Showing results 61 to 80 of 176
  Comparaison empirique des estimateurs des taux d'erreur en analyse discriminante; ; et al in Revue de Statistique Appliquée (2003), LI(3), 61-74 Monte Carlo experiments are performed to compare twenty estimators or error rates in discriminant analysis in the case of two populations and linear classification rule. Several distributions (normal, chi ... [more ▼] Monte Carlo experiments are performed to compare twenty estimators or error rates in discriminant analysis in the case of two populations and linear classification rule. Several distributions (normal, chi-square and beta) have been considered. Estimators eOS (for actual and expected error rate) and eB (for optimal error rate) are the best, except for distributions very different from normal distributions. The e632 estimator is the best non parametric estimator. This estimator is better than parmetric estimators for distributions very different from normal distributions. [less ▲] Detailed reference viewed: 11 (0 ULg)Empirical comparison of error rate estimators in discriminant analysis; Palm, Rodolphe  Poster (2002, July) Detailed reference viewed: 4 (0 ULg)Macros Minitab pour la détermination par Bootstrap des limites de confiance d'un estimateurPalm, Rodolphe Software (2002) Detailed reference viewed: 2 (0 ULg)Development Of A Visual Method To Quantify The Gossypol Content In Cotton Seeds; Lognay, Georges ; Palm, Rodolphe et alin Crop Science (2002), 42(6), 1937-1942 Detailed reference viewed: 24 (3 ULg)Répartition des arbres et des volumes par classes de grosseur dans les peuplements de pin d'Alep (Pinus halepensis Mill.) en Tunisie; Palm, Rodolphe in Annals of Forest Science (2002), 59(3), 293-300 A study of the number and volume of trees by girth classes for Aleppo pine (Pinus halepensis Mill.) in Tunisia carried out using data collected from 348 temporary plots of 4 ares. The standard deviation ... [more ▼] A study of the number and volume of trees by girth classes for Aleppo pine (Pinus halepensis Mill.) in Tunisia carried out using data collected from 348 temporary plots of 4 ares. The standard deviation, the FISHER coefficient and PEARSON coefficient for the girth distribution were calculated for each plot and related to age, dominant height and mean plot circomference. The resulting relationships were used to estimate the parameters of the girth distribution for each theoretical stand corresponding to one row of the yield tables that were establied from the same plots. The probability density function relative to PEARSON's type I distribution was determined for each theoretical stand. According to this function of density, distribution tables giving the number and the volume of trees (in percent) by girth classes of 10 cm were drawn up. [less ▲] Detailed reference viewed: 20 (1 ULg)Conditions d'application et transformations de variables en régression linéairePalm, Rodolphe ; in Notes de Statistique et d'Informatique (2002), (1), 1-34 This note first reviews methods used for checking the assumptions in linear regression (lack of fit, normality, homoscedasticity and independance of the residuals) and then describes variables ... [more ▼] This note first reviews methods used for checking the assumptions in linear regression (lack of fit, normality, homoscedasticity and independance of the residuals) and then describes variables transformations as remedial action when the assumptions are not fulfilled. [less ▲] Detailed reference viewed: 29 (1 ULg)Macros Minitab pour la régression linéairePalm, Rodolphe Software (2002) Detailed reference viewed: 6 (0 ULg)Utilisation du bootstrap pour les problèmes statistiques liés à l'estimation des paramètres.Palm, Rodolphe in Biotechnologie, Agronomie, Société et Environnement = Biotechnology, Agronomy, Society and Environment [=BASE] (2002), 6(3), Detailed reference viewed: 22 (0 ULg) Compared Regression Methods For Inferring Ammonium Nitrogen Concentrations In Running Freshwaters From Aquatic Bryophyte AssemblagesVanderpoorten, Alain ; Palm, Rodolphe in Hydrobiologia (2001), 452(1-3), 181-190 Detailed reference viewed: 4 (1 ULg)Modèle de productivité et tarif de cubage des peuplements de teck (tectona grandis L. F.) au Sud-Bénin; Palm, Rodolphe ; et alin Annales des Sciences Agronomiques du Bénin (2001), 2(2), 209-224 This study aims to build site index model and stem volume function of pure, even aged and relatively homogeneous teak stands in south Benin. The characteristics of the stands were obtained from the ... [more ▼] This study aims to build site index model and stem volume function of pure, even aged and relatively homogeneous teak stands in south Benin. The characteristics of the stands were obtained from the inventory of 104 temporary plots sampled from stands with different ages and fertility. The stem analysis of 19 dominant trees wer used to establish, by serial regression, a model giving the evolution of top height according to the age. The site index curves were built in order to determine site index of the stands. The estimated volume function obtained shows that age, site index and basal area are the main stand parameters of stem volume funtion. [less ▲] Detailed reference viewed: 20 (1 ULg)Etude empirique des estimateurs des taux d'erreur en analyse discriminante; Palm, Rodolphe in Revue de Statistique Appliquée (2001), XLIX(4), 71-85 Monte Carlo experiments are performed to compare ten parametric and six non parametric estimators of the three error rates (actual, expected and optimal error rate) in discriminant analysis. This ... [more ▼] Monte Carlo experiments are performed to compare ten parametric and six non parametric estimators of the three error rates (actual, expected and optimal error rate) in discriminant analysis. This comparison is restricted to the context of two p-dimensional normal group conditional distributions with the same covariance matrix. The study shows that certain estimators are markedly superior and users should be warned against some estimators available in statistical softwares. [less ▲] Detailed reference viewed: 27 (1 ULg)L'analyse de la variance multivariée et l'analyse canonique discriminante : principes et applicationsPalm, Rodolphe in Notes de Statistique et d'Informatique (2000), (1), 40 This note describes the principles of multivariate analysis of variance and of canonical discriminant analysis. The methods are illustrated by two examples. Detailed reference viewed: 29 (0 ULg)Hipóteses estatísticas : revendo idéias sobre ortogonalidade e balanceamento em análise de varîancia; Claustriaux, Jean-Jacques ; Palm, Rodolphe in Multiciência (2000), 4(1), 62-82 Detailed reference viewed: 4 (0 ULg)A propos de l'intervalle de confiance des indices d'aptitude Cp et Cpk; Palm, Rodolphe in XXXIèmes Journées de Statistiques (1999, May) Detailed reference viewed: 4 (0 ULg)Indices d'aptitude des procédés de productionPalm, Rodolphe in Notes de Statistique et d'Informatique (1999), (5), 26 This note describes the main process capability indices and presents some inferential porperties. A numerical example is analysed by Minitab and SAS softwares. Detailed reference viewed: 6 (0 ULg)L'analyse discriminante décisionnelle : principes et applicationPalm, Rodolphe in Notes de Statistique et d'Informatique (1999), (4), 41 The principles of discriminant analysis are described and illustrated by the iris data set published by Fisher [1936]. Detailed reference viewed: 17 (0 ULg)Statistique, empirique, informelle : quelle enquête pour la collecte d'informations sur les exploitations agricoles ?; Palm, Rodolphe in Cahiers Agricultures (1999), 8 Detailed reference viewed: 4 (0 ULg)Tables de cubage des arbres et des peuplements forestiers.; Palm, Rodolphe ; Rondeux, Jacques et alBook published by Les Presses Agronomiques de Gembloux - 2ème édition (1999) Les "Tables de cubage des arbres et des peuplements forestiers" sont destinées aux propriétaires, aux gestionnaires et aux exploitants forestiers de la Moyenne et de la Haute Belgique et des régions ... [more ▼] Les "Tables de cubage des arbres et des peuplements forestiers" sont destinées aux propriétaires, aux gestionnaires et aux exploitants forestiers de la Moyenne et de la Haute Belgique et des régions limitrophes (Allemagne, France et Grand-Duché de Luxembourg), ainsi qu'aux enseignants qui s'intéressent aux problèmes d'estimation et de croissance des arbres et des forêts. Elles comprennent des tables et des équations de cubage très diversifiées relatives à douze essences ou groupes d'essences : bouleaux, chênes, chêne rouge d'Amérique, douglas, épicéa, érable sycomore, frêne, hêtre, mélèzes, merisier, ormes et pin sylvestre. Les équations sont présentées sous une forme mathématique conventionnelle. Moyennant quelques modifications, celles-ci peuvent être converties en langages de programmation courants sur les micro-ordinateurs, être utilisées sur des machines à calculer programmables ou encore au sein de feuilles de calcul propres aux tableurs. [less ▲] Detailed reference viewed: 76 (11 ULg)Influence of some experimental factors on the evaluation of the sensitivity of Aphidius rhopalosiphi De Stefani-Perez to phosalone.; ; et al in Mededelingen van de Faculteit Landbouwkundige en Toegepaste Biologische Wetenschappen (Rijksuniversiteit te Gent) (1999), 64(3a), Detailed reference viewed: 16 (6 ULg)Influence de facteurs abiotiques ou biotiques sur l'evaluation de la sensibilite d'Aphidius rhopalosiphi De Stefani-Perez a la phosalone.; ; et al in Parasitica (1999), 54(2-3), Detailed reference viewed: 6 (2 ULg) |
||
