Estatística - Interinstitucional (PIPGEs)
https://repositorio.ufscar.br/handle/ufscar/8205
2018-12-22T18:03:17ZEstudo do impacto da escolha do modelo para o controle de overdose na fase I dos ensaios clínicos
https://repositorio.ufscar.br/handle/ufscar/10754
Estudo do impacto da escolha do modelo para o controle de overdose na fase I dos ensaios clínicos
Escalation with overdose control proportional hazards is a Bayesian method with overdose control that estimates the maximum tolerated dose (MTD) assuming that the time a patient takes to show toxicity follows the proportional hazards model. In this work, we analyse the consequences of adopting a method based on the proportional hazard model when the time until toxicity follows the proportional survival model. In order to seek to answer if we would have an overestimate or an underestimate of MTD, simulations were performed in which we considered proportional odds survival data and application of the EWOC-PH method. As an extension of the EWOC-PH method, we propose the EWOC-POS method which assumes that time until toxicity follows the proportional odds survival model.
2018-10-03T00:00:00ZAbordagem de martingais para análise assintótica do passeio aleatório do elefante
https://repositorio.ufscar.br/handle/ufscar/10463
Abordagem de martingais para análise assintótica do passeio aleatório do elefante
In this work we study the elephant random walk introduced in (SCHUTZ; TRIMPER, 2004),
a discrete time, non-Markovian stochastic process with unlimited range memory that presents
phase transition. Our objective is to proof the almost sure convergence for the subcritical and
critical regimes of the model. We also present a demonstration of the Central Limit Theorem
for both regimes. For the supercritical regime we proof the convergence of the elephant random
walk to a non-normal random variable based on the articles (BAUR; BERTOIN, 2016), (BERCU,
2018) and (COLETTI; GAVA; SCHUTZ, 2017b).
2018-08-20T00:00:00ZQuantificação em problemas com mudança de domínio
https://repositorio.ufscar.br/handle/ufscar/10300
Quantificação em problemas com mudança de domínio
Several machine learning applications use classifiers as a way of quantifying the prevalence of positive class labels in a target dataset, a task named quantification. For instance, a naive way of determining what proportion of positive reviews about given product in the Facebook with no labeled reviews is to (i) train a classifier based on Google Shopping reviews to predict whether a user likes a product given its review, and then (ii) apply this classifier to Facebook posts about that product. Unfortunately, it is well known that such a two-step approach, named Classify and Count, fails because of data set shift, and thus several improvements have been recently proposed under an assumption named prior shift. However, these methods only explore the relationship between the covariates and the response via classifiers and none of them take advantage of the fact that one often has access to a few labeled samples in the target set. Moreover, the literature lacks in approaches that can handle a target population that varies with another covariate; for instance: How to accurately estimate how the proportion of new posts or new webpages in favor of a political candidate varies in time? We propose novel methods that fill these important gaps and compare them using both real and artificial datasets. Finally, we provide a theoretical analysis of the methods.
2018-05-17T00:00:00ZModelos preditivos para LGD
https://repositorio.ufscar.br/handle/ufscar/10236
Modelos preditivos para LGD
Financial institutions willing to use the advanced Internal Ratings Based (IRB) need to develop
methods to estimate the LGD (Loss Given Default) risk component. Proposals for PD (Probability
of default) modeling have been presented since the 1950s, in contrast, LGD’s forecast has
received more attention only after the publication of the Basel II Accord. LGD also has a
small literature, compared to PD, and there is no efficient method in terms of accuracy and
interpretation such as logistic regression for PD. Regression models for LGD play a key role
in the risk management of financial institutions, due to their importance this work proposes a
methodology to quantify the LGD risk component. Considering the characteristics reported
on the distribution of LGD and in the flexible form that the beta distribution may assume, we
propose a methodology for estimation of LGD using the zero inflated bimodal beta regression
model. We developed the zero inflated bimodal beta distribution, presented some properties,
including moments, defined estimators via maximum likelihood and constructed the regression
model for this probabilistic model, presented asymptotic confidence intervals and hypothesis
test for this model, as well as selection criteria of models, we performed a simulation study
to evaluate the performance of the maximum likelihood estimators for the parameters of the
zero inflated bimodal beta distribution. For comparison with our proposal we selected the beta
regression models and inflated beta regression, which are more usual approaches, and the SVR
algorithm, due to the significant superiority reported in other studies.
2018-05-04T00:00:00Z