Elias Teixeira Krainski

Direct fitting of dynamic models using integrated nested Laplace approximations - INLA

Inference in state-space models usually relies on recursive forms for filtering and smoothing of the state vectors regarding the temporal structure of the observations, an assumption that is, from our view point, unnecessary if the dataset is fixed, that is, completely available before analysis. In this paper, we propose a computational framework to perform approximate full Bayesian inference in linear and generalized dynamic linear models based on the Integrated Nested Laplace Approximation (INLA) approach. The proposed framework directly approximates the posterior marginals of interest disregarding the assumption of recursive updating/estimation of the states and hyperparameters in the case of fixed datasets and, therefore, enable us to do fully Bayesian analysis of complex state-space models more easily and in a short computational time. The proposed framework overcomes some limitations of current tools in the dynamic modeling literature and is vastly illustrated with a series of simulated as well as well known real-life examples from the literature, including realistically complex models with correlated error structures and models with more than one state vector, being mutually dependent on each other. R code is available online for all the examples presented.

Where do people live longer and shorter lives? An ecological study of old-age survival across 4404 small areas from 18 European countries

Background Further increases in life expectancy in high-income countries depend to a large extent on advances in old-age survival. We aimed to characterise the spatial distribution of old-age survival across small areas of Europe, and to identify areas with significantly high or low survivorship. Methods This study incorporated 4404 small areas from 18 European countries. We used a 10-year survival rate to express the proportion of population aged 75–84 years who reached 85–94 years of age (beyond average life expectancy). This metric was calculated for each gender using decennial census data (1991, 2001 and 2011) at small geographical areas. To address problems associated with small areas, rates were smoothed using a Bayesian spatial model. Excursion sets were defined to identify areas with significantly high (>95th centile) and low (<5th) survival. Results In 2011, on average, 47.1% (range: 22.5–71.5) of the female population aged 75–84 years had reached 85–94 years of age, compared to 34.2% (16.4–49.6) of the males. These figures, however, hide important and time-persistent spatial inequalities. Higher survival rates were concentrated in northern Spain, Andorra and northeastern Italy, and in the south and west of France. Lower survival was found in parts of the UK, Scandinavia and the Netherlands, and in some areas of southern Europe. Within these regions, we detected areas with significantly high and low old-age survival. Conclusions Clear and persistent spatial inequalities in old-age survival exist, suggesting that European social unity is still to be accomplished. These inequalities could arise from a myriad of population health determinants (eg, poverty, unhealthy lifestyles), which merit further study.

Autologistic model with an application to the citrus "sudden death" disease

The citrus sudden death (CSD) disease affects dramatically citrus trees causing a progressive plant decline and death. The disease has been identified in the late 90s in the main citrus production area of Brazil and since then there are efforts to understand the etiology as well as the mechanisms its spreading. One relevant aspect of such studies is to investigate spatial patterns of the occurrence within a field. Methods for determining whether the spatial pattern is aggregated or not has been frequently used. However it is possible to further explore and describe the data by means of adopting an explicit model to discriminate and quantify effects by attaching parameters to covariates which represent aspects of interest to be investigated. One alternative involves autologistic models, which extend a usual logistic model in order to accommodate spatial effects. In order to implement such model it is necessary to take into account the reuse of data to built spatial covariates, which requires extensions in methodology and algorithms to assess the variance of the estimates. This work presents an application of the autologistic model to data collected at 11 time points from citrus fields affected by CSD. It is shown how the autologistic model is suitable to investigate diseases of this type, as well as a description of the model and the computational aspects necessary for model fitting.

Modelo autologístico espaço-temporal com aplicação à análise de padrões espaciais da leprose-dos-citros

The goal of this study was to propose modeling strategies applied to the analysis of citrus leprosis incidence, through the use of a spatial temporal autologistic model. We evaluated the adequacy of autologistic model to consider data collected at different times; to detect spatial-temporal patterns through different neighboring structures; to consider the effect of covariates from previous times; and assessing the effect of the presence of the disease vector in the probability of new infections occurrence. The spatial temporal autologistic model adopted has extended the usual logistic model, in which the neighboring structures is described by means of covariates built from the status of plants nearby, at the same or at previous times. Data regarding the presence of the leprosis on plants were collected at field points referenced in space, over a period of approximately two years. Models detect the presence of spatial patterns on new infections for the studied neighboring structures, at the same or previous time. Additionally, probability estimates of a plant become infected can be obtained from the fitted models, given the occurrence of the disease and vector.

The influence of socioeconomic, biogeophysical and built environment on old-age survival in a Southern European city.

Old-age survival is a good indicator of population health and regional development. We evaluated the spatial distribution of old-age survival across Porto neighbourhoods and its relation with physical (biogeophysical and built) and socioeconomic factors (deprivation). Smoothed survival rates and odds ratio (OR) were estimated using Bayesian spatial models. There were important geographical differentials in the chances of survival after 75 years of age. Socioeconomic deprivation strongly impacted old-age survival (Men: least deprived areas OR=1.31(1.05-1.63); Women OR=1.53(1.24-1.89)), explaining over 40% of the spatial variance. Walkability and biogeophysical environment were unrelated to old-age survival and also unrelated to socioeconomic deprivation, being fairly evenly distributed through the city.

Can collective memories shape fish distributions? A test, linking space-time occurrence models and population demographics

Social learning can be fundamental to cohesive group living, and schooling fishes have proven ideal test subjects for recent work in this field. For many species, both demographic factors, and inter- (and intra-) generational information exchange are considered vital ingredients in how movement decisions are reached. Yet key information is often missing on the spatial outcomes of such decisions, and questions concerning how migratory traditions are influenced by collective memory, density-dependent and density-independent processes remain open. To explore these issues, we focused on Atlantic herring (Clupea harengus), a long-lived, dense-schooling species of high commercial importance, noted for its unpredictable shifts in winter distribution, and developed a series of Bayesian space-time occurrence models to investigate wintering dynamics over 23 years, using point-referenced fishery and survey records from Icelandic waters. We included covariates reflecting local-scale environmental factors, temporally-lagged prey biomass and recent fishing activity, and through an index capturing distributional persistence over time, derived two proxies for spatial memory of past wintering sites. The previous winters occurrence pattern was a strong predictor of the present pattern, its influence increasing with adult population size. Although the mechanistic underpinnings of this result remain uncertain, we suggest that a ‘wisdom of the crowd’ dynamic may be at play, by which navigational accuracy towards traditional wintering sites improves in larger and/or denser, better synchronized schools. Wintering herring also preferred warmer, fresher, moderately stratified waters of lower velocity, close to hotspots of summer zooplankton biomass, our results indicative of heightened environmental sensitivity in younger cohorts. Incorporating spatiotemporal correlation structure and time-varying regression coefficients improved model performance, and validation tests on independent observations one-year ahead illustrate the potential of uniting demographic information and non-stationary models to quantify both the strength of collective memory in animal groups and its relevance for the spatial management of populations. This article is protected by copyright. All rights reserved.

Spatial patterns of the Citrus leprosis virus and its associated mite vector in systems without intervention

R. B. Bassanezi* , A. B. C. Czermainski, F. F. Laranjeira, A. S. Moreira , P. J. Ribeiro J unior, E. T. Krainski and L. Amorim Research & Development Department, Fundecitrus, CP 391, 14801-970 Araraquara, SP; Embrapa Grape & Wine, CP 130, 95700-000 Bento Gonc alves, RS; Embrapa Cassava & Fruits, 44380-000 Cruz das Almas, BA; Department of Statistics, Federal University of Parana, CP 19081, 81531-990 Curitiba, PR; and Plant Pathology and Nematology Department, University of Sao Paulo, CP 9, 13418-900 Piracicaba, SP, Brazil

The influence of socioeconomic deprivation, access to healthcare and physical environment on old-age survival in Portugal

Spatial inequalities in old-age survival exist in Portugal and might be associated with factors pertaining to three distinct domains: socioeconomic, physical environmental and healthcare. We evaluated the contribution of these factors on the old-age survival across Portuguese municipalities deriving a surrogate measure of life expectancy, a 10-year survival rate that expresses the proportion of the population aged 75-84 years old who reached 85-94. As covariates we used two internationally comparable multivariate indexes: the European deprivation index and the multiple physical environmental deprivation index. A national index was developed to evaluate the access to healthcare. Smoothed rates and odds ratios (OR) were estimated using Bayesian spatial models. Socioeconomic deprivation was found to be the most relevant factor influencing old-age survival in Portugal [women: least deprived areas OR=1.132(1.064-1.207); men OR=1.044(1.001- 1.094)] and explained a sizable amount of the spatial variance in survival, especially among women. Access to healthcare was associated with old-age survival in the univariable model only; results lost significance after adjustment for socioeconomic circumstances [women: higher access to healthcare OR=1.020(0.973- 1.072); men OR=1.021(0.989-1.060)]. Physical environmental deprivation was unrelated with old-age survival. In conclusion, socioeconomic deprivation was the most important determinant in explaining spatial disparities in old-age survival in Portugal, which indicates that policy makers should direct their efforts to tackle socioeconomic differentials between regions.