Advocates of privatizing education suggest that traditional public schools are not adequately preparing students for college, career readiness, and global citizenship (Lobosco, 2019; Schneider and Berkshire, 2020; Tienken and Mullen, 2016). Charter school supporters believe charter school students perform better than public school children on state standardized tests (Lubienski and Lubienski, 2014). Advocates for traditional public schools promote the idea that there are no significant differences between public and charter schools in academic achievement (Chen, 2020b; Fischler, 2021). This study compares public and charter elementary school students in terms of their reading and math assessment scores, both as measured by the Virginia Standard of Learning (SOL) for the 2018-2019 school year. Data were collected and analyzed on 642 students enrolled in three of Virginia's elementary charter schools and three traditional public schools in Loudoun County and Richmond City. SOL assessment data for the public and charter schools were compared for the overall student population per grade level to determine if there is a significant difference for the 2018-2019 school year. A two-way ANOVA was utilized in this study. Results indicated no significant differences in the reading mean SOL assessment scores between traditional public elementary and public charter school students: F (1, 636) = .119, p = .730. Additionally, results showed no significant interaction between school type and grade level between traditional public elementary and public charter schools: F (2, 636) = 1.076, p = .342. However, findings revealed a significant difference in the reading SOL assessment scores between grade levels of traditional public elementary schools and public charter schools: F (2, 636) = 4.473, p = .012. Furthermore, results from the math analysis indicated no statistical differences in math SOL scores between traditional public elementary schools and public charter schools: F (1, 636) = .000, p = .997. Also, findings indicated no significant difference in the math SOL scores between the grade levels of traditional public elementary and public charter schools: F (2, 636) = .520, p = .595. / Doctor of Education / Advocates of privatizing education suggest that traditional public "brick-and-mortar" schools are not adequately preparing students for college, career readiness, and global citizenship (Lobosco, 2019; Tienken and Mullen, 2016; Schneider and Berkshire, 2020). Charter school supporters believe charter school students perform better than public school children on state standardized tests (Lubienski and Lubienski, 2014). Advocates for traditional public schools promote the idea that there are no significant differences between public and charter schools in academic achievement (Chen, 2020b; Fischler, 2021). This study compares public and charter elementary school students in terms of their reading and math assessment scores, both as measured by the Virginia Standard of Learning (SOL) for the 2018-2019 school year. Data were collected and analyzed on 642 students enrolled in three of Virginia's elementary charter schools and three traditional public schools in Loudoun County and Richmond City. SOL assessment data for the public and charter schools were compared for the overall student population per grade level to determine if there is a significant difference for the 2018-2019 school year. This study did not reveal any significant differences in reading and math SOL scores between traditional elementary public schools and public elementary charter schools. However, findings in this study revealed significant differences in reading SOL scores on average among grade levels. Conversely, findings did not reveal any differences in math SOL assessment scores on average between grade levels of traditional public elementary school and public elementary charter school students.

L'objectif de cette thèse est l'investigation de nouvelles méthodes de surface de réponse afin de réaliser l'analyse de sensibilité de modèles numériques complexes et coûteux en temps de calcul. Pour ce faire, nous nous sommes intéressés aux méthodes basées sur la décomposition ANOVA. Nous avons proposé l'utilisation d'une méthode basée sur les splines de lissage de type ANOVA, alliant procédures d'estimation et de sélection de variables. L'étape de sélection de variable peut devenir très coûteuse en temps de calcul, particulièrement dans le cas d'un grand nombre de paramètre d'entrée. Pour cela nous avons développé un algorithme de seuillage itératif dont l'originalité réside dans sa simplicité d'implémentation et son efficacité. Nous avons ensuite proposé une méthode directe pour estimer les indices de sensibilité. En s'inspirant de cette méthode de surface de réponse, nous avons développé par la suite une méthode adaptée à l'approximation de modèles très irréguliers et discontinus, qui utilise une base d'ondelettes. Ce type de méthode a pour propriété une approche multi-résolution permettant ainsi une meilleure approximation des fonctions à forte irrégularité ou ayant des discontinuités. Enfin, nous nous sommes penchés sur le cas où les sorties du simulateur sont des séries temporelles. Pour ce faire, nous avons développé une méthodologie alliant la méthode de surface de réponse à base de spline de lissage avec une décomposition en ondelettes. Afin d'apprécier l'efficacité des méthodes proposées, des résultats sur des fonctions analytiques ainsi que sur des cas d'ingénierie de réservoir sont présentées. / The purpose of this thesis is to investigate innovative response surface methods to address the problem of sensitivity analysis of complex and computationally demanding computer codes. To this end, we have focused our research work on methods based on ANOVA decomposition. We proposed to use a smoothing spline nonparametric regression method, which is an ANOVA based method that is performed using an iterative algorithm, combining an estimation procedure and a variable selection procedure. The latter can become computationally demanding when dealing with high dimensional problems. To deal with this, we developed a new iterative shrinkage algorithm, which is conceptually simple and efficient. Using the fact that this method is an ANOVA based method, it allows us to introduce a new method for computing sensitivity indices. Inspiring by this response surface method, we developed a new method to approximate the model for which the response involves more complex outputs. This method is based on a multiresolution analysis with wavelet decompositions, which is well known to produce very good approximations on highly nonlinear or discontinuous models. Finally we considered the problem of approximating the computer code when the outputs are times series. We proposed an original method for performing this task, combining the smoothing spline response surface method and wavelet decomposition. To assess the efficiency of the developed methods, numerical experiments on analytical functions and reservoir engineering test cases are presented.

Dans les domaines de la modélisation et de la simulation numérique, les simulateurs développés prennent parfois en compte de nombreux paramètres dont l'impact sur les sorties n'est pas toujours bien connu. L'objectif principal de l'analyse de sensibilité est d'aider à mieux comprendre comment les sorties d'un modèle sont sensibles aux variations de ces paramètres. L'approche la mieux adaptée pour appréhender ce problème dans le cas de modèles potentiellement complexes et fortement non linéaires repose sur la décomposition ANOVA et les indices de Sobol'. En particulier, ces derniers permettent de quantifier l'influence de chacun des paramètres sur la réponse du modèle. Dans cette thèse, nous nous intéressons au problème de l'estimation des indices de Sobol'. Dans une première partie, nous réintroduisons de manière rigoureuse des méthodes existantes au regard de l'analyse harmonique discrète sur des groupes cycliques et des tableaux orthogonaux randomisés. Cela nous permet d'étudier les propriétés théoriques de ces méthodes et de les généraliser. Dans un second temps, nous considérons la méthode de Monte Carlo spécifique à l'estimation des indices de Sobol' et nous introduisons une nouvelle approche permettant de l'améliorer. Cette amélioration est construite autour des hypercubes latins et permet de réduire le nombre de simulations nécessaires pour estimer les indices de Sobol' par cette méthode. En parallèle, nous mettons en pratique ces différentes méthodes sur un modèle d'écosystème marin. / In the fields of modelization and numerical simulation, simulators generally depend on several input parameters whose impact on the model outputs are not always well known. The main goal of sensitivity analysis is to better understand how the model outputs are sensisitive to the parameters variations. One of the most competitive method to handle this problem when complex and potentially highly non linear models are considered is based on the ANOVA decomposition and the Sobol' indices. More specifically the latter allow to quantify the impact of each parameters on the model response. In this thesis, we are interested in the issue of the estimation of the Sobol' indices. In the first part, we revisit in a rigorous way existing methods in light of discrete harmonic analysis on cyclic groups and randomized orthogonal arrays. It allows to study theoretical properties of this method and to intriduce generalizations. In a second part, we study the Monte Carlo method for the Sobol' indices and we introduce a new approach to reduce the number of simulations of this method. In parallel with this theoretical work, we apply these methods on a marine ecosystem model.

Esta dissertação apresenta um método adaptado do estudo de repetitividade e reprodutibilidade para analisar a capacidade e o desempenho de sistemas de medição, no contexto da análise de dados funcionais. Dado funcional é a variável de resposta dada por uma coleção de dados que formam um perfil ou uma curva. O método adaptado contribui para o avanço do estado da arte sobre a análise de sistemas de medição. O método proposto é uma alternativa ao uso de métodos tradicionais de análise, que usados de forma equivocada, podem deteriorar a qualidade dos produtos monitorados através de variáveis de resposta funcionais. O método proposto envolve a adaptação de testes de hipótese e da análise de variância de um e dois fatores usados em comparações de populações, na avaliação de sistemas de medições. A proposta de adaptação foi baseada na utilização de distâncias entre curvas. Foi usada a Distância de Hausdorff como uma medida de proximidade entre as curvas. A adaptação proposta à análise de variância foi composta de três abordagens. Os métodos adaptados foram aplicados a um estudo simulado de repetitividade e reprodutibilidade. O estudo foi estruturado para analisar cenários em que o sistema de medição foi aprovado e reprovado. O método proposto foi denominado de ANOVA das Distâncias. / This work presents a method to analyze a measurement system's performance in a functional data analysis context, based on repeatability and reproducibility studies. Functional data are a collection of data points organized as a profile or curve. The proposed method contributes to the state of the art on measurement system analysis. The method is an alternative to traditional methods often used mistakenly, leading to deterioration in the quality of products monitored through functional responses. In the proposed method we adapt hypothesis tests and one-way and two-way ANOVA to be used in measurement system analysis. The method is grounded on the use of distances between curves. For that matter the Hausdorff distance was chosen as a measure of proximity between curves. Three ANOVA approaches were proposed and applied in a simulated repeatability and reproducibility study. The study was structured to analyze scenarios in which the measurement system was approved or rejected. The proposed method was named ANOVA of the distances.

Esta dissertação apresenta um método adaptado do estudo de repetitividade e reprodutibilidade para analisar a capacidade e o desempenho de sistemas de medição, no contexto da análise de dados funcionais. Dado funcional é a variável de resposta dada por uma coleção de dados que formam um perfil ou uma curva. O método adaptado contribui para o avanço do estado da arte sobre a análise de sistemas de medição. O método proposto é uma alternativa ao uso de métodos tradicionais de análise, que usados de forma equivocada, podem deteriorar a qualidade dos produtos monitorados através de variáveis de resposta funcionais. O método proposto envolve a adaptação de testes de hipótese e da análise de variância de um e dois fatores usados em comparações de populações, na avaliação de sistemas de medições. A proposta de adaptação foi baseada na utilização de distâncias entre curvas. Foi usada a Distância de Hausdorff como uma medida de proximidade entre as curvas. A adaptação proposta à análise de variância foi composta de três abordagens. Os métodos adaptados foram aplicados a um estudo simulado de repetitividade e reprodutibilidade. O estudo foi estruturado para analisar cenários em que o sistema de medição foi aprovado e reprovado. O método proposto foi denominado de ANOVA das Distâncias. / This work presents a method to analyze a measurement system's performance in a functional data analysis context, based on repeatability and reproducibility studies. Functional data are a collection of data points organized as a profile or curve. The proposed method contributes to the state of the art on measurement system analysis. The method is an alternative to traditional methods often used mistakenly, leading to deterioration in the quality of products monitored through functional responses. In the proposed method we adapt hypothesis tests and one-way and two-way ANOVA to be used in measurement system analysis. The method is grounded on the use of distances between curves. For that matter the Hausdorff distance was chosen as a measure of proximity between curves. Three ANOVA approaches were proposed and applied in a simulated repeatability and reproducibility study. The study was structured to analyze scenarios in which the measurement system was approved or rejected. The proposed method was named ANOVA of the distances.

Esta dissertação apresenta um método adaptado do estudo de repetitividade e reprodutibilidade para analisar a capacidade e o desempenho de sistemas de medição, no contexto da análise de dados funcionais. Dado funcional é a variável de resposta dada por uma coleção de dados que formam um perfil ou uma curva. O método adaptado contribui para o avanço do estado da arte sobre a análise de sistemas de medição. O método proposto é uma alternativa ao uso de métodos tradicionais de análise, que usados de forma equivocada, podem deteriorar a qualidade dos produtos monitorados através de variáveis de resposta funcionais. O método proposto envolve a adaptação de testes de hipótese e da análise de variância de um e dois fatores usados em comparações de populações, na avaliação de sistemas de medições. A proposta de adaptação foi baseada na utilização de distâncias entre curvas. Foi usada a Distância de Hausdorff como uma medida de proximidade entre as curvas. A adaptação proposta à análise de variância foi composta de três abordagens. Os métodos adaptados foram aplicados a um estudo simulado de repetitividade e reprodutibilidade. O estudo foi estruturado para analisar cenários em que o sistema de medição foi aprovado e reprovado. O método proposto foi denominado de ANOVA das Distâncias. / This work presents a method to analyze a measurement system's performance in a functional data analysis context, based on repeatability and reproducibility studies. Functional data are a collection of data points organized as a profile or curve. The proposed method contributes to the state of the art on measurement system analysis. The method is an alternative to traditional methods often used mistakenly, leading to deterioration in the quality of products monitored through functional responses. In the proposed method we adapt hypothesis tests and one-way and two-way ANOVA to be used in measurement system analysis. The method is grounded on the use of distances between curves. For that matter the Hausdorff distance was chosen as a measure of proximity between curves. Three ANOVA approaches were proposed and applied in a simulated repeatability and reproducibility study. The study was structured to analyze scenarios in which the measurement system was approved or rejected. The proposed method was named ANOVA of the distances.

In research where experiments on humans and animals is performed, it is in advance important to determine how many observations that is needed in a study to detect any effects in groups and to save time and costs. This could be examined by power analysis, in order to determine a sample size which is enough to detect any effects in a study, a so called “power”. Power is the probability to reject the null hypothesis when the null hypothesis is false. Mälardalen University and the Caroline Institute have in cooperation, formed a study (The Climate Friendly and Ecological Food on Microbiota) based on individual’s dietary intake. Every single individual have been assigned to a specific diet during 8 weeks, with the purpose to examine whether emissions of carbon dioxide, CO2, differs reliant to the specific diet each individuals follows. There are two groups, one treatment and one control group. Individuals assigned to the treatment group are supposed to follow a climatarian diet while the individuals in the control group follows a conventional diet. Each individual have been followed up during 8 weeks in total, with three different measurements occasions, 4 weeks apart. The different measurements are Baseline assessment, Midline assessment and End assessment. In the CLEAR-study there are a total of 18 individuals, with 9 individuals in each group. The amount of individuals are not enough to reach any statistical significance in a test and therefore the sample size shall be examined through power analysis. In terms of, data, every individual have three different measurements occasions that needs to be modeled through mixed-design ANOVA and linear mixed models. These two methods takes into account, each individual’s different measurements. The models which describes data are applied in the computations of sample sizes and power. All the analysis are done in the programming language R with means and standard deviations from the study and the models as a base. Sample sizes and power have been computed for two different linear mixed models and one ANOVA model. The linear mixed models required less individuals than ANOVA in terms of a desired power of 80 percent. 24 individuals in total were required by the linear mixed model that had the factors group, time, id and the covariate sex. 42 individuals were required by ANOVA that includes the variables id, group and time. / Inom forskning där försök, dels utförs på människor och djur, vill man försäkra sig om en lämplig urvalsstorlek för att spara tid och kostnad samtidigt som en önskad statistisk styrka uppnås. Mälardalens högskola och Karolinska institutet har gjort en pilotstudie (CLEAR) som undersöker människors koldioxidutsläpp i förhållande till kosthållning. Varje individ i studien har fått riktlinjer om att antingen följa en klimatvänlig- eller en konventionell kosthållning i totalt 8 veckor. Individerna följs upp med 4 veckors mellanrum, vilket har resulterat i tre mättillfällen, inklusive en baslinjemätning. I CLEAR-studien finns variabler om individernas kön, ålder, kosthållning samt intag av makro- och mikronäringsämnen. Nio individer i respektive grupp finns, där grupperna är klimat- och kontrollgruppen. Totala antalet individer i pilotstudien är för få för att erhålla statistisk signifikans vid statistiska tester och därför bör urvalsstorleken undersökas genom att göra styrkeberäkningar. Styrkan som beräknas är sannolikheten att förkasta nollhypotesen när den är falsk. För att kunna beräkna urvalsstorlekar måste modeller skapas utifrån strukturen på data, vilket kommer att göras med metoderna mixed-design ANOVA och linjära mixade modeller. Metoderna tar hänsyn till att varje individ har fler än en mätning. Modellerna som beskriver data tillämpas i beräkningarna av styrka. Urvalsstorlekarna och styrkan som beräknats är simuleringsbaserad och har analyserats i programspråket R med modellerna och värden från pilotstudien som grund. Styrka och urvalsstorlekar har beräknats för två linjära mixade modeller och en ANOVA. De linjära mixade modellerna kräver färre individer än ANOVA för en önskad styrka på 80 procent. Av de linjära mixade modellerna som krävde minst individer behövdes totalt 24 individer medan mixed design-ANOVA krävde 42 individer totalt.

Les alliages Al-Si sont largement utilisés dans l’industrie automobile en fonderie sous pression, en particulier pour la fabrication des blocs moteurs, en raison de leurs bon rapport résistance/ poids et leurs excellentes propriétés mécaniques. Du fait de l’internationalisation de la production, la composition chimique de ces alliages et les paramètres du procédé HPDC peuvent varier d’un pays à l’autre, ils peuvent même varier d’un site de fabrication à l’autre dans le même pays. Or, les conceptions des pièces automobiles sont aujourd’hui de type déterministe et elles sont réalisées sur la base des matériaux et procédés européens, ce qui peut affecter les propriétés de ces pièces dans le cas d’une localisation hors Europe. Ainsi, il est important de pouvoir adapter les conceptions rapidement et à moindre coût en prenant en compte les contraintes matériau/ process locales. Dans cette thèse, nous avons proposé une approche méthodologique permettant de prédire les caractéristiques mécaniques en fonction de la variabilité matériaux/ process en s'appuyant sur une étude expérimentale/ statistique de l’effet de la variabilité des principaux éléments d’alliage (Si, Cu, Mg) et des paramètres procédé (température de la coulée et pression d’injection) sur les propriétés mécaniques des alliages d’Al-Si moulés sous pression. La microstructure et le taux de porosités ont également été évalués. Cette méthodologie a abouti à la construction d’un outil de conception produit permettant de prédire les caractéristiques mécaniques dans le cas du changement de l’un (ou des) paramètres Matériau/ Process. / Secondary Al-Si alloys are widely used in automotive industry for engine blocks because they offer a considerable weight reduction whilst maintaining good mechanical properties. The ever-expanding internationalisation of production, with same stages of production processes spread across a number of countries to produce locally, causes however high variability in the casting products. The chemical composition of the same alloys and the working variables of the unchanged high-pressure die casting process (HPDC) may change for the same casting parts from one country to another, they can even sometimes vary from one manufacturing site to another within the same country. Designing for aluminium automotive components does call today for new deterministic design methods that are often achieved from European material and casting process databases, which can affect the properties of these parts in the case of a location outside Europe. Thus, it is important to adapt the design of die casting parts quickly and inexpensively by taking into account the material and process local constraints. In this work, a methodological approach which permits to predict mechanical properties as a function of material and process variability based on an experimental/ statistical study on the effect of the variability of the primary factors of alloying elements contents (Si, Cu and Mg) and HPDC process parameters (casting temperature and injection pressure) on mechanical properties of die cast aluminium alloys has been proposed. The microstructural features and the porosity level were also investigated and assessed. This approach has resulted in statistical design tool that will allow designers to make changes to the design of their casting and to industrialize them outside Europe.

GNSS-teknik ersätter i allt högre grad terrester mätteknik, dels på grund av sin enkelhet och dels på grund av att den är mindre kostsam än traditionella metoder. En vanlig förekommande GNSS-teknik är RTK (Real Time Kinematic) som är en teknik som beräknar en position i realtid genom bärvågsmätning. Inom RTK-mätning finns det olika tekniker att utöva; enkelstations-RTK (ERTK) och nätverks-RTK (NRTK). I studien undersöktes kvaliteten och lägesosäkerhet på höjdbestämningsdata erhållen från dessa metoder. En envägs variansanalys (ANOVA) användes för att undersöka om det fanns en signifikant skillnad mellan de genomsnittliga avvikelser som erhölls från mätmetoderna. Mätmetoderna utfördes över två punkter med känd höjd som fastställdes tidigare med ett dubbelavvägningståg. ERTK och NRTK varvades med en observationstid på 20 minuter med positioneringsintervall på 3 sekunder. Tidseparationen mellan mätningarna varade i 30 minuter och sammanlagt utfördes 5 mätserier med 400 observationer i varje serie. Grova fel eliminerades genom att kassera värden som föll utanför 3σ-gränsen. Resultaten från ERTK-mätningarna visade att punkten kunde höjdbestämmas med en lägesosäkerhet på 22 mm och en mätosäkerhet på 32 mm (2σ) för samtliga mätserier tillsammans. Internt varierade lägesosäkerheten 13–28 mm mellan serierna. NRTK mätningarna erhöll en total lägesosäkerhet på 14 mm och en mätosäkerhet på 24 mm (2σ). Från enskilda mätserier erhöll serie 3 den lägsta lägesosäkerheten på 9 mm, och serie 4 den högsta med 18 mm. Generellt visade NRTK-metoden lägre och jämnare avvikelser från referensdata än ERTK, resultatet kan dock ha blivit påverkat av basens läge i relation till ett närliggande träd. ANOVA-testet visade att det fanns en signifikant skillnad mellan mätserierna (p =0,00) per enskild metod, men skillnaden av medelavvikelserna mellan dessa metoder var inte signifikanta (p =0,115). Resultatet från denna studie är viktig med avseende på kvalitetsutvärdering av olika GNSS-metoder och kan användas som underlag för beslut om tillämpad metod för andra mätuppdrag. / A quality survey was performed on the position accuracy of two GNSS-methods (single station-RTK and network-RTK) for height determination, and a one-way analysis of variance (ANOVA) was used for statistical investigation of differences in the spread of height deviations. The GNSS-methods were applied on a reference point, which was determined prior with leveling, and measured with 20 minutes observation time and 30 minutes time separation, resulting in 5 series containing 400 observations each from respective method. The ANOVA test was performed by grouping the height deviations with respect to the measurement series, as well as the mean deviations with respect to the methods. Height determination with the ERTK method showed a total positional uncertainty of 22 mm (13-28 mm between the series) and a measurement uncertainty of 32 mm (2σ). Results obtained with NRTK showed a total positional uncertainty of 14 mm (9-14 between the series) and a total measurement uncertainty of 24 mm (2σ). The statistical tests showed that the differences between the measurement series for individual methods were significant (p = 0,000) but that the mean deviations between the methods were not (p = 0,115). NRTK obtained a lower positional uncertainty than ERTK measurements in this study, and the ANOVA test showed that there was no significant difference in the distribution of the mean deviations between the measurement methods. This study is important with regard to quality evaluation of different GNSS-methods and can be used as a basis for deciding on the applied measurement method.

Temas relacionados ao desenvolvimento de novos materiais têm sido cada vez mais abordados e discutidos, num contexto em que questões como meio ambiente, sociedade, economia de energia e aproveitamento de resíduos, vêm se tornando relevantes. Neste cenário, faz-se necessário estudar aplicações de insumos alternativos na produção de pisos de madeira, tanto para reduzir o consumo de essências tropicais quanto para suprir o aumento da demanda de madeira nas indústrias deste segmento. O objetivo deste estudo foi produzir painéis de partículas homogêneos de alta densidade, com resíduos de madeira de Pinus elliottii e casca de aveia (Avena sativa), aderidos sob pressão com dois tipos de adesivo, poliuretano à base de óleo de mamona e melamina formaldeído, nos percentuais de 11 e 13%, e avaliar o desempenho físico-mecânico de tais painéis para aplicação em pisos. O desempenho físico-mecânico dos painéis (Planejamento I - 20 tratamentos) foi avaliado com base nas normas ABNT NBR 14810 (2006 e 2013). Realizou-se análise de variância (ANOVA) para testar a influência dos fatores individuais (percentual de casca de aveia, percentual de adesivo e tipo de adesivo), além das interações entre tais fatores (dois a dois e três a três) nas propriedades físico-mecânicas dos painéis. Também foi avaliado o desempenho para pisos, tanto dos painéis (Planejamento II - 12 tratamentos) quanto de três espécies de madeira tropical (Angelim Vermelho, Dinizia excelsa; Cumaru, Dipteryx odorata e Jatobá, Hymenaea sp.), segundo diversas normas relacionadas a pisos de madeira. Os resultados apontaram propriedades físico-mecânicas dos painéis, em alguns tratamentos superiores aos requisitos estipulados por normas nacionais e internacionais. Quanto ao desempenho para pisos, os painéis apresentaram desempenho semelhante as três espécies de madeira, na maioria das propriedades avaliadas. A análise de porosimetria por intrusão de mercúrio confirmou a similaridade entre os painéis (do Planejamento II) e as três espécies de madeira avaliadas, evidenciando a potencialidade dos painéis produzidos para aplicação na indústria de pisos engenheirados. / Matters related to the development of new materials have been increasingly addressed and discussed in a context where issues such as the environment, society, energy and waste recovery economy, is becoming relevant. In this scenario, it is necessary to study alternative inputs for applications in the production of wood floors, both to reduce the consumption of tropical essences as to meet the increasing demand for wood in industries in this segment. The aim this study was to produce high density homogeneous particleboard with waste wood of Pinus elliottii and oat hulls (Avena sativa), adhered under pressure with two types of adhesive, castor oil-based polyurethane and melamine formaldehyde, the percentage of 11 and 13%, and evaluate the physical and mechanical performance of such panels for use in floors. The physical-mechanical performance of the panels (Planning I - 20 treatments) was evaluated based on the NBR 14810 (2006 and 2013) standards. We conducted an analysis of variance (ANOVA) to evaluate the influence of individual factors (oat hulls percentage, adhesive percentage and type of adhesive), and the interactions between these factors (two by two and three by three) on the physical properties-mechanical panels. It was also evaluated the performance for floors, both panels (Planning II - 12 treatments) as three species of tropical wood (Angelim Vermelho, Dinizia excelsa; Cumaru, Dipteryx odorata e Jatobá, Hymenaea sp.), according to various standards related to wood floors. The results indicated physical and mechanical properties of the panels, in some treatments superior to the requirements stipulated by national and international standards. As for performance flooring, panels statistically equivalent to the three species of wood, most of the evaluated properties. Porosimetry analysis by mercury intrusion confirmed the similarity between the panels (from Planning II) and the three wood species evaluated, demonstrating the potential of the panels produced for use in the flooring industry engineered.