Onderzoek naar betere schatting van de dichtheid van gras- en maiskuilen
Zom, R.L.G. ; Abbink, G.W. ; Schooten, H.A. van - \ 2015
Wageningen : Wageningen UR Livestock Research (Rapport / Wageningen UR Livestock Research 872) - 46
graskuilvoer - kuilvoer - maïskuilvoer - dichtheid - voorraden - veevoeder - voedingswaarde - kuilvoerkwaliteit - lineaire modellen - regressieanalyse - grass silage - silage - maize silage - density - stocks - fodder - nutritive value - silage quality - linear models - regression analysis
This report describes the results of a study on the possibilities to estimate the density of grass en maize silages for calculation of the fodder stock more accurately than the current table values. During ensiling the amount of crop of 104 grass silage clamps, 42 maize silage clamps and 108 big bales (54 round and 54 square) were weighted and after ensiling the dimensions were measured and the chemical composition was analysed. For round and square bales a new regression formula was derived, which estimates the density more accurate than the current table values. It is recommended to calculate the density of round en square bales with the following formula: Density (kg/m3) = 994.81 - 0.5335 x dry matter content (g/kg) - 1.196 x crude fibre content (g/kg ds). For grass en maize silage in clamps and bunker silo’s no new model could be derived which estimated the density more accurately than the current table values.
Models to relate species to environment: a hierarchical statistical approac
Jamil, T. - \ 2012
Wageningen University. Promotor(en): Cajo ter Braak. - S.l. : s.n. - ISBN 9789461731395 - 146
statistiek - lineaire modellen - interacties - kenmerken - bayesiaanse theorie - plantenecologie - biostatistiek - statistics - linear models - interactions - traits - bayesian theory - plant ecology - biostatistics
In the last two decades, the interest of community ecologists in trait-based approaches has grown dramatically and these approaches have been increasingly applied to explain and predict response of species to environmental conditions. A variety of modelling techniques are available. The dominant technique is tocluster the species based on their functional traits and then summarize the response of the clusters to environmental change. In general, fitting explicit models to data is always more informative and powerful than more informal approaches. The central theme of the thesis is how to quantify the relation of traits with the environment using three data tables, data on species occurrence and abundance in sites, data on traits of species and data on the environmental characteristics of sites. In this thesis, we place the challenge of quantifying trait-environment relationships in the context of species distribution modelling, so in the context of species-environment relationships. We present a hierarchal statistical approach to species distribution modelling that efficiently utilize the trait information and that is able to automatically select the relevant traits and environmental characteristics. This model-based approach, coupled with recent statistical developments and increased computing power, opens up possibilities that were unimaginable before.
In the present study a hierarchical statistical approach is introduced for modeling and explaining species response along environmental gradients by species traits. The model is an extension of the generalized linear model with random terms that express the between-species variation in response to the environment. This so-called generalized linear mixed model (GLMM)is derived byintegrating a two-step procedure into one. As the basic GLMM we take the random intercept and random slope model. To introduce traits, the regression parameters (intercept and slope) are made linearly dependent on the species traits. As a consequence the trait-environment relationship is represented as an interaction term in the model. The method is illustrated using the famous Dune Meadow Data using Ellenberg indicator values as species traits.
Niche theory proclaims that species response to environmental gradients is nonlinear. Each species has preferred an environmental condition in which it can survive and reproduce optimally. Thus each species tends to be most abundant around a specific environmental optimum and the distribution of species along any environmental gradient is usually unimodal, with the maximum at some ecological optimum.For presence-absence data, the simplest unimodal (non-negative) species response curve is the Gaussian logistic response curve with three parameters that characterize the niche: optimum (niche centre), tolerance (niche width) and maximum (expected occurrence at the centre). Niches of species differ between species and species are assumed to be evolutionary adapted. It is difficult to fit the Gaussian logistic model with linear trait submodels for the parameters with the available (generalized) nonlinear mixed model software.
We develop the trait-modulated Gaussian logistic model in which the niche parameters are made linearly dependent on species traits. The model is fitted to data in the Bayesian frameworkusing OpenBUGS (Bayesian inference Using Gibbs Sampling).A Bayesian variable selection method is used to identify which species traits and environmental variables best explain the species data through this model. We extended the approach to find the best linear combination of environmental variables.
We explained why and when (generalized) linear mixed models can effectively analyse unimodal data and presented a graphical tool and statistical test to test for unimodality while fitting just a generalized linear mixed model without any squared or other polynomial term. A GLMM is, of course, a linear model. Despite this fact, it can be used to detect unimodality and to fit unimodal data, with the provision that the differences in niche widthsamongspecies are not too large. As graphical tool we suggested to plot the random site effects against the environmental variable. There is an indication for unimodality, when this graph shows a quadratic relationship. The efficacy of GLMM to analyse unimodal data is illustrated by comparing the GLMM approach with an explicit unimodal model approach on simulated data and real data that show unimodality.
When a system is described by a statistical model, model complexity leads to a very large computing time and poor estimation, especially if the number of predictors is large relative to the data size. As an alternative to and improvement over stepwise methods, shrinkage methods have been proposed. One of these is the Relevance vector machine (RVM). RVM assigns individual precisions to weights of predictors which are then estimated by maximizing the marginal likelihood (Type-II ML or empirical Bayes). We also investigated the selection properties of RVM both analytically and by experiments. We found that RVM is rather tolerant for predictors to stay in the model and concluded that RVM is not a real solution in high-dimensional data problems.
By further study the multi-trait and multi-environmental variablemodel selection method developed that used our previous study in a linear mixed model context. The method is called tiered forward selection. In the first tier, the random factors are selected, in the second, the fixed effects are selected and in the final tier non-significant terms are removed based on a modified Akaike information criterion. The linear mixed model with the tiered forward selection is compared with Type-II ML and existing methods for detecting trait-environment relationships that are not based on mixed models, namely the fourth corner method and the linear trait-environment method (LTE).
Mathematical algorithm to transform digital biomass distribution maps into linear programming networks in order to optimize bio-energy delivery chains
Velazquez-Marti, B. ; Annevelink, E. - \ 2008
biomassa productie - bio-energie - lineaire modellen - agro-industriële ketens - geografische informatiesystemen - biomass production - bioenergy - linear models - agro-industrial chains - geographical information systems
Many linear programming models have been developed to model the logistics of bio-energy chains. These models help to determine the best set-up of bio-energy chains. Most of them use network structures built up from nodes with one or more depots, and arcs connecting these depots. Each depot is source of a certain biomass type. Nodes can also be a storage point for a certain biomass type or a production facility (e.g. power plant) where the biomass is used. Arcs represent transport between depots. To be able to combine GIS spatial studies with linear programming models it is necessary to build a network from a digital map. In this work a mathematical calculation method is developed to select the actual points on the map where to collect biomass that will then be considered as biomass sources in a network model.
Dynamisch melken en voeren levert geld op
Ouweltjes, W. ; Andre, G. ; Zom, R.L.G. ; Bleumer, E.J.B. - \ 2008
V-focus 5 (2008)april (2). - ISSN 1574-1575 - p. 22 - 23, 25.
melkveehouderij - melken - voedering - krachtvoeding - automatisering - melkstandinrichtingen - robots - lineaire modellen - dynamische modellen - bedrijfsresultaten in de landbouw - dairy farming - milking - feeding - force feeding - automation - milking parlours - robots - linear models - dynamic models - farm results
Op het High-techbedrijf van de Waiboerhoeve is in 2006 een prototype voor een dynamisch lineair adviessysteem voor melken en voeren ontwikkeld en getoetst. De resultaten geven aan dat met deze benadering een aanzienlijk beter saldo behaald kan worden dan met traditionele adviezen
Designing food supply chains- a structured methodology: a case on novel protein foods
Apaiah, R.K. - \ 2006
Wageningen University. Promotor(en): Tiny van Boekel, co-promotor(en): Eligius Hendrix; Anita Linnemann. - [S.l. ] : S.n. - ISBN 9789085044659 - 147
voedselketens - nieuwe voedingsmiddelen - erwten - peulvruchteiwit - ontwerp - besluitvorming - lineaire modellen - milieueffect - methodologie - kwaliteit - kosten - ketenmanagement - agro-industriële ketens - nieuwe eiwitten - food chains - novel foods - peas - legume protein - design - decision making - linear models - environmental impact - methodology - quality - costs - supply chain management - agro-industrial chains - novel proteins
This thesis proposes and implements a structured methodology to aid in chain design and the evaluation and decision making processes that accompany it.It focusesonhow to design the entire chain from start to finish, so that the consumer gets a product that he/she wants, i.e.concentrating on product attributes rather than on the delivery of the product. The novel protein food (NPF) case from the PROFETAS program was used to develop the methodology. Two attributes of quality were investigated with the qualitative model. Some insights obtained from this model were: thegeneric supply chain for a food product constitutes the following links: primary production, ingredient preparation/processing, product processing, distribution and retailing and consumer processing.This entire chain from primary production up to and including consumer processing influences the final product; but the relative contribution of the links varies according to the goal for which the chain is being designed and optimised. Chains have to be designed for a specific end product as the chain pathway changes and the relative contribution of the links changes with the product. Chain design also changes with the goal.A linear programming model was developed to design a supply chain for the NPF with lowest cost of manufacture. Exergy analysis was used to study the environmental impact of the NPF chain. These models were combined with multiple criteria decision making (MCDM) to give a structured methodology to aid in the design, evaluation and decision making processes of chain design. Variables in each link of the chain were screened to generate potential supply chains (alternatives) and these were evaluated with two MCDM models and ranked. The goals used to evaluate the alternatives are the quality of the product, the cost and the environmental load.The most important factor in the choice of these models was the ease with which they could handle a mix of quantitative and qualitative information, quantify the qualitative information and generate an overall value for each alternative and generate a preference order. The methodology was successful in focussing the decision makers' attention to the issues on hand. The stepwise process made the decision making process transparent and easy to review and audit.
Choice of attractions, expenditure and satisfaction of international tourists to Kenya
Odunga, P.O. - \ 2005
Wageningen University. Promotor(en): Henk Folmer; Gerrit Antonides; Wim Heijman. - s.l. : S.n. - 193
internationaal toerisme - toerisme - kenya - toeristische attracties - besteding van toerist - klanttevredenheid - natuurtoerisme - cultureel toerisme - besluitvorming - lineaire modellen - covariantie-analyse - international tourism - tourism - kenya - decision making - tourist attractions - tourist expenditure - consumer satisfaction - nature tourism - cultural tourism - linear models - analysis of covariance
Keywords: tour packaging, preference, choice, expenditure, satisfaction, tourist characteristics, trip attributes, structural equation modelling, LISREL, KenyaIn this thesis, we examine the impact of tour packaging on preference, expenditure and satisfaction among the international tourists visiting
Breeding for longevity in Italian Chianina cattle
Forabosco, F. - \ 2005
Wageningen University. Promotor(en): Johan van Arendonk, co-promotor(en): Piter Bijma; R. Bozzi. - Wageningen : - ISBN 9789085042662 - 153
chianina - vleesvee - gebruiksduur - productieve levensduur - fenotypen - rundvleesproductie - genetische analyse - lineaire modellen - overleving - rentabiliteit - kenmerken - selectief fokken - genetische verbetering - chianina - beef cattle - longevity - productive life - phenotypes - beef production - genetic analysis - linear models - survival - profitability - traits - selective breeding - genetic improvement
The objective of this thesis was to evaluate genetic aspects of longevity (LPL) in the Chianina beef cattle population in order to define how to include this trait in selection criteria. The Chianina breed has been raised for over twenty-two centuries inItalyand today this breed is present in different countries across Europe, South and Central America,Australia,Canada and the USA. Its characteristics of somatic gigantism and rapid growth are combined with enormous resistance to harsh environmental conditions, great ease of calving and an excellent meat quality. In this breed longevity was recorded as the length of productive life (LPL), defined as years from the age at the insemination that resulted in the birth of the first calf to the date of culling or censoring. Six mo were added after the last date of calving to account for the time that the calf remains with the cow. The LPL was equal to 5.97 years on average. Heritability was equal to 0.11 when both censored and uncensored data were included to estimate longevity with the survival analysis. Type traits were used as an early predictor of profitability and muscularity traits were the most important parameters for longevity among the factors studied. Cows with approximately one calf per year remained in the herd longer than cows with fewer calves.Cows with a long LPL were more profitable than cows with short LPL. The final score could be used as an early predictor of profitability. An increase of one day unit in LPL was associated with an increase of +0.19 /cow per year and +1.65 /cow on a lifetime basis. Including longevity in both the Chianina breeding index and breeding goal either using empirical or economical weights has the positive effect of increasing the response (+2.97 and +4.92 days/year respectively). Beef breeding organizations should consider the opportunity to include longevity in a future breeding scheme to increase profit and to promote the well-being and welfare of the cows.
Rural Industrial Entrepreneurship - The Case of Bardhaman District in West Bengal
Dutta, S. - \ 2004
Wageningen University. Promotor(en): Henk Folmer; Wim Heijman, co-promotor(en): A. Majumder. - Wageningen : Wageningen Universiteit - ISBN 9789085040460 - 371
ondernemerschap - plattelandsindustrie - plattelandsontwikkeling - west bengal - inkomsten van buiten het landbouwbedrijf - industrialisatie - armoede - cultuur - lineaire modellen - india - boeren - schatting - entrepreneurship - rural industry - rural development - west bengal - india - non-farm income - farmers - industrialization - poverty - culture - linear models - estimation
For a living, most of the rural people in developing countries are primarily dependent on agriculture. If the farmers, who have investible surplus generated from agriculture, are interested in non-farm entrepreneurship then rural economy can find an industrial route of development. With this consideration, the study has posed the research question as to what determines non-farm entrepreneurship among farmers and thus attempted to identify the factors that may influence farmer's non-farm entrepreneurship. The theoretical part constituted a set of 13 hypotheses which in turn led to formulation of two questionnaires in order to collect data—one questionnaire was for interviewing the farmers who were engaged in non-farm manufacturing activities and the other questionnaire was for interviewing the farmers who were engaged in farming only. So far as the investigation part of the study is concerned Bardhaman district of the state of West Bengal in India was selected because during 1980s and 1990s the state has experiencedhighagricultural growth compared to the previous decades, which implies that farmers might have been able to gather surplus generated from agricultural development and therefore it was considered interesting to study non-farm entrepreneurship of farmers of West Bengal Five administrative blocks were randomly selected from the eastern part (agricultural part) of Bardhaman district, and then six panchayats have been randomly selected from each block, and finally 10 farm households were randomly selected from each panchayat, i.e. totally 300 samples were randomly selected for interviews. The LISREL (LInear Structural RELations) approach was applied to estimate the model which was constituted in the form of simultaneous equations system that included a set of 10 equations (indicating interdependencies between the endogenous and explanatory variables) with a consideration of the hypotheses of the theoretical model; and we applied the LISREL approach, by using its maximum likelihood estimator, since this approach can control for simultaneity bias in the model, and simultaneously deal with latent variables and the observable variable or, as we may say, can simultaneously estimate the measurement model and the structural model. The farmers who are married, engaged in producing three crops year, and risk takers have been found to have a relatively high probability to become non-farm entrepreneurs. The farmers who are relatively wealthy and have high levels of education have been found to be less likely in becoming non-farm entrepreneurs whereas age of farmer has indirect positive impact on non-farm entrepreneurship via marriage and indirect negative impact on non-farm entrepreneurship via risk attitude and wealth. The number of children of a farmer has been found to have an insignificant effect on non-farm entrepreneurship, but interestingly non-farm entrepreneurship has been found to have a positive impact on the number of children. Three exogenous variables—viz. age squared, farmer's primary involvement in agriculture either as a landowner or as a sharecropper, and farmer's faith in work-effort or fate - have been found to be highly insignificant and therefore have been removed from the structural model. Three explanatory variables - viz. political affiliation of farmer, financial family support, marriage relation, and innovativeness - have also been found to have insignificant impacts on non-farm entrepreneurship.
Prototype van een dynamisch krachtvoer advies systeem voor melkvee
Duinkerken, G. van; André, G. ; Zom, R.L.G. - \ 2003
Lelystad : Praktijkonderzoek Veehouderij (PraktijkRapport / Animal Sciences Group, Praktijkonderzoek : Rundvee ) - 54
melkvee - melkveehouderij - rundveevoeding - concentraten - melkproductie - melkopbrengst - lineaire modellen - diervoeding - diervoedering - dairy cattle - dairy farming - cattle feeding - concentrates - milk production - milk yield - linear models - animal nutrition - animal feeding
Een zogenaamd dynamisch krachtvoeradvies houdt rekening met de individuele melkproductierespons van dieren op het opgenomen krachtvoer en benut daarmee de verschillen tussen dieren voor wat betreft de efficiëntie waarmee het (kracht)voer wordt benut. Daarbij wordt uitgegaan van de zogenaamde krachtvoercoëfficiënt, die aangeeft hoeveel kg melk extra is te verwachten indien van een bepaald dier de krachtvoeropname met één kg/dag stijgt. Ook houdt het dynamische model rekening met de variatie binnen de dieren als gevolg van veranderingen die tijdens de lactatie optreden. Het prototype dynamisch model bleek goed bruikbaar om schattingen te geven van zowel het basisniveau (van de melkgift) als de krachtvoercoëfficiënt. Zodoende is het mogelijk om goede voorspellingen te geven van de verwachte melkgift op korte termijn en daar een krachtvoeradvies aan te koppelen. Ook de monitoringfunctie van het model, waarbij onverwachte afwijkingen in de melkgift direct worden gesignaleerd en gemeld op basis waarvan de veehouder kan nagaan of er oorzaken voor de afwijkingen te vinden zijn, zoals bijvoorbeeld kreupelheid of tochtigheid van de betreffende koe, functioneerde goed in de uitgevoerde proef
Berekening samenstellingen van mengvoeders: lineaire versus niet-lineaire of stochastische methodiek
Roush, W.B. ; Zhang, Z. ; Home, P.L.M. van; Meijerhof, R. - \ 1997
Beekbergen : Praktijkonderzoek Pluimveehouderij (PP uitgave : praktijkonderzoek pluimveehouderij 67) - 23
mengvoer - voersamenstelling - voedertabellen - berekening - lineaire modellen - stochastische modellen - compound feeds - feed formulation - feed composition tables - calculation - linear models - stochastic models
Voor het samenstellen van mengvoer wordt over het algemeen gebruik gemaakt van lineaire programmering. Naast lineaire programmering is recentelijk de stochastische of niet-lineaire programmering beschikbaar gekomen.
Een computerprogramma voor het bepalen van de optimale ligging van drie lijnstukken door een serie getallenparen
Wesseling, J.G. - \ 1981
Wageningen : I.C.W. (Nota / Instituut voor Cultuurtechniek en Waterhuishouding 1313) - 34
computer software - toepassingen - kleinste kwadraten - interpolatie - numerieke methoden - optimalisatiemethoden - lineaire modellen - computer software - applications - least squares - interpolation - numerical methods - optimization methods - linear models
Een vaak voorkomend probleem in het onderzoek is dat men uit een serie metingen een aantal paren waarnemingen heeft verkregen. In de meeste gevallen zullen deze paren door één of meerdere rechte lijnen kunnen worden benaderd. Het is natuurlijk mogelijk om 'op het oog' een rechte lijn door de paren punten te trekken, twee punten van deze lijn te nemen en hieruit de vergelijking van die lijn te bepalen. Dit blijkt in de praktijk nogal eens tot verschillende numerieke oplossingen te leiden, vooral indien de uitkomsten gespreid liggen. De belangstelling voor het numeriek bepalen van de 'best fit' wordt steeds groter. Hiermee komen we op het terrein van de optimalisatie van parameters. Deze nota beschrijft één van de vele mogelijkheden voor het oplossen van zo'n probleem: de methode van Fletcher-Reeves. Na een korte probleembeschrijving zal worden ingegaan op enkele oplossingsmethoden, die algemeen worden gebruikt. Vervolgens zal in het kort de methode van Fletcher-Reeves worden besproken. Het computerprogramma FLETCH zal worden beschreven met enkele toepassingen van dit programma.