MIMCA: multiple imputation for categorical variables with multiple correspondence analysis

We propose a multiple imputation method to deal with incomplete categorical data. This method imputes the missing entries using the principal component method dedicated to categorical data: multiple correspondence analysis (MCA). The uncertainty concerning the parameters of the imputation model is reflected using a non-parametric bootstrap. Multiple imputation using MCA (MIMCA) requires estimating a small number of parameters due to the dimensionality reduction property of MCA. It allows the user to impute a large range of data sets. In particular, a high number of categories per variable, a high number of variables or a small number of individuals are not an issue for MIMCA. Through a simulation study based on real data sets, the method is assessed and compared to the reference methods (multiple imputation using the loglinear model, multiple imputation by logistic regressions) as well to the latest works on the topic (multiple imputation by random forests or by the Dirichlet process mixture of products of multinomial distributions model). The proposed method provides a good point estimate of the parameters of the analysis model considered, such as the coefficients of a main effects logistic regression model, and a reliable estimate of the variability of the estimators. In addition, MIMCA has the great advantage that it is substantially less time consuming on data sets of high dimensions than the other multiple imputation methods.     

Asymptotic behaviour of binned kernel density estimators for locally non-stationary random fields

We investigate the asymptotic behaviour of binned kernel density estimators for dependent and locally non-stationary random fields converging to stationary random fields. We focus on the study of the bias and the asymptotic normality of the estimators. A simulation experiment conducted shows that both the kernel density estimator and the binned kernel density estimator have the same behavior and both estimate accurately the true density when the number of fields increases. We apply our results to the 2002 incidence rates of tuberculosis in the departments of France.     

A Bayesian approach for zero-modified Skellam model with Hamiltonian MCMC

Statistical Methods & Applications - In this paper is presented the zero-modified poisson difference and present possible applications of them in the analysis of paired count data. The...     

江苏省仪征市真州东园位置考证

东园是仪征历史上最著名的一座园林,也是中国宋代最著名的园林之一,在中国古代园林史上占有重要地位.梅尧臣、苏轼、王安石等人都曾经在园中游览,留下了优美的诗篇,欧阳修为它写了著名的散文《真州东园记》.虽然这座园林在清代已经消失,但是今天许多人士希望能够确定东园遗址的位置,重建这座园林,为仪征保留一份珍贵的历史文化遗产.由于年代久远,仪征当地的地形地貌发生了巨大变化,东园遗迹几乎完全消失;同时,文献中东园位置的记载也是十分简略的,因此,确定它的位置非常困难.在前人研究的基础上,通过查阅文献并结合实地调查,确定了东园遗址的准确位置和边界.东园遗址的位置在以今天文墩遗址为中心,真州城东翼城遗址的南侧,真州城东门遗址的东侧,清代儒学遗址的北侧,小教场遗址的西侧.     

Estimating the population proportion in modified ranked set sampling methods

In this paper, proportion estimators and associated variance estimators are proposed for a binary variable with a concomitant variable based on modified ranked set sampling methods, which are extreme ranked set sampling (ERSS), median ranked set sampling (MRSS), percentile ranked set sampling (Per-RSS) and L ranked set sampling (LRSS) methods. The Monte Carlo simulation study is performed to compare the performance of the estimators based on bias, mean squared error, and relative efficiency for different levels of correlation coefficient, set and cycle sizes under normal and log-normal distributions. Moreover, the study is supported with real data application.     

COWORDS: a probabilistic model for multiple word clouds

Word clouds constitute one of the most popular statistical tools for the visual analysis of text documents because they provide users with a quick and intuitive understanding of the content. Despite their popularity for visualizing single documents, word clouds are not appropriate to compare different text documents. Independently generating word clouds for each document leads to configurations where the same word is typically located in widely different positions. This makes it very difficult to compare two or more word clouds. This paper introduces COWORDS, a new stochastic algorithm to create multiple word clouds, including one for each document. The shared words in multiple documents are placed in the same position in all clouds. Similar documents produce similar and compact clouds, making it easier to simultaneously compare and interpret several word clouds. The algorithm is based on a probability distribution in which the most probable configurations are those with a desirable visual aspect, such as a low value for the total distance between the words in all clouds. The algorithm output is a set of word clouds that are randomly selected from this probability distribution. The selection procedure uses a Markov chain Monte Carlo simulation method. We present several examples that illustrate the performance and visual results that can be obtained by our algorithm.     

Stressful Life Events and Physical and Psychological Health: Mediating Effects of Differentiation of Self in a Spanish Sample

The pathways between differentiation of self and health remain only partly elucidated. This cross‐cultural study sought to test Bowen's hypothesis about the associations between differentiation, stressful life events, and physical and psychological health, in a sample of 466 Spanish adults. Results show that people with higher levels of differentiation were less prone to physical ailments (e.g., heart disease, cancer, or blood disorders) and psychological symptoms (e.g., depression or anxiety). Further, differentiation mediated the association between stress (i.e., perceived negativity of stress in the past year and number of stressful events across the lifetime) and physical and psychological health. The current research provides cross‐cultural empirical evidence for the links between differentiation and mind and body health in a Mediterranean culture.     

An Ecological Model for Quantitative Risk Assessment for Schistosomiasis: The Case of a Patchy Environment in the Coastal Tropical Area of Northeastern Brazil

We developed a stochastic model for quantitative risk assessment for the Schistosoma mansoni (SM) parasite, which causes an endemic disease of public concern. The model provides answers in a useful format for public health decisions, uses data and expert opinion, and can be applied to any landscape where the snail Biomphalaria glabrata is the main intermediate host (South and Central America, the Caribbean, and Africa). It incorporates several realistic and case‐specific features: stage‐structured parasite populations, periodic praziquantel (PZQ) drug treatment for humans, density dependence, extreme events (prolonged rainfall), site‐specific sanitation quality, environmental stochasticity, monthly rainfall variation, uncertainty in parameters, and spatial dynamics. We parameterize the model through a real‐world application in the district of Porto de Galinhas (PG), one of the main touristic destinations in Brazil, where previous studies identified four parasite populations within the metapopulation. The results provide a good approximation of the dynamics of the system and are in agreement with our field observations, i.e., the lack of basic infrastructure (sanitation level and health programs) makes PG a suitable habitat for the persistence and growth of a parasite metapopulation. We quantify the risk of SM metapopulation explosion and quasi‐extinction and the time to metapopulation explosion and quasi‐extinction. We evaluate the sensitivity of the results under varying scenarios of future periodic PZQ treatment (based on the Brazilian Ministry of Health's plan) and sanitation quality. We conclude that the plan might be useful to slow SM metapopulation growth but not to control it. Additional investments in better sanitation are necessary.