RESUMO
This work presents a model-agnostic evaluation of four different models that estimate a disease's basic reproduction number. The evaluation presented is twofold: first, the theory behind each of the models is reviewed and compared; then, each model is tested with eight impartial simulations. All scenarios were constructed in an experimental framework that allows each model to fulfill its assumptions and hence, obtain unbiased results for each case. Among these models is the one proposed by Thompson et al. (Epidemics 29:100356, 2019), i.e., a Bayesian estimation method well established in epidemiological practice. The other three models include a novel state-space method and two simulation-based approaches based on a Poisson infection process. The advantages and flaws of each model are discussed from both theoretical and practical standpoints. Finally, we present the evolution of Covid-19 outbreak in Colombia as a case study for computing the basic reproduction number with each one of the reviewed methods.
Assuntos
Número Básico de Reprodução/estatística & dados numéricos , COVID-19/epidemiologia , COVID-19/transmissão , Pandemias/estatística & dados numéricos , SARS-CoV-2 , Teorema de Bayes , Colômbia/epidemiologia , Simulação por Computador , Intervalos de Confiança , Epidemias/estatística & dados numéricos , Humanos , Conceitos Matemáticos , Modelos Biológicos , Modelos Estatísticos , Distribuição de PoissonRESUMO
There is a well-established tradition within the statistics literature that explores different techniques for reducing the dimensionality of large feature spaces. The problem is central to machine learning and it has been largely explored under the unsupervised learning paradigm. We introduce a supervised clustering methodology that capitalizes on a Metropolis Hastings algorithm to optimize the partition structure of a large categorical feature space tailored towards minimizing the test error of a learning algorithm. This is a general methodology that can be applied to any supervised learning problem with a large categorical feature space. We show the benefits of the algorithm by applying this methodology to the problem of risk adjustment in competitive health insurance markets. We use a large claims data set that records ICD-10 codes, a large categorical feature space. We aim at improving risk adjustment by clustering diagnostic codes into risk groups suitable for health expenditure prediction. We test the performance of our methodology against common alternatives using panel data from a representative sample of twenty three million citizens in Colombian Healthcare System. Our results outperform common alternatives and suggest that it has potential to improve risk adjustment.