The purpose of this research was to evaluate the effect on parametric and nonparametric tests using ordinal data when the distances between points changed on the measurement scale. The research examined the performance of Type I and Type II error rates using selected parametric and nonparametric tests.

The coastal zone of Belize is home to the largest recorded number of the threatened Antillean manatee (Trichechus manatus manatus) within the species' Caribbean range. The objectives of my study were: (1) to determine long-term trends in aerial survey counts and indices of the manatee population in the coastal zone of Belize; and (2) to examine the seasonal change in manatee distribution among habitats in the coastal zone. Standardized extended-area aerial surveys were conducted along the entire coastline of Belize in the dry and wet seasons of 1997, and 1999 - 2002. Manatees were counted in five habitat categories: cay, coast, estuary, lagoon, and river. Total sightings per survey ranged from 90 to 338; the greatest number was counted in the 2002 wet season. Calf percentage ranged from 5 to 13. A slight negative trend in total counts was significant for dry-season, not wet-season surveys, indicating an interactive effect of season and year. Based on analysis of variance, the Abundance Index (transformed manatee sightings per hour) did not differ significantly among years, although it varied significantly within year by season and habitat by season. In applying a spatial approach, the general survey route was buffered 1 km on both sides, and 1 km grids were overlaid and classified by habitat type. The presence or absence of each cell for each survey was used in likelihood ratio tests of the single and interactive effect of season and habitat. The Index for river habitat was higher in the dry season, while cay habitat was higher in the wet season. Overall, near-shore habitat (estuary, lagoon, and river) showed a higher Index than did the offshore habitat (cay and coast) although the total number of sightings was higher offshore. Considering the interactive effect of year, season, and habitat, long-term studies are needed, in both seasons, and among all habitats to account for variation. Continued broad-scale surveys, along with metapopulation analysis would fine-tune the understanding of specific sites, enhancing integrated coastal zone management for protected species and their habitat systems.

In Part 1 of this paper, we adapt Turnbull¡¦s algorithm to estimate the distribution function of univariate interval-censored and truncated failure time data. We also propose four non-parametric tests to test whether two groups of the data come from the same distribution. The powers of proposed test statistics are compared by simulation under different distributions. The proposed tests are then used to analyze an AIDS study. In Part 2, for bivariate interval-censored data, we propose some models of how to generate the data and several methods to measure the correlation between the two variates. We also propose several nonparametric tests to determine whether the two variates are mutually independent or whether they have the same distribution. We demonstrate the performance of these tests by simulation and give an application to AIDS study¡]ACTG 181¡^.

The coastal zone of Belize is home to the largest recorded number of the threatened Antillean manatee (Trichechus manatus manatus) within the species' Caribbean range. The objectives of my study were: (1) to determine long-term trends in aerial survey counts and indices of the manatee population in the coastal zone of Belize; and (2) to examine the seasonal change in manatee distribution among habitats in the coastal zone. Standardized extended-area aerial surveys were conducted along the entire coastline of Belize in the dry and wet seasons of 1997, and 1999 - 2002. Manatees were counted in five habitat categories: cay, coast, estuary, lagoon, and river. Total sightings per survey ranged from 90 to 338; the greatest number was counted in the 2002 wet season. Calf percentage ranged from 5 to 13. A slight negative trend in total counts was significant for dry-season, not wet-season surveys, indicating an interactive effect of season and year. Based on analysis of variance, the Abundance Index (transformed manatee sightings per hour) did not differ significantly among years, although it varied significantly within year by season and habitat by season. In applying a spatial approach, the general survey route was buffered 1 km on both sides, and 1 km grids were overlaid and classified by habitat type. The presence or absence of each cell for each survey was used in likelihood ratio tests of the single and interactive effect of season and habitat. The Index for river habitat was higher in the dry season, while cay habitat was higher in the wet season. Overall, near-shore habitat (estuary, lagoon, and river) showed a higher Index than did the offshore habitat (cay and coast) although the total number of sightings was higher offshore. Considering the interactive effect of year, season, and habitat, long-term studies are needed, in both seasons, and among all habitats to account for variation. Continued broad-scale surveys, along with metapopulation analysis would fine-tune the understanding of specific sites, enhancing integrated coastal zone management for protected species and their habitat systems.

Masters of Science / The multivariate two-sample tests provide a means to test the match between two multivariate distributions. Although many tests exist in the literature, relatively little is known about the relative power of these procedures. The studies reported in the thesis contrasts the effectiveness, in terms of power, of seven such tests with a Monte Carlo study. The relative power of the tests was investigated against location, scale, and correlation alternatives. Samples were drawn from bivariate exponential, normal and uniform populations. Results from the power studies show that there is no single test which is the most powerful in all situations. The use of particular test statistics is recommended for specific alternatives. A possible supplementary non-parametric graphical procedure, such as the Depth-Depth plot, can be recommended for diagnosing possible differences between the multivariate samples, if the null hypothesis is rejected. As an example of the utility of the procedures for real data, the multivariate two-sample tests were applied to photometric data of twenty galactic globular clusters. The results from the analyses support the recommendations associated with specific test statistics.

Résumé : Il est bien connu que les lois marginales d'un vecteur aléatoire ne suffisent pas à caractériser sa distribution. Lorsque les lois marginales du vecteur aléatoire sont continues, le théorème de Sklar garantit l'existence et l'unicité d'une fonction appelée copule, caractérisant la dépendance entre les composantes du vecteur. La loi du vecteur aléatoire est parfaitement définie par la donnée des lois marginales et de la copule. Dans ce travail de thèse, nous proposons deux tests non paramétriques de détection de ruptures dans la distribution d’observations multivariées, particulièrement sensibles à des changements dans la copule des observations. Ils améliorent tous deux des propositions récentes et donnent lieu à des tests plus puissants que leurs prédécesseurs pour des classes d’alternatives pertinentes. Des simulations de Monte Carlo illustrent les performances de ces tests sur des échantillons de taille modérée. Le premier test est fondé sur une statistique à la Cramér-von Mises construite à partir du processus de copule empirique séquentiel. Une procédure de rééchantillonnage à base de multiplicateurs est proposée pour la statistique de test ; sa validité asymptotique sous l’hypothèse nulle est démontrée sous des conditions de mélange fort sur les données. Le second test se focalise sur la détection d’un changement dans le rho de Spearman multivarié des observations. Bien que moins général, il présente de meilleurs résultats en terme de puissance que le premier test pour les alternatives caractérisées par un changement dans le rho de Spearman. Deux stratégies de calcul de la valeur p sont comparées théoriquement et empiriquement : l’une utilise un rééchantillonnage de la statistique, l’autre est fondée sur une estimation de la loi limite de la statistique de test. // Abstract : It is very well-known that the marginal distributions of a random vector do not characterize the distribution of the random vector. When the marginal distributions are continuous, the work of Sklar ensures the existence and uniqueness of a function called copula which can be regarded as capturing the dependence between the components of the random vector. The cumulative distribution function of the vector can then be rewritten using only the copula and the marginal cumulative distribution functions. In this work, we propose two non-parametric tests for change-point detection, particularly sensitive to changes in the copula of multivariate time series. They improve on recent propositions and are more powerful for relevant alternatives involving a change in the copula. The finite-sample behavior of these tests is investigated through Monte Carlo experiments. The first test is based on a Cramér-von Mises statistic and on the sequential empirical copula process. A multiplier resampling scheme is suggested and its asymptotic validity under the null hypothesis is demonstrated under strong mixing conditions. The second test focuses on the detection of a change in Spearman’s rho. Monte Carlo simulations reveal that this test is more powerful than the first test for alternatives characterized by a change in Spearman’s rho. Two approaches to compute approximate p-values for the test are studied empirically and theoretically. The first one is based on resampling, the second one consists of estimating the asymptotic null distribution of the test statistic.

Il est bien connu que les lois marginales d'un vecteur aléatoire ne susent pas à caractériser sa distribution. Lorsque les lois marginales du vecteur aléatoire sont continues, le théorème de Sklar garantit l'existence et l'unicité d'une fonction appelée copule, caractérisant la dépendance entre les composantes du vecteur. La loi du vecteur aléatoire est parfaitement dénie par la donnée des lois marginales et de la copule. Dans ce travail de thèse, nous proposons deux tests non paramétriques de détection de ruptures dans la distribution d'observations multivariées, particulièrement sensibles à des changements dans la copule des observations. Ils améliorent tous deux des propositions récentes et donnent lieu à des tests plus puissants que leurs prédécesseurs pour des classes d'alternatives pertinentes. Des simulations de Monte Carlo illustrent les performances de ces tests sur des échantillons de taille modérée. Le premier test est fondé sur une statistique à la Cramér-von Mises construite à partir du processus de copule empirique séquentiel. Une procédure de rééchantillonnage à base de multiplicateurs est proposée pour la statistique de test ; sa validité asymptotique sous l'hypothèse nulle est démontrée sous des conditions de mélange fort sur les données. Le second test se focalise sur la détection d'un changement dans le rho de Spearman multivarié des observations. Bien que moins général, il présente de meilleurs résultats en terme de puissance que le premier test pour les alternatives caractérisées par un changement dans le rho de Spearman. Deux stratégies de calcul de la valeur p sont comparées théoriquement et empiriquement : l'une utilise un rééchantillonnage de la statistique, l'autre est fondée sur une estimation de la loi limite de la statistique de test. / It is very well-known that the marginal distributions of a random vector do not characterize the distribution of the random vector. When the marginal distributions are continuous, the work of Sklar ensures the existence and uniqueness of a function called copula which can be regarded as capturing the dependence between the components of the random vector. The cumulative distribution function of the vector can then be rewritten using only the copula and the marginal cumulative distribution functions. In this work, we propose two non-parametric tests for change-point detection, particularly sensitive to changes in the copula of multivariate time series. They improve on recent propositions and are more powerful for relevant alternatives involving a change in the copula. The finite-sample behavior of these tests is investigated through Monte Carlo experiments. The first test is based on a Cramér-von Mises statistic and on the sequential empirical copula process. A multiplier resampling scheme is suggested and its asymptotic validity under the null hypothesis is demonstrated under strong mixing conditions. The second test focuses on the detection of a change in Spearman's rho. Monte Carlo simulations reveal that this test is more powerful than the first test for alternatives characterized by a change in Spearman's rho. Two approaches to compute approximate p-values for the test are studied empirically and theoretically. The first one is based on resampling, the second one consists of estimating the asymptotic null distribution of the test statictic.

[ES] Con el aumento de la demanda de soluciones más amigables con el medio ambiente en la industria de la automoción, el motor de combustión interna alternativo (MCIA) enfrenta actualmente grandes desafíos para minimizar su consumo de recursos no renovables y especialmente, para reducir sus emisiones contaminantes. Debido a que el aporte de los MCIAs es fundamental para cubrir las necesidades de movilidad y de generación de energía alrededor de todo el mundo, y el hecho de que diferentes alternativas, como los motores eléctricos e hibrido, están y continuaran enfrentado múltiples obstáculos para su implementación masiva en el futuro cercano, la investigación continua en MCIA es fundamental para cumplir con los propósitos de reducción de emisiones. En este aspecto, una aproximación para el aumento de la eficiencia del motor y la reducción del consumo de combustible es mediante la implementación de alternativas dirigidas a reducir las pérdidas mecánicas por fricción. Estas alternativas tribológicas incluyen aquellas que requieren modificaciones en los componentes del motor, como materiales y acabados superficiales, y el uso de formulaciones de aceite lubricante de menor viscosidad o aditivos que mejoren las condiciones de lubricación del motor. Con la contante evolución y mejoras en el MCIA y las condiciones de trabajo cada vez más severas, también surgen nuevas alternativas tribológicas para enfrentar los nuevos desafíos del motor, y por tanto se requiere de investigaciones adicionales en este tema. Durante el desarrollo de esta Tesis, uno de los objetivos consistió en contribuir a la investigación del uso de aceites de baja viscosidad para el ahorro de combustible como un efecto conjunto con las condiciones de conducción del vehículo. Para llevar a cabo este objetivo, se desarrollaron ensayos experimentales bajo condiciones estacionarias en un banco de motor con formulaciones de aceite de diferente viscosidad HTHS, algunas de ellos con aditivo modificador de fricción para expandir el rango de reducción de fricción a condiciones de lubricación más severas. Los mapas de consumo de combustible resultantes de estos ensayos fueron utilizados en un modelo de simulación del vehículo para estimar su consumo de combustible como función del aceite y las condiciones de trabajo de tres ciclos de conducción. Con el objetivo de expandir los conocimientos en los fundamentos de lubricación de los MCIAs y tener la capacidad de evaluar otras alternativas para reducir las pérdidas por fricción, se consideró necesario enfocar la investigación en el conjunto pistón-camisa, que es el par tribológico con mayor aporte a las perdidas por fricción. Para conseguir este objetivo, durante esta Tesis se desarrolló una maqueta específica para el ensamble pistón-camisa, y un modelo teórico para simular la lubricación del segmento de compresión. Para la primera parte, la maqueta se desarrolló basada en el método de camisa flotante, en el cual la camisa fue aislada del resto del motor y la fuerza de fricción generada en la interfaz pistón-camisa pudo ser medida mediante sensores de fuerza. En esta instalación se desarrollaron diferentes ensayos los cuales permitieron llevar a cabo un análisis exhaustivo de los fundamentos de lubricación de este par tribológico como función de diferentes parámetros que tiene impacto en las condiciones de lubricación. Este estudio se complementó con el desarrollo de un modelo de lubricación para el segmento de compresión basado en el método de diferencias finitas. Finalmente, se llevó a cabo una comparativa de resultados experimentales y teóricos para el segmento de compresión, lo cual permitió validar los ensayos experimentales en la maqueta de camisa flotante, así como el modelo de simulación desde el punto de vista de datos de entrada, condiciones de contorno y supuestos. / [CA] Amb l'augment de la demanda de solucions més amigables amb el medi ambient en la indústria de l'automoció, el motor de combustió interna alternatiu (MCIA) s'enfronta actualment a grans desafiaments per minimitzar el seu consum de recursos no renovables i especialment, per reduir les seves emissions contaminants . Tenint en compte que l'aportació dels MCIA és fonamental per a cobrir les necessitats de mobilitat i generació d'energia arreu de tot el món, i el fet que diferents alternatives, com els motors elèctrics i híbrids, estan i continuaran enfrontat múltiples obstacles per a la seva implementació massiva al proper futur, la investigació contínua en MCIA és fonamental per complir amb els propòsits de reducció d'emissions. En aquest aspecte, una aproximació per a l'augment de l'eficiència del motor i la reducció de consum de combustible és mitjançant la implementació d'alternatives dirigides a reduir les pèrdues mecàniques per fricció. Aquestes alternatives tribològiques inclouen aquelles que requereixen modificacions de components del motor, com materials i acabats superficials, i l'ús de formulacions d'oli lubricant de menor viscositat o additius que milloren les condicions de lubricació del motor. Amb la constant evolució i millores en el MCIA i les condicions de treball cada vegada més severes, també sorgeixen noves alternatives tribològiques per enfrontar els nous desafiaments del motor, i per tant es requereix d'investigacions addicionals en aquest tema. Durant el desenvolupament d'aquesta Tesi, un dels objectius va consistir a contribuir a la investigació de l'ús d'olis de baixa viscositat per a l'estalvi de combustible com un efecte conjunt amb les condicions de conducció de vehicle. Per dur a terme aquest objectiu, es van desenvolupar assajos experimentals sota condicions estacionàries en un banc de motor amb formulacions d'oli de diferent viscositat HTHS, algunes d'elles amb additiu modificador de fricció per expandir el rang de reducció de fricció a condicions de lubricació més severes . Els mapes de consum de combustible resultants d'aquests assajos van ser utilitzats en un model de simulació del vehicle per estimar el seu consum de combustible com a funció de l'oli i les condicions de treball de tres cicles de conducció. Amb l'objectiu d'expandir els coneixements en els fonaments de lubricació dels MCIAs i tenir la capacitat d'avaluar altres alternatives per reduir les pèrdues per fricció, es va considerar necessari enfocar la recerca al conjunt pistó-camisa, que és el parell tribològic amb major aportació a les perdudes per fricció. Per aconseguir aquest objectiu, durant aquesta Tesi es va desenvolupar una maqueta específica per al acoblament pistó-camisa, i un model teòric per simular la lubricació del segment de compressió. Per a la primera part, la maqueta es va desenvolupar basada en el mètode de camisa flotant, en el qual la camisa va ser aïllada de la resta del motor i la força de fricció generada en la interfície pistó-camisa va poder ser mesurada mitjançant sensors de força. En aquesta instal·lació es van desenvolupar diferents assajos els quals van permetre dur a terme una anàlisi exhaustiva dels fonaments de lubricació d'aquest parell tribològic com a funció de diferents paràmetres que tenen impacte en les condicions de lubricació. Aquest estudi es va complementar amb el desenvolupament d'un model de lubricació per al segment de compressió basat en el mètode de diferències finites. Finalment, es va dur a terme una comparativa de resultats experimentals i teòrics per al segment de compressió, la qual cosa va permetre validar els assajos experimentals a la maqueta de camisa flotant, així com el model de simulació des del punt de vista de dades d'entrada, condicions de contorn i hipòtesis. / [EN] With the increasing demand for greener solutions in the automotive industry, the ICE is currently facing great challenges to minimize the consumption of nonrenewable resources and specially to reduce its harmful emissions. Given that the contribution of the ICE is fundamental to cover the actual mobility and power generation needs worldwide, and the fact that different power-train alternatives, such as electric and hybrid vehicles, are and will continue facing multiple obstacles for their large-scale implementation in the near future, the continuous research on the ICE is fundamental in order to meet the emissions reduction targets. In this regard, one approach to increase the engine efficiency and reduce the fuel consumption, is through the implementation of alternatives aimed to reduce the friction mechanical losses. These tribological alternatives include those that require modifications to the engine components, such as materials and surface finishes, and the use of lubricant oil formulation of lower viscosity or additives that improve the lubrication performance of the engine. With the ongoing evolution and improvement of the ICE and the increasingly severe working conditions, new tribological solutions also emerge to face the new challenges in the ICE, and therefore further research is required on this subject. During the development of this Thesis, one of the objectives was to contribute to the research on low viscosity engine oils for fuel economy as a joint effect with the driving conditions of the vehicle. To accomplish this, experimental tests were performed under stationary conditions in an engine bench test for oil formulations of different HTHS viscosity, some of them with friction modifier additive to expand the friction reduction effect to more severe lubrication conditions. The resultant fuel consumption maps were then employed in a vehicle model to estimate the fuel consumption of the vehicle as function of the oil formulation and the working conditions of the three driving cycles. With the aim of expanding the knowledge on the lubrication fundamentals of the engine and to have the capability to assess other alternatives to further reduce the friction mechanical losses, it was deemed necessary to focus the research on the piston-cylinder liner assembly, the tribo-pair of major friction share. In order to achieve this objective, a test rig was developed in this Thesis specific for the piston-liner assembly, and a theoretical model to estimate the lubrication of the piston compression ring. For the first part, the test rig was designed based on the floating liner method, where the cylinder liner was isolated from the rest of the engine and the friction force generated in the piston-liner conjunction could be measured by means of force sensors. Different tests were developed in this test rig which allowed a comprehensive analysis of the piston lubrication fundamentals as function of different parameters having an impact on the lubrication performance of this assembly. This study was complemented with the development of a piston compression ring lubrication model based on the finite differences method. A comparison of experimental and theoretical results was performed for the piston compression ring that helped to validate both the experimental tests in the floating liner and the simulation model from the point of view of input data, boundary conditions and assumptions. / Bastidas Moncayo, KS. (2021). Experimental and analytical study of the mechanical friction losses in the piston-cylinder liner tribological pair in internal combustion engines (ICE) [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/172188 / TESIS