Bayesian Emulation for Sequential Modeling, Inference and Decision Analysis

The advances in three related areas of state-space modeling, sequential Bayesian learning, and decision analysis are addressed, with the statistical challenges of scalability and associated dynamic sparsity. The key theme that ties the three areas is Bayesian model emulation: solving challenging analysis/computational problems using creative model emulators. This idea defines theoretical and applied advances in non-linear, non-Gaussian state-space modeling, dynamic sparsity, decision analysis and statistical computation, across linked contexts of multivariate time series and dynamic networks studies. Examples and applications in financial time series and portfolio analysis, macroeconomics and internet studies from computational advertising demonstrate the utility of the core methodological innovations.

Chapter 1 summarizes the three areas/problems and the key idea of emulating in those areas. Chapter 2 discusses the sequential analysis of latent threshold models with use of emulating models that allows for analytical filtering to enhance the efficiency of posterior sampling. Chapter 3 examines the emulator model in decision analysis, or the synthetic model, that is equivalent to the loss function in the original minimization problem, and shows its performance in the context of sequential portfolio optimization. Chapter 4 describes the method for modeling the steaming data of counts observed on a large network that relies on emulating the whole, dependent network model by independent, conjugate sub-models customized to each set of flow. Chapter 5 reviews those advances and makes the concluding remarks.

Measuring, Modeling, and Forecasting Volatility and Correlations from High-Frequency Data

This dissertation contains four essays that all share a common purpose: developing new methodologies to exploit the potential of high-frequency data for the measurement, modeling and forecasting of financial assets volatility and correlations. The first two chapters provide useful tools for univariate applications while the last two chapters develop multivariate methodologies. In chapter 1, we introduce a new class of univariate volatility models named FloGARCH models. FloGARCH models provide a parsimonious joint model for low frequency returns and realized measures, and are sufficiently flexible to capture long memory as well as asymmetries related to leverage effects. We analyze the performances of the models in a realistic numerical study and on the basis of a data set composed of 65 equities. Using more than 10 years of high-frequency transactions, we document significant statistical gains related to the FloGARCH models in terms of in-sample fit, out-of-sample fit and forecasting accuracy compared to classical and Realized GARCH models. In chapter 2, using 12 years of high-frequency transactions for 55 U.S. stocks, we argue that combining low-frequency exogenous economic indicators with high-frequency financial data improves the ability of conditionally heteroskedastic models to forecast the volatility of returns, their full multi-step ahead conditional distribution and the multi-period Value-at-Risk. Using a refined version of the Realized LGARCH model allowing for time-varying intercept and implemented with realized kernels, we document that nominal corporate profits and term spreads have strong long-run predictive ability and generate accurate risk measures forecasts over long-horizon. The results are based on several loss functions and tests, including the Model Confidence Set. Chapter 3 is a joint work with David Veredas. We study the class of disentangled realized estimators for the integrated covariance matrix of Brownian semimartingales with finite activity jumps. These estimators separate correlations and volatilities. We analyze different combinations of quantile- and median-based realized volatilities, and four estimators of realized correlations with three synchronization schemes. Their finite sample properties are studied under four data generating processes, in presence, or not, of microstructure noise, and under synchronous and asynchronous trading. The main finding is that the pre-averaged version of disentangled estimators based on Gaussian ranks (for the correlations) and median deviations (for the volatilities) provide a precise, computationally efficient, and easy alternative to measure integrated covariances on the basis of noisy and asynchronous prices. Along these lines, a minimum variance portfolio application shows the superiority of this disentangled realized estimator in terms of numerous performance metrics. Chapter 4 is co-authored with Niels S. Hansen, Asger Lunde and Kasper V. Olesen, all affiliated with CREATES at Aarhus University. We propose to use the Realized Beta GARCH model to exploit the potential of high-frequency data in commodity markets. The model produces high quality forecasts of pairwise correlations between commodities which can be used to construct a composite covariance matrix. We evaluate the quality of this matrix in a portfolio context and compare it to models used in the industry. We demonstrate significant economic gains in a realistic setting including short selling constraints and transaction costs.

ASSESSING THE DETERMINANTS OF TISSUE CULTURE BANANA ADOPTION IN WESTERN KENYA

In this study cross-section data was used to analyze the effect of farmers’ demographic, socioeconomic and institutional setting, market access and physical attributes on the probability and intensity of tissue culture banana (TCB) adoption. The study was carried out between July 2011 and November 2011. Both descriptive (mean, variance, promotions) and regression analysis were used in the analysis. A double hurdle regression model was fitted on the data. Using multistage sampling technique, four counties and eight sub-locations were randomly selected. Using random sampling technique, three hundred and thirty farmers were selected from a list of banana households in the selected sub-locations. The adoption level of tissue culture banana (TCB) was about 32%. The results also revealed that the likelihood of TCB adoption was significantly influenced by: availability of TCB planting material, proportion of banana income to the total farm income, per capita household expenditure and the location of the farmer in Kisii County; while those that significantly influenced the intensity of TCB adoption were: occupation of farmers, family size, labour source, farm size, soil fertility, availability/access of TCB plantlets to farmers, distance to banana market, use of manure in planting banana, access to agricultural extension services and index of TCB/non-TCB banana cultivar attributes which were scored by farmers. Compared to West Pokot County, farmers located in Bungoma County are more significantly and likely to adopt TCB technology. Therefore, the results of the study suggest that the probability of adoption and intensity of the use of TCB should be enhanced. This can be done by taking cognizance of these variables in order to meet the priority needs of the smallholder farmers who were the target group. This would lead to alleviating banana shortage in the region for enhanced food security. Subsequently, actors along the banana value chain are encouraged to target the intervention strategies based on the identified farmer, farm and institutional characteristics for enhanced impact on food provision. Opening up more TCB multiplication centres in different regions will make farmers access the TCB technology for enhanced impact on the target population.

A eficiência técnica dos portos e terminais públicos e privados brasileiros marítimos no período de 2010 a 2014

Dissertação (mestrado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Civil e Ambiental, 2016.

Efficient Control in Multistage Stochastic Optimization Problem

AMS subject classification: 90C31, 90A09, 49K15, 49L20.

Optimizing counterparty credit risk portfolio by reducing exposure at default variance

Rahoitusyhtiöt pitävät omaa pääomaa taseessa harvinaisen suuria markkinamuutoksia varten ja tämän pääoman määrä on ohjattu valvontaviranomaisten toimesta. Euroopassa Basel akordi antaa suuntaviivat näille säädöksille. 2007 vuoden finanssikriisin jälkeen rahoitusyhtiöt sekä valvojat ovat olleet entistä kiinnostuneempia pääoman riittävyydestä. Tutkimuksia riskistä, säädöksistä ja pääomavaateen madaltamisesta on tehty aikaisemmin, mutta tässä tutkimuksessa keskitytään vaateen jatkuvan muutoksen suuruuteen. Tutkimus sisältää hypoteettisen vastapuoliriski portfolion, jossa on mukana valuuttajohdannaisia. Tätä portfoliota simuloidaan eri tavoin, jotta nähtäisiin kuinka suuri vaikutus portfolion koostumuksella voi olla pääomavaateen varianssiin. Jos tämä muuttuja on merkittävä, pitäisikö rahoitusyhtiöiden yrittää pienentää muutosta, jotta yhtiöiden varapääoman määrää voitaisiin alentaa? Tutkimuksessa on myös haastateltu Suomen johtavia vastapuoliriski asiantuntijoita, jotta nähtäisiin rahoitusalan oma näkemys asian merkittävyydestä. Tutkimusmenetelminä toimivat haastattelut sekä numeerinen analyysi hypoteettisella portfoliolla. Kaupat tähän vastapuoliriski portfolioon on luotu 14 vuoden ajalle ja se sisältää ainoastaan valuuttajohdannaisia viidessä eri valuutassa. Riski lasketaan markkina-arvo menetelmällä, joista lasketaan VaR-mallilla tulevaisuuden riski nettoutuksen kera. Portfolion rakennetta muutetaan simuloinneissa, jotta nähtäisiin vaikutus tulevaisuuden riskeille, joita käytetään edustamaan pääomavaateen määrää ja sen vaihtelua yli ajan. Portfolioiden riskejä lasketaan myös rasituskokeiden avulla, jotta tuloksista saataisiin mahdollisimman todenmukaisia. Analyyttinen osuus tutkimuksesta näyttää sen, että tämän kaltainen optimointi on suuresti riippuvainen alkuperäisestä portfoliosta, jonka määrittää yleisesti rahoitusyhtiön myyntistrategia. Yleisesti ottaen pääomavaateen varianssin muutos voi simuloinneissa olla melko suurta, varsinkin jos mukaan huomioidaan rasitus testit, puuttuvat tuotteet sekä muut pääomavaateen laskentaan huomioitavat seikat. Haastatteluissa saatiin selville millainen optimointi voisi olla mahdollista todellisuudessa. Huomattiin myös että tämän kaltainen ajattelumalli on jo huomattu alalla ennestään. Jon Gregory jopa mainitsi, että jotkin rahoitusyhtiöt ovat enemmän kiinnostuneita muutosten pienentämisestä kuin itse pääomavaateen suuruudesta. Näyttääkin siltä, että tämän aihepiiri vaatisi entistä enemmän tutkimusta, sillä sitä ei ennestään vielä ole, ja rahoitusyhtiöt ovat jo alkaneet etsimään uusia keinoja selvitäkseen rahoitusalalla, joka on yhä entisestään kilpailullisempi.

Optimization of the valence energy variance of the CuH molecule

We developed the concept of split-'t to deal with the large molecules (in terms of the number of electrons and nuclear charge Z). This naturally leads to partitioning the local energy into components due to each electron shell. The minimization of the variation of the valence shell local energy is used to optimize a simple two parameter CuH wave function. Molecular properties (spectroscopic constants and the dipole moment) are calculated for the optimized and nearly optimized wave functions using the Variational Quantum Monte Carlo method. Our best results are comparable to those from the single and double configuration interaction (SDCI) method.

Mean Squared Residue Based Biclustering Algorithms for the Analysis of Gene Expression Data

Computational Biology is the research are that contributes to the analysis of biological data through the development of algorithms which will address significant research problems.The data from molecular biology includes DNA,RNA ,Protein and Gene expression data.Gene Expression Data provides the expression level of genes under different conditions.Gene expression is the process of transcribing the DNA sequence of a gene into mRNA sequences which in turn are later translated into proteins.The number of copies of mRNA produced is called the expression level of a gene.Gene expression data is organized in the form of a matrix. Rows in the matrix represent genes and columns in the matrix represent experimental conditions.Experimental conditions can be different tissue types or time points.Entries in the gene expression matrix are real values.Through the analysis of gene expression data it is possible to determine the behavioral patterns of genes such as similarity of their behavior,nature of their interaction,their respective contribution to the same pathways and so on. Similar expression patterns are exhibited by the genes participating in the same biological process.These patterns have immense relevance and application in bioinformatics and clinical research.Theses patterns are used in the medical domain for aid in more accurate diagnosis,prognosis,treatment planning.drug discovery and protein network analysis.To identify various patterns from gene expression data,data mining techniques are essential.Clustering is an important data mining technique for the analysis of gene expression data.To overcome the problems associated with clustering,biclustering is introduced.Biclustering refers to simultaneous clustering of both rows and columns of a data matrix. Clustering is a global whereas biclustering is a local model.Discovering local expression patterns is essential for identfying many genetic pathways that are not apparent otherwise.It is therefore necessary to move beyond the clustering paradigm towards developing approaches which are capable of discovering local patterns in gene expression data.A biclusters is a submatrix of the gene expression data matrix.The rows and columns in the submatrix need not be contiguous as in the gene expression data matrix.Biclusters are not disjoint.Computation of biclusters is costly because one will have to consider all the combinations of columans and rows in order to find out all the biclusters.The search space for the biclustering problem is 2 m+n where m and n are the number of genes and conditions respectively.Usually m+n is more than 3000.The biclustering problem is NP-hard.Biclustering is a powerful analytical tool for the biologist.The research reported in this thesis addresses the problem of biclustering.Ten algorithms are developed for the identification of coherent biclusters from gene expression data.All these algorithms are making use of a measure called mean squared residue to search for biclusters.The objective here is to identify the biclusters of maximum size with the mean squared residue lower than a given threshold. All these algorithms begin the search from tightly coregulated submatrices called the seeds.These seeds are generated by K-Means clustering algorithm.The algorithms developed can be classified as constraint based,greedy and metaheuristic.Constarint based algorithms uses one or more of the various constaints namely the MSR threshold and the MSR difference threshold.The greedy approach makes a locally optimal choice at each stage with the objective of finding the global optimum.In metaheuristic approaches particle Swarm Optimization(PSO) and variants of Greedy Randomized Adaptive Search Procedure(GRASP) are used for the identification of biclusters.These algorithms are implemented on the Yeast and Lymphoma datasets.Biologically relevant and statistically significant biclusters are identified by all these algorithms which are validated by Gene Ontology database.All these algorithms are compared with some other biclustering algorithms.Algorithms developed in this work overcome some of the problems associated with the already existing algorithms.With the help of some of the algorithms which are developed in this work biclusters with very high row variance,which is higher than the row variance of any other algorithm using mean squared residue, are identified from both Yeast and Lymphoma data sets.Such biclusters which make significant change in the expression level are highly relevant biologically.

Use of the statistical properties of the wavelet-transform coefficients for optimization of integration time in Fourier transform spectrometry

We show that an analysis of the mean and variance of discrete wavelet coefficients of coaveraged time-domain interferograms can be used as a specification for determining when to stop coaveraging. We also show that, if a prediction model built in the wavelet domain is used to determine the composition of unknown samples, a stopping criterion for the coaveraging process can be developed with respect to the uncertainty tolerated in the prediction.

Selecting from amongst non–nested conditional variance models: information criteria and portfolio determination

We consider the finite sample properties of model selection by information criteria in conditionally heteroscedastic models. Recent theoretical results show that certain popular criteria are consistent in that they will select the true model asymptotically with probability 1. To examine the empirical relevance of this property, Monte Carlo simulations are conducted for a set of non–nested data generating processes (DGPs) with the set of candidate models consisting of all types of model used as DGPs. In addition, not only is the best model considered but also those with similar values of the information criterion, called close competitors, thus forming a portfolio of eligible models. To supplement the simulations, the criteria are applied to a set of economic and financial series. In the simulations, the criteria are largely ineffective at identifying the correct model, either as best or a close competitor, the parsimonious GARCH(1, 1) model being preferred for most DGPs. In contrast, asymmetric models are generally selected to represent actual data. This leads to the conjecture that the properties of parameterizations of processes commonly used to model heteroscedastic data are more similar than may be imagined and that more attention needs to be paid to the behaviour of the standardized disturbances of such models, both in simulation exercises and in empirical modelling.

The importance of body-mass exponent optimization for evaluation of performance capability in cross-country skiing

Introduction Performance in cross-country skiing is influenced by the skier’s ability to continuously produce propelling forces and force magnitude in relation to the net external forces. A surrogate indicator of the “power supply” in cross-country skiing would be a physiological variable that reflects an important performance-related capability, whereas the body mass itself is an indicator of the “power demand” experienced by the skier. To adequately evaluate an elite skier’s performance capability, it is essential to establish the optimal ratio between the physiological variable and body mass. The overall aim of this doctoral thesis was to investigate the importance of body-mass exponent optimization for the evaluation of performance capability in cross-country skiing. Methods In total, 83 elite cross-country skiers (56 men and 27 women) volunteered to participate in the four studies. The physiological variables of maximal oxygen uptake (V̇O2max) and oxygen uptake corresponding to a blood-lactate concentration of 4 mmol∙l-1 (V̇O2obla) were determined while treadmill roller skiing using the diagonal-stride technique; mean oxygen uptake (V̇O2dp) and upper-body power output (Ẇ) were determined during double-poling tests using a ski-ergometer. Competitive performance data for elite male skiers were collected from two 15-km classical-technique skiing competitions and a 1.25-km sprint prologue; additionally, a 2-km double-poling roller-skiing time trial using the double-poling technique was used as an indicator of upper-body performance capability among elite male and female junior skiers. Power-function modelling was used to explain the race and time-trial speeds based on the physiological variables and body mass. Results The optimal V̇O2max-to-mass ratios to explain 15-km race speed were V̇O2max divided by body mass raised to the 0.48 and 0.53 power, and these models explained 68% and 69% of the variance in mean skiing speed, respectively; moreover, the 95% confidence intervals (CI) for the body-mass exponents did not include either 0 or 1. For the modelling of race speed in the sprint prologue, body mass failed to contribute to the models based on V̇O2max, V̇O2obla, and V̇O2dp. The upper-body power output-to-body mass ratio that optimally explained time-trial speed was Ẇ ∙ m-0.57 and the model explained 63% of the variance in speed. Conclusions The results in this thesis suggest that V̇O2max divided by the square root of body mass should be used as an indicator of performance in 15-km classical-technique races among elite male skiers rather than the absolute or simple ratio-standard scaled expression. To optimally explain an elite male skier’s performance capability in sprint prologues, power-function models based on oxygen-uptake variables expressed absolutely are recommended. Moreover, to evaluate elite junior skiers’ performance capabilities in 2-km double-poling roller-skiing time trials, it is recommended that Ẇ divided by the square root of body mass should be used rather than absolute or simple ratio-standard scaled expression of power output.

Alocação dinâmica ótima com momentos de ordem superior para a estratégia de carry trade

O objetivo do presente trabalho é verificar se, ao levar-se em consideração momentos de ordem superior (assimetria e curtose) na alocação de uma carteira de carry trade, há ganhos em relação à alocação tradicional que prioriza somente os dois primeiros momentos (média e variância). A hipótese da pesquisa é que moedas de carry trade apresentam retornos com distribuição não-Normal, e os momentos de ordem superior desta têm uma dinâmica, a qual pode ser modelada através de um modelo da família GARCH, neste caso IC-GARCHSK. Este modelo consiste em uma equação para cada momento condicional dos componentes independentes, explicitamente: o retorno, a variância, a assimetria, e a curtose. Outra hipótese é que um investidor com uma função utilidade do tipo CARA (constant absolute risk aversion), pode tê-la aproximada por uma expansão de Taylor de 4ª ordem. A estratégia do trabalho é modelar a dinâmica dos momentos da série dos logartimos neperianos dos retornos diários de algumas moedas de carry trade através do modelo IC-GARCHSK, e estimar a alocação ótima da carteira dinamicamente, de tal forma que se maximize a função utilidade do investidor. Os resultados mostram que há ganhos sim, ao levar-se em consideração os momentos de ordem superior, uma vez que o custo de oportunidade desta foi menor que o de uma carteira construída somente utilizando como critérios média e variância.

An adaptive chart for monitoring the process mean and variance

Traditionally, an (X) over bar chart is used to control the process mean and an R chart is used to control the process variance. However, these charts are not sensitive to small changes in the process parameters. The adaptive ($) over bar and R charts might be considered if the aim is to detect small disturbances. Due to the statistical character of the joint (X) over bar and R charts with fixed or adaptive parameters, they are not reliable in identifing the nature of the disturbance, whether it is one that shifts the process mean, increases the process variance, or leads to a combination of both effects. In practice, the speed with which the control charts detect process changes may be more important than their ability in identifying the nature of the change. Under these circumstances, it seems to be advantageous to consider a single chart, based on only one statistic, to simultaneously monitor the process mean and variance. In this paper, we propose the adaptive non-central chi-square statistic chart. This new chart is more effective than the adaptive (X) over bar and R charts in detecting disturbances that shift the process mean, increase the process variance, or lead to a combination of both effects. Copyright (c) 2006 John Wiley & Sons, Ltd.

Synthetic control chart for monitoring the pprocess mean and variance

In this article, we consider the synthetic control chart with two-stage sampling (SyTS chart) to control the process mean and variance. During the first stage, one item of the sample is inspected; if its value X, is close to the target value of the process mean, then the sampling is interrupted. Otherwise, the sampling goes on to the second stage, where the remaining items are inspected and the statistic T = Sigma [x(i) - mu(0) + xi sigma(0)](2) is computed taking into account all items of the sample. The design parameter is function of X-1. When the statistic T is larger than a specified value, the sample is classified as nonconforming. According to the synthetic procedure, the signal is based on Conforming Run Length (CRL). The CRL is the number of samples taken from the process since the previous nonconforming sample until the occurrence of the next nonconforming sample. If the CRL is sufficiently small, then a signal is generated. A comparative study shows that the SyTS chart and the joint X and S charts with double sampling are very similar in performance. However, from the practical viewpoint, the SyTS chart is more convenient to administer than the joint charts.

X charts with supplementary samples to control the mean and variance

A standard X chart for controlling a process takes regular individual observations, for instance every half hour. This article proposes a modification of the X chart that allows one to take supplementary samples. The supplementary sample is taken (and the (X) over bar and R values computed) when the current value of X falls outside the control limits. With the supplementary sample, the signal of out-of-control is given by an (X) over bar value outside the (X) over bar chart's control limits or an R value outside the R chart's control limit. The proposed chart is designed to hold the supplementary sample frequency, during the in-control period, as low as 5% or less. In this context, the practitioner might prefer to verify an out-of-control condition by simply comparing the (X) over bar and R values with the control limits. In other words, without plotting the (X) over bar and R points. The X chart with supplementary samples has two major advantages when compared with the standard (X) over bar and A charts: (a) the user will be plotting X values instead of (X) over bar and R values; (b) the shifts in the process mean and/or changes in the process variance are detected faster.