How much structure in empirical models?

This chapter highlights the problems that structural methods and SVAR approaches have when estimating DSGE models and examining their ability to capture important features of the data. We show that structural methods are subject to severe identification problems due, in large part, to the nature of DSGE models. The problems can be patched up in a number of ways but solved only if DSGEs are completely reparametrized or respecified. The potential misspecification of the structural relationships give Bayesian methods an hedge over classical ones in structural estimation. SVAR approaches may face invertibility problems but simple diagnostics can help to detect and remedy these problems. A pragmatic empirical approach ought to use the flexibility of SVARs against potential misspecificationof the structural relationships but must firmly tie SVARs to the class of DSGE models which could have have generated the data.

An assessment of empirical Bayes and composite estimators for small areas

We compare a set of empirical Bayes and composite estimators of the population means of the districts (small areas) of a country, and show that the natural modelling strategy of searching for a well fitting empirical Bayes model and using it for estimation of the area-level means can be inefficient.

The minimax distortion redundancy in empirical quantizer design

We obtain minimax lower and upper bounds for the expected distortionredundancy of empirically designed vector quantizers. We show that the meansquared distortion of a vector quantizer designed from $n$ i.i.d. datapoints using any design algorithm is at least $\Omega (n^{-1/2})$ awayfrom the optimal distortion for some distribution on a bounded subset of${\cal R}^d$. Together with existing upper bounds this result shows thatthe minimax distortion redundancy for empirical quantizer design, as afunction of the size of the training data, is asymptotically on the orderof $n^{1/2}$. We also derive a new upper bound for the performance of theempirically optimal quantizer.

Adaptive model selection using empirical complexities

Given $n$ independent replicates of a jointly distributed pair $(X,Y)\in {\cal R}^d \times {\cal R}$, we wish to select from a fixed sequence of model classes ${\cal F}_1, {\cal F}_2, \ldots$ a deterministic prediction rule $f: {\cal R}^d \to {\cal R}$ whose risk is small. We investigate the possibility of empirically assessingthe {\em complexity} of each model class, that is, the actual difficulty of the estimation problem within each class. The estimated complexities are in turn used to define an adaptive model selection procedure, which is based on complexity penalized empirical risk.The available data are divided into two parts. The first is used to form an empirical cover of each model class, and the second is used to select a candidate rule from each cover based on empirical risk. The covering radii are determined empirically to optimize a tight upper bound on the estimation error. An estimate is chosen from the list of candidates in order to minimize the sum of class complexity and empirical risk. A distinguishing feature of the approach is that the complexity of each model class is assessed empirically, based on the size of its empirical cover.Finite sample performance bounds are established for the estimates, and these bounds are applied to several non-parametric estimation problems. The estimates are shown to achieve a favorable tradeoff between approximation and estimation error, and to perform as well as if the distribution-dependent complexities of the model classes were known beforehand. In addition, it is shown that the estimate can be consistent,and even possess near optimal rates of convergence, when each model class has an infinite VC or pseudo dimension.For regression estimation with squared loss we modify our estimate to achieve a faster rate of convergence.

University admission marks in Catalonia: Some highlights from the empirical research

The results of the examinations taken by graduated high school studentswho want to enrol at a Catalan university are here studied. To do so,the authors address several issues related to the equity of the system:reliability of grading, difficulty and discrimination power of the exams.The general emphasis is put upon the concurrent research and empiricalevidence about the properties of the examination items and scores. Aftera discussion about the limitations of the exams' format and appropriatenessof the instruments used in the study, the article concludes with somesuggestions to improve such examinations.

An empirical evaluation of small area estimators

This paper investigates the comparative performance of five small areaestimators. We use Monte Carlo simulation in the context of boththeoretical and empirical populations. In addition to the direct andindirect estimators, we consider the optimal composite estimator withpopulation weights, and two composite estimators with estimatedweights: one that assumes homogeneity of within area variance andsquare bias, and another one that uses area specific estimates ofvariance and square bias. It is found that among the feasibleestimators, the best choice is the one that uses area specificestimates of variance and square bias.

Empirical studies of cloud effects on UV radiation: A review

The interest in solar ultraviolet (UV) radiation from the scientific community and the general population has risen significantly in recent years because of the link between increased UV levels at the Earth's surface and depletion of ozone in the stratosphere. As a consequence of recent research, UV radiation climatologies have been developed, and effects of some atmospheric constituents (such as ozone or aerosols) have been studied broadly. Correspondingly, there are well-established relationships between, for example, total ozone column and UV radiation levels at the Earth's surface. Effects of clouds, however, are not so well described, given the intrinsic difficulties in properly describing cloud characteristics. Nevertheless, the effect of clouds cannot be neglected, and the variability that clouds induce on UV radiation is particularly significant when short timescales are involved. In this review we show, summarize, and compare several works that deal with the effect of clouds on UV radiation. Specifically, works reviewed here approach the issue from the empirical point of view: Some relationship between measured UV radiation in cloudy conditions and cloud-related information is given in each work. Basically, there are two groups of methods: techniques that are based on observations of cloudiness (either from human observers or by using devices such as sky cameras) and techniques that use measurements of broadband solar radiation as a surrogate for cloud observations. Some techniques combine both types of information. Comparison of results from different works is addressed through using the cloud modification factor (CMF) defined as the ratio between measured UV radiation in a cloudy sky and calculated radiation for a cloudless sky. Typical CMF values for overcast skies range from 0.3 to 0.7, depending both on cloud type and characteristics. Despite this large dispersion of values corresponding to the same cloud cover, it is clear that the cloud effect on UV radiation is 15–45% lower than the cloud effect on total solar radiation. The cloud effect is usually a reducing effect, but a significant number of works report an enhancement effect (that is increased UV radiation levels at the surface) due to the presence of clouds. The review concludes with some recommendations for future studies aimed to further analyze the cloud effects on UV radiation

Eliminació d'artefactes en EGG mitjançant l'ús de la Multivariate Empirical Mode Decomposition

La tècnica de l’electroencefalograma (EEG) és una de les tècniques més utilitzades per estudiar el cervell. En aquesta tècnica s’enregistren els senyals elèctrics que es produeixen en el còrtex humà a través d’elèctrodes col•locats al cap. Aquesta tècnica, però, presenta algunes limitacions a l’hora de realitzar els enregistraments, la principal limitació es coneix com a artefactes, que són senyals indesitjats que es mesclen amb els senyals EEG. L’objectiu d’aquest treball de final de màster és presentar tres nous mètodes de neteja d’artefactes que poden ser aplicats en EEG. Aquests estan basats en l’aplicació de la Multivariate Empirical Mode Decomposition, que és una nova tècnica utilitzada per al processament de senyal. Els mètodes de neteja proposats s’apliquen a dades EEG simulades que contenen artefactes (pestanyeigs), i un cop s’han aplicat els procediments de neteja es comparen amb dades EEG que no tenen pestanyeigs, per comprovar quina millora presenten. Posteriorment, dos dels tres mètodes de neteja proposats s’apliquen sobre dades EEG reals. Les conclusions que s’han extret del treball són que dos dels nous procediments de neteja proposats es poden utilitzar per realitzar el preprocessament de dades reals per eliminar pestanyeigs.

The contribution of rectangularization to the secular increase of life expectancy: an empirical study.

BACKGROUND: In low-mortality countries, life expectancy is increasing steadily. This increase can be disentangled into two separate components: the delayed incidence of death (i.e. the rectangularization of the survival curve) and the shift of maximal age at death to the right (i.e. the extension of longevity). METHODS: We studied the secular increase of life expectancy at age 50 in nine European countries between 1922 and 2006. The respective contributions of rectangularization and longevity to increasing life expectancy are quantified with a specific tool. RESULTS: For men, an acceleration of rectangularization was observed in the 1980s in all nine countries, whereas a deceleration occurred among women in six countries in the 1960s. These diverging trends are likely to reflect the gender-specific trends in smoking. As for longevity, the extension was steady from 1922 in both genders in almost all countries. The gain of years due to longevity extension exceeded the gain due to rectangularization. This predominance over rectangularization was still observed during the most recent decades. CONCLUSIONS: Disentangling life expectancy into components offers new insights into the underlying mechanisms and possible determinants. Rectangularization mainly reflects the secular changes of the known determinants of early mortality, including smoking. Explaining the increase of maximal age at death is a more complex challenge. It might be related to slow and lifelong changes in the socio-economic environment and lifestyles as well as population composition. The still increasing longevity does not suggest that we are approaching any upper limit of human longevity.

Estimation of jump-diffusion processes via empirical characteristic functions

Preface The starting point for this work and eventually the subject of the whole thesis was the question: how to estimate parameters of the affine stochastic volatility jump-diffusion models. These models are very important for contingent claim pricing. Their major advantage, availability T of analytical solutions for characteristic functions, made them the models of choice for many theoretical constructions and practical applications. At the same time, estimation of parameters of stochastic volatility jump-diffusion models is not a straightforward task. The problem is coming from the variance process, which is non-observable. There are several estimation methodologies that deal with estimation problems of latent variables. One appeared to be particularly interesting. It proposes the estimator that in contrast to the other methods requires neither discretization nor simulation of the process: the Continuous Empirical Characteristic function estimator (EGF) based on the unconditional characteristic function. However, the procedure was derived only for the stochastic volatility models without jumps. Thus, it has become the subject of my research. This thesis consists of three parts. Each one is written as independent and self contained article. At the same time, questions that are answered by the second and third parts of this Work arise naturally from the issues investigated and results obtained in the first one. The first chapter is the theoretical foundation of the thesis. It proposes an estimation procedure for the stochastic volatility models with jumps both in the asset price and variance processes. The estimation procedure is based on the joint unconditional characteristic function for the stochastic process. The major analytical result of this part as well as of the whole thesis is the closed form expression for the joint unconditional characteristic function for the stochastic volatility jump-diffusion models. The empirical part of the chapter suggests that besides a stochastic volatility, jumps both in the mean and the volatility equation are relevant for modelling returns of the S&P500 index, which has been chosen as a general representative of the stock asset class. Hence, the next question is: what jump process to use to model returns of the S&P500. The decision about the jump process in the framework of the affine jump- diffusion models boils down to defining the intensity of the compound Poisson process, a constant or some function of state variables, and to choosing the distribution of the jump size. While the jump in the variance process is usually assumed to be exponential, there are at least three distributions of the jump size which are currently used for the asset log-prices: normal, exponential and double exponential. The second part of this thesis shows that normal jumps in the asset log-returns should be used if we are to model S&P500 index by a stochastic volatility jump-diffusion model. This is a surprising result. Exponential distribution has fatter tails and for this reason either exponential or double exponential jump size was expected to provide the best it of the stochastic volatility jump-diffusion models to the data. The idea of testing the efficiency of the Continuous ECF estimator on the simulated data has already appeared when the first estimation results of the first chapter were obtained. In the absence of a benchmark or any ground for comparison it is unreasonable to be sure that our parameter estimates and the true parameters of the models coincide. The conclusion of the second chapter provides one more reason to do that kind of test. Thus, the third part of this thesis concentrates on the estimation of parameters of stochastic volatility jump- diffusion models on the basis of the asset price time-series simulated from various "true" parameter sets. The goal is to show that the Continuous ECF estimator based on the joint unconditional characteristic function is capable of finding the true parameters. And, the third chapter proves that our estimator indeed has the ability to do so. Once it is clear that the Continuous ECF estimator based on the unconditional characteristic function is working, the next question does not wait to appear. The question is whether the computation effort can be reduced without affecting the efficiency of the estimator, or whether the efficiency of the estimator can be improved without dramatically increasing the computational burden. The efficiency of the Continuous ECF estimator depends on the number of dimensions of the joint unconditional characteristic function which is used for its construction. Theoretically, the more dimensions there are, the more efficient is the estimation procedure. In practice, however, this relationship is not so straightforward due to the increasing computational difficulties. The second chapter, for example, in addition to the choice of the jump process, discusses the possibility of using the marginal, i.e. one-dimensional, unconditional characteristic function in the estimation instead of the joint, bi-dimensional, unconditional characteristic function. As result, the preference for one or the other depends on the model to be estimated. Thus, the computational effort can be reduced in some cases without affecting the efficiency of the estimator. The improvement of the estimator s efficiency by increasing its dimensionality faces more difficulties. The third chapter of this thesis, in addition to what was discussed above, compares the performance of the estimators with bi- and three-dimensional unconditional characteristic functions on the simulated data. It shows that the theoretical efficiency of the Continuous ECF estimator based on the three-dimensional unconditional characteristic function is not attainable in practice, at least for the moment, due to the limitations on the computer power and optimization toolboxes available to the general public. Thus, the Continuous ECF estimator based on the joint, bi-dimensional, unconditional characteristic function has all the reasons to exist and to be used for the estimation of parameters of the stochastic volatility jump-diffusion models.

Counterfactuals and causal inference: Methods and principles for social research

"Most quantitative empirical analyses are motivated by the desire to estimate the causal effect of an independent variable on a dependent variable. Although the randomized experiment is the most powerful design for this task, in most social science research done outside of psychology, experimental designs are infeasible. (Winship & Morgan, 1999, p. 659)." This quote from earlier work by Winship and Morgan, which was instrumental in setting the groundwork for their book, captures the essence of our review of Morgan and Winship's book: It is about causality in nonexperimental settings.

The 2005 Pakistan earthquake revisited: Methods for integrated landslide assessment

Five years after the 2005 Pakistan earthquake that triggered multiple mass movements, landslides continue to pose a threat to the population of Azad Kashmir, especially during heavy monsoon rains. The thousands of landslides that were triggered by the 7.6 magnitude earthquake in 2005 were not just due to a natural phenomenon but largely induced by human activities, namely, road building, grazing, and deforestation. The damage caused by the landslides in the study area (381 km2) is estimated at 3.6 times the annual public works budget of Azad Kashmir for 2005 of US$ 1 million. In addition to human suffering, this cost constitutes a significant economic setback to the region that could have been reduced through improved land use and risk management. This article describes interdisciplinary research conducted 18 months after the earthquake to provide a more systemic approach to understanding risks posed by landslides, including the physical, environmental, and human contexts. The goal of this research is twofold: to present empirical data on the social, geological, and environmental contexts in which widespread landslides occurred following the 2005 earthquake; and, second, to describe straightforward methods that can be used for integrated landslide risk assessments in data-poor environments. The article analyzes limitations of the methodologies and challenges for conducting interdisciplinary research that integrates both social and physical data. This research concludes that reducing landslide risk is ultimately a management issue, based in land use decisions and governance.

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.

Optimization of Snow Drifting Mitigation and Control Methods for Iowa Conditions Part II, TR-626, 2015

Blowing and drifting of snow is a major concern for transportation efficiency and road safety in regions where their development is common. One common way to mitigate snow drift on roadways is to install plastic snow fences. Correct design of snow fences is critical for road safety and maintaining the roads open during winter in the US Midwest and other states affected by large snow events during the winter season and to maintain costs related to accumulation of snow on the roads and repair of roads to minimum levels. Of critical importance for road safety is the protection against snow drifting in regions with narrow rights of way, where standard fences cannot be deployed at the recommended distance from the road. Designing snow fences requires sound engineering judgment and a thorough evaluation of the potential for snow blowing and drifting at the construction site. The evaluation includes site-specific design parameters typically obtained with semi-empirical relations characterizing the local transport conditions. Among the critical parameters involved in fence design and assessment of their post-construction efficiency is the quantification of the snow accumulation at fence sites. The present study proposes a joint experimental and numerical approach to monitor snow deposits around snow fences, quantitatively estimate snow deposits in the field, asses the efficiency and improve the design of snow fences. Snow deposit profiles were mapped using GPS based real-time kinematic surveys (RTK) conducted at the monitored field site during and after snow storms. The monitored site allowed testing different snow fence designs under close to identical conditions over four winter seasons. The study also discusses the detailed monitoring system and analysis of weather forecast and meteorological conditions at the monitored sites. A main goal of the present study was to assess the performance of lightweight plastic snow fences with a lower porosity than the typical 50% porosity used in standard designs of such fences. The field data collected during the first winter was used to identify the best design for snow fences with a porosity of 50%. Flow fields obtained from numerical simulations showed that the fence design that worked the best during the first winter induced the formation of an elongated area of small velocity magnitude close to the ground. This information was used to identify other candidates for optimum design of fences with a lower porosity. Two of the designs with a fence porosity of 30% that were found to perform well based on results of numerical simulations were tested in the field during the second winter along with the best performing design for fences with a porosity of 50%. Field data showed that the length of the snow deposit away from the fence was reduced by about 30% for the two proposed lower-porosity (30%) fence designs compared to the best design identified for fences with a porosity of 50%. Moreover, one of the lower-porosity designs tested in the field showed no significant snow deposition within the bottom gap region beneath the fence. Thus, a major outcome of this study is to recommend using plastic snow fences with a porosity of 30%. It is expected that this lower-porosity design will continue to work well for even more severe snow events or for successive snow events occurring during the same winter. The approach advocated in the present study allowed making general recommendations for optimizing the design of lower-porosity plastic snow fences. This approach can be extended to improve the design of other types of snow fences. Some preliminary work for living snow fences is also discussed. Another major contribution of this study is to propose, develop protocols and test a novel technique based on close range photogrammetry (CRP) to quantify the snow deposits trapped snow fences. As image data can be acquired continuously, the time evolution of the volume of snow retained by a snow fence during a storm or during a whole winter season can, in principle, be obtained. Moreover, CRP is a non-intrusive method that eliminates the need to perform man-made measurements during the storms, which are difficult and sometimes dangerous to perform. Presently, there is lots of empiricism in the design of snow fences due to lack of data on fence storage capacity on how snow deposits change with the fence design and snow storm characteristics and in the estimation of the main parameters used by the state DOTs to design snow fences at a given site. The availability of such information from CRP measurements should provide critical data for the evaluation of the performance of a certain snow fence design that is tested by the IDOT. As part of the present study, the novel CRP method is tested at several sites. The present study also discusses some attempts and preliminary work to determine the snow relocation coefficient which is one of the main variables that has to be estimated by IDOT engineers when using the standard snow fence design software (Snow Drift Profiler, Tabler, 2006). Our analysis showed that standard empirical formulas did not produce reasonable values when applied at the Iowa test sites monitored as part of the present study and that simple methods to estimate this variable are not reliable. The present study makes recommendations for the development of a new methodology based on Large Scale Particle Image Velocimetry that can directly measure the snow drift fluxes and the amount of snow relocated by the fence.

Oral versus intravenous empirical antimicrobial therapy for fever in patients with granulocytopenia who are receiving cancer chemotherapy. International Antimicrobial Therapy Cooperative Group of the European Organization for Research and Treatment of Cancer.

BACKGROUND: Intravenously administered antimicrobial agents have been the standard choice for the empirical management of fever in patients with cancer and granulocytopenia. If orally administered empirical therapy is as effective as intravenous therapy, it would offer advantages such as improved quality of life and lower cost. METHODS: In a prospective, open-label, multicenter trial, we randomly assigned febrile patients with cancer who had granulocytopenia that was expected to resolve within 10 days to receive empirical therapy with either oral ciprofloxacin (750 mg twice daily) plus amoxicillin-clavulanate (625 mg three times daily) or standard daily doses of intravenous ceftriaxone plus amikacin. All patients were hospitalized until their fever resolved. The primary objective of the study was to determine whether there was equivalence between the regimens, defined as an absolute difference in the rates of success of 10 percent or less. RESULTS: Equivalence was demonstrated at the second interim analysis, and the trial was terminated after the enrollment of 353 patients. In the analysis of the 312 patients who were treated according to the protocol and who could be evaluated, treatment was successful in 86 percent of the patients in the oral-therapy group (95 percent confidence interval, 80 to 91 percent) and 84 percent of those in the intravenous-therapy group (95 percent confidence interval, 78 to 90 percent; P=0.02). The results were similar in the intention-to-treat analysis (80 percent and 77 percent, respectively; P=0.03), as were the duration of fever, the time to a change in the regimen, the reasons for such a change, the duration of therapy, and survival. The types of adverse events differed slightly between the groups but were similar in frequency. CONCLUSIONS: In low-risk patients with cancer who have fever and granulocytopenia, oral therapy with ciprofloxacin plus amoxicillin-clavulanate is as effective as intravenous therapy.