the estimator. [less ▲]

Science et symbole. Libres propos autour des méthodes de recherche.

Scientific conference (2006, February)

Theoretically, a research worker tries to understand the unknown world around himself. To answer his question, he follows a road called scientific methodology. Is it the only possible way to find ? The ... [more ▼]

Theoretically, a research worker tries to understand the unknown world around himself. To answer his question, he follows a road called scientific methodology. Is it the only possible way to find ? The objective of this paper is to draw a picture introducing the scientific and the symbolic methodologies to approach new knowledges. [less ▲]