Key technology and multi-directional decomposition method of the causal mediation effect analysis / 四川精神卫生

The purpose of this paper was to introduce five key techniques and the multi-directional decomposition methods of effect components in the analysis of causal mediation effects. The contents of the five key technologies were as follows： ① identification of causal mediation effect； ② regression method of causal mediation effect analysis； ③ maximum likelihood estimation； ④ estimation of total effect and various component effects； ⑤ estimation by bootstrap method. The multi-directional decomposition methods included 3 bidirectional decompositions， 2 three-directional decompositions and 1 four-directional decomposition. Through an example， a causal mediation effect analysis model including covariates and interaction terms was constructed with the help of SAS， bidirectional decomposition， three-directional decomposition and four-directional decomposition were carried out for the total effect in the causal mediation effect analysis， and the output results were explained.

Evaluation of input and output efficiency of scientific research in hospital by Bootstrap data envelopment analysis / 中华医学科研管理杂志

Objective:To comprehensively evaluate the input and output efficiency of scientific research in hospital by bootstrap data envelopment analysis, to provide useful information for optimization of scientific performance appraisal and hospital discipline development strategy.Methods:37 disciplines were included as decision making unit, input variables include research expenditure and number of research personnel, and output variables include number of science and technology awards, research projects, patent transfer, paper, composition, and academic influence. The bootstrap-DEA method was used to evaluate the efficiency of all DMUs.Results:The main of overall efficiency and pure technical efficiency in basic DEA model are 0.858 and 0.909, but are 0.804 and 0.853 in Bootstrap DEA model, the differences between two models have statistically significant ( P<0.001). There are 11 DMUs with an overall efficiency in 0.9~1.0, 14 DMUs in 0.8~0.9, 7 DMUs in 0.6~0.8, 5 DMUs lower than 0.6. There are 3 DMUs are increasing return to scale, 16 DMUs are constant return to scale, 18 DMUs are decreasing return to scale. No statistically significance was observed between different types of DMUs( P>0.05). There are 4 DMUs reveal input slacks in number of research staffs and 10 DMUs reveal output slacks. Conclusions:The results of Bootstrap-DEA are more accurate than the basic methods for the evaluation of the input-output efficiency of hospital scientific research, so that it is worth popularizing and applying. According to the evaluation results, the hospital management department and disciplines could optimize their discipline development strategies and put forward targeted improvement measurements.

Large or Small Panel in the Delphi Study? Application of Bootstrap Technique.

Despite consensus group methods such as Delphi technique commonly used in medical education, there is a lack of standardization in methodology definitions and reporting. Size of the panel is one of fundamental questions of the researcher in a Delphi study. The present study was conducted to determine adequacy of the panel size in the Delphi round.METHODSIn this study, to determine adequacy of the panel size, the data stability was investigated in Delphi round. The Delphi study was conducted to determine competencies of educational leaders in Iran's medical sciences universities. Original data was collected from 33 experts, who were selected purposefully. Computer-generated samples of 1000 and 2000 were used for resampling. Data analysis was performed using bootstrap technique.RESULTSResults of the bootstrap technique showed that, in each of the three data groups (original and resampling data), 10 common items were in priority of 1 to 10. Ethical, commitment, punctuality, full recognition of their duties, strategic thinking, believing in values and morals, self-confidence, team working, trusteeship, motivation, maintaining morale, and supporting the faculty and staff were selected as 10 common competencies.CONCLUSIONSStability results of three data types showed that, selected panel size was sufficient to conduct this research. In Delphi studies, regardless of emphasis on small or large panel size, a panel of appropriate size should be selected. Using statistical methods, adequacy of size of the study panel can also be ensured.

Successful strategies for human microbiome data generation, storage and analyses

Current interest in the potential for clinical use of new tools for improving human health are now focused on techniques forthe study of the human microbiome and its interaction with environmental and clinical covariates. This review outlines theuse of statistical strategies that have been developed in past studies and can inform successful design and analyses ofcontrolled perturbation experiments performed in the human microbiome. We carefully outline what the data are, theirimperfections and how we need to transform, decontaminate and denoise them. We show how to identify the importantunknown parameters and how to can leverage variability we see to produce efficient models for prediction and uncertaintyquantification. We encourage a reproducible strategy that builds on best practice principles that can be adapted for effectiveexperimental design and reproducible workflows. Nonparametric, data-driven denoising strategies already provide the beststrain identification and decontamination methods. Data driven models can be combined with uncertainty quantification toprovide reproducible aids to decision making in the clinical context, as long as careful, separate, registered confirmatorytesting are undertaken. Here we provide guidelines for effective longitudinal studies and their analyses. Lessons learnedalong the way are that visualizations at every step can pinpoint problems and outliers, normalization and filtering improvepower in downstream testing. We recommend collecting and binding the metadata and covariates to sample descriptors andrecording complete computer scripts into an R markdown supplement that can reduce opportunities for human error andenable collaborators and readers to replicate all the steps of the study. Finally, we note that optimizing the bioinformatic andstatistical workflow involves adopting a wait-and-see approach that is particularly effective in cases where the features suchas ‘mass spectrometry peaks’ and metagenomic tables can only be partially annotated.

Evaluation of the scientific research efficiency of 100 tertiary hospitals and the influencing factors analysis based on Bootstrap DEA-OLS model / 中华医院管理杂志

Objective To evaluate the scientific research efficiency of tertiary hospitals and analyze the influencing factors, providing reference for the decision-making of scientific research managers in China. Methods Evaluation indicators were collected from 100 tertiary hospitals in China, and their research efficiency was evaluated using Bootstrap data envelopment analysis (DEA) method. The influencing factors were analyzed using ordinary least square ( OLS) regression model. Results The averaged scientific research efficiency of these hospitals using Bootstrap DEA method was 0. 5224, lower than that using conventional DEA method (0. 0676), yet with a great variation (from 0. 1103 to 0. 8790) among them. Linear regression analysis showed that factors such as R&D input and output, and hospital types has statistical significance on the saentific research efficiency (P < 0. 05). Conclusions These hospitals are inefficient in scientific research with sizable room for improvement. Conventional DEA method should be used with caution, as deviations should be corrected with Bootstrap DEA method. The research development level and hospital types of their province can influence the research efficiency the hospitals significantly.

Semi-quantitative analysis of the effect of 131I on residual thyroid tissue in patients with differentiated thyroid cancer / 中华地方病学杂志

Objective To evaluate the effect of postoperative thyroid residual tissue on 131I treatment of differentiated thyroid carcinoma (DTC) metastases in patients with DTC.Methods Patients with thyroid residual tissue and lymph node metastases or distant organ metastases were confirmed by 131I whole body scan after 131I treatment of DTC from January 2004 to January 2013 in Dalian.The clinical data were divided into the cured group and the non-cured group according to the final results of mI treatment.The per unit area count value (Kc/cm2) of residual thyroid remnant (NTR),lymph node metastases (LNM) and distant metastases (DM) were measured and performed semi-quantitative analysis.The thresholds of the analysis results were calculated by the Bootstrap method.Results A total of 114 patients were studied,aged from 14 to 80 years old,including 47 males and 67 females;the ratio of males to females was 1.0:1.4.There were significant differences in NTR unit area counts (0.25 vs 1.29 Kc/cm2) between the cured group and the non-cured group (72 in the cured group and 42 in the non-cured group,U =0.001,P ＜ 0.05);there was no significant difference in LNM unit area counts (0.21 vs 0.41 Kc/cm2) between the cured group and the non-cured group (U =0.052,P ＞ 0.05).Those with the ratio of residual area to lymph node metastases (N/L) and the ratio of residual area to distant metastases(N/D) less than 1.7 had a better 131I treatment;unit area N/L greater than 4.9 and unit area N/D greater than 8.0 had a poor therapeutic effect.Conclusion Excessive residual tissue after surgery results in poor efficacy of 131I treatment;semi-quantitative analysis for whole body scan after 131I treatment can predict the efficacy of 131I treatment.

Nuevos marcadores mitocondriales mejoran la filogenia de la tortuga carey Eretmochelys imbricata (Testudines: Cheloniidae) / New mitochondrial markers improve the phylogeny of the hawksbill turtle Eretmochelys imbricata (Testudines: Cheloniidae)

Las tortugas marinas (Cheloniidae) son un grupo de siete especies originadas en el cretaceo. Analisis de secuencias parciales de DNA mitocondrial han revelado inconsistencias filogeneticas dentro de este grupo de quelonios. Sin embargo, estos marcadores mitocondriales han permitido entender y dilucidar la composicion de las poblaciones en areas de forrajeo, habitos reproductivos, inferencias de patrones de migracion y tambien definir las unidades de manejo en el mundo, con el fin de proponer planes de manejo y conservacion. El objetivo de este estudio fue evaluar la posicion de la tortuga carey E. imbricata dentro de la familia Cheloniidae y la filogenia de las tortugas marinas utilizando genes mitocondriales codificantes de proteinas, genes ribosomicos y el genoma mitocondrial completo de la tortuga carey anidante del Caribe colombiano, al compararlo con las otras seis especies de tortugas marinas disponibles en GenBank. Se utilizaron cuatro metodos de inferencias filogeneticas: Neighbor-Joining (NJ), Maxima Verosimilitud (ML), Maxima Parsimonia (MP) e Inferencia Bayesiana (IB). Los arboles NJ, ML, MP e IB mostraron que ND2, COX1, 16S ARNr, ND5, 12S ARNr, ND4, COX3 y ND1 son los marcadores que presentan una mejor resolucion filogenetica con sustentos bootstrap entre 89,0% y 99,98%. Los genes ATP6, ATP8, COX2, ND3, ND4L y ND5 presentaron politomias y establecieron relaciones filogeneticas equivocadas. El analisis con el mitogenoma completo presento arboles altamente sustentados (bootstrap de 98,0%) en comparacion con el analisis con marcadores individuales. Los arboles obtenidos con el gen ND2 e IB resolvieron con buen sustento las relaciones evolutivas entre las especies comparadas, consolidandose la posicion de E. imbricata dentro de la tribu Carettini con probabilidad posterior de 0,98-1,0. Los marcadores ND2, ND5, ND4, COX3 y ND1 no han sido utilizados en trabajos previos y representan una nueva alternativa para explicar la filogenia en este grupo de reptiles marinos. En el presente caso utilizando mitogenomas completos se obtuvieron arboles robustos y altamente sustentados.

The sea turtles (Cheloniidae) are a group of seven species of cretaceous origin. Analyses of partial mitochondrial sequences have revealed phylogenetic inconsistences within this group. Nevertheless, these mitochondrial markers have allowed us to understand, explain and clarify population composition in areas of foraging, reproductive habits, inferences of migration patterns and, also, to define management units in the world, in order to trace conservation and monitoring plans. In this study, four methods were evaluated and compared for phylogenetic inference (Neighbor-Joining-NJ, Maximum Likelihood-ML, Maximum Parsimony-MP and Bayesian inference-BI) by using coding genes, ribosomal genes and full mitogenomes of the hawksbill, E. imbricata, and other six species of sea turtles obtained from GenBank. The sequences were analyzed independently and jointly to identify the method and marker that better explain the phylogenetic relationships among this group of reptiles. The NJ, ML, MP and BI trees showed that ND2, COX1, 16S rRNA, ND5, 12S rRNA, ND4 and COX3 are the markers that give phylogenetic trees with better resolution and support, with bootstrap values ranging from 89.0% to 99.98%. ATP6, ATP8, COX2, ND1, ND3, ND5 and ND4L genes presented polytomies. The analysis with full mitogenome often provides highly supported trees (bootstrap 98.0%) compared with single marker analysis. Trees obtained with the BI method and the ND2 gene is the one that better resolved the evolutionary relationships among the species, consolidating the position of E. imbricata within the Carettini tribe with a value of posterior probability of 0.98-1.0. The markers ND2, ND4, ND5 and COIII, not used in previous works, represent a new alternative to explain the phylogeny in this group of marine reptiles. In the present study, a complete mitogenome analysis produced robust and highly supported trees.

Accurate authentication of and its closely related species by comparative analysis of complete plastomes

Owing to its great medicinal and ornamental values, is frequently adulterated with other species on the market. Unfortunately, the utilization of the common DNA markers ITS, ITS2, and + is unable to distinguish from 5 closely related species of it (, , , and ). Here, we compared 63 plastomes comprising 40 newly sequenced plastomes of the 6 species and 23 previously published plastomes. The plastomes of and its closely related species were shown to have conserved genome structure and gene content. Comparative analyses revealed that small single copy region contained higher variation than large single copy and inverted repeat regions, which was mainly attributed to the loss/retention of genes. Furthermore, the intraspecific sequence variability among different species was shown to be diversified, which necessitates a cautious evaluation of genetic markers specific for different species. By evaluating the maximum likelihood trees inferred from different datasets, we found that the complete plastome sequence dataset had the highest discriminatory power for and its closely related species, indicating that complete plastome sequences can be used to accurately authenticate species.

Sample size for estimation of the Pearson correlation coefficient in cherry tomato tests / Tamanho de amostra para estimar o coeficiente de correlação de Pearson em ensaios com tomate cereja

ABSTRACT: The aim of this study was to determine the required sample size for estimation of the Pearson coefficient of correlation between cherry tomato variables. Two uniformity tests were set up in a protected environment in the spring/summer of 2014. The observed variables in each plant were mean fruit length, mean fruit width, mean fruit weight, number of bunches, number of fruits per bunch, number of fruits, and total weight of fruits, with calculation of the Pearson correlation matrix between them. Sixty eight sample sizes were planned for one greenhouse and 48 for another, with the initial sample size of 10 plants, and the others were obtained by adding five plants. For each planned sample size, 3000 estimates of the Pearson correlation coefficient were obtained through bootstrap re-samplings with replacement. The sample size for each correlation coefficient was determined when the 95% confidence interval amplitude value was less than or equal to 0.4. Obtaining estimates of the Pearson correlation coefficient with high precision is difficult for parameters with a weak linear relation. Accordingly, a larger sample size is necessary to estimate them. Linear relations involving variables dealing with size and number of fruits per plant have less precision. To estimate the coefficient of correlation between productivity variables of cherry tomato, with a confidence interval of 95% equal to 0.4, it is necessary to sample 275 plants in a 250m² greenhouse, and 200 plants in a 200m² greenhouse.

RESUMO: O objetivo deste trabalho foi determinar o tamanho de amostra necessário para estimar o coeficiente de correlação de Pearson entre variáveis do tomate cereja. Foram instalados dois ensaios de uniformidade em ambiente protegido na primavera/verão de 2014. As variáveis observadas em cada planta foram comprimento médio de fruto, largura média de fruto, peso médio de fruto, número de cachos, número de frutos por cacho, número de frutos e peso total de frutos, sendo calculada a matriz de correlação de Pearson entre elas. Foram planejados 68 tamanhos de amostra em uma estufa e 48 em outra, com tamanho inicial composto de 10 plantas e os demais obtidos acrescentando cinco plantas. Para cada tamanho de amostra planejado foram obtidas 3000 estimativas do coeficiente de correlação de Pearson através de reamostragens "bootstrap" com reposição. O tamanho de amostra de cada coeficiente de correlação foi determinado quando o valor da amplitude do intervalo de confiança de 95% foi menor ou igual a 0,4. A obtenção das estimativas do coeficiente de correlação de Pearson com elevada precisão é difícil para caracteres com relação linear fraca e, consequentemente, maior é o tamanho amostra necessário para estima-los. As relações lineares envolvendo as variáveis relacionadas com o tamanho e o número de frutos por planta tem menor precisão. Para estimar o coeficiente de correlação entre variáveis produtivas do tomate cereja, com intervalo de confiança de 95% igual a 0,4, é necessário amostrar 275 plantas na estufa de 250m², e 200 plantas na estufa de 200m².

Operational efficiency of county level public hospitals in Hubei:a Bootstrap-data envelopment analysis / 中华医院管理杂志

Objective To estimate the operational efficiency of 37 county level public general hospitals in Hubei province using the world popular method of Bootstrap-data envelopment analysis.The aim is to make up for the theory and methodology gaps on DEA research for hospitals in China,and to provide policy and management recommendations for their further improvement.Methods The input and output indicators of hospital efficiency evaluation were selected based on our previous research.R Software was used to describe the current input and output indicators,while FEAR package used to measure Bootstrap-DEA efficiency value of the sample hospitals with bias corrected,along with such applied analysis as efficiency benchmarking for the technical efficiency outcomes.Results There are great differences among the healthcare input and output of these hospitals.In particular,the difference in the number of actual beds was 4.67 times between the highest hospital and the lowest one.All of the bias corrected efficiency scores were lower than those before correction,and the average bias corrected score of the sample hospitals is 0.717 9.Moreover,only 20 hospitals(54.05%)have their efficiency scores above the median level.Conclusions The healthcare resources allocation of these hospitals needs to be further optimized.Hospitals still have big potential to improve their efficiency.Besides providing policy support,the government is advised to guide hospitals to innovate their management mechanisms,such as introducing and applying benchmarking,ranking,inter-hospital learning among others,so as to continuously improve their operational efficiency.

Social support and professional identification of nursing students: the mediating role of resilience / 中国实用护理杂志

Objective To explore the relationship between social support and professional identification among nursing students,and to examine the mediating role of resilience.Methods A total of 650 nursing students were evaluated with Social Support Rating Scale,Professional Identity Questionnaires for Nursing Students and Chinese revision of Connor-Davidson Resilience Scale.Results The scores of nursing students' social support,resilience and professional identification were (38.93±5.30),(66.79±11.93),(57.45±9.95).Professional identification could positively influence their professional identification(r=0.233-0.422,P＜0.01).Resilience mediated the relationship between social support and professional identification,the effect sizes were 52.27％.Conclusions Resilience plays a mediating role between social support and professional identity.It is important to pay attention to social support and resilience and take proper interventions to promote nursing students professional identification.

The analysis of threshold effect using Empower Stats software / 中华流行病学杂志

In many studies about biomedical research factors influence on the outcome variable,it has no influence or has a positive effect within a certain range.Exceeding a certain threshold value,the size of the effect and/or orientation will change,which called threshold effect.Whether there are threshold effects in the analysis of factors (x) on the outcome variable (y),it can be observed through a smooth curve fitting to see whether there is a piecewise linear relationship.And then using segmented regression model,LRT test and Bootstrap resampling method to analyze the threshold effect.Empower Stats software developed by American X & Y Solutions Inc has a threshold effect analysis module.You can input the threshold value at a given threshold segmentation simulated data.You may not input the threshold,but determined the optimal threshold analog data by the software automatically,and calculated the threshold confidence intervals.

Modelos não lineares para a liberação de potássio de estercos animais em latossolos / Non linear models to potassium release from animals manure in Latosols

Modelos não lineares são adequados para a descrição da liberação de nutrientes, uma vez que estimam quantidades de interesse prático e apresentam boa qualidade de ajuste. Embora seu processo inferencial seja baseado em argumentos assintóticos, existem meios de se conhecer a intensidade da não linearidade. Neste trabalho, avaliou-se a não linearidade de dois modelos de regressão não linear por meio das curvaturas de Bates e Watts, vício de Box e do estudo das propriedades amostrais dos estimadores de mínimos quadrados, obtido por simulação. Os dados são provenientes do estudo, ao longo do tempo, da liberação de K de quatro estercos animais em combinação com dois solos. O modelo Exponencial foi mais adequado, em termos inferenciais e para aplicação prática, uma vez que por todas as medidas apresentou menor não linearidade.

Nonlinear models are appropriate to describe nutrient release, since they estimate quantities of practical interest and they have goodness of fit. Although its inferential process is based on asymptotic arguments, there are ways to know the nonlinearity intensity. In this work, we evaluate the nonlinearity of two nonlinear regression models through the curvatures of Bates e Watts, bias of Box and the least squares estimator sampling properties by simulation study. The data are from the study, over time, of the K release from 4 animal manure in combination with 2 soils. The exponential model was more appropriate in terms of inferential and practical aspects, since by all measures showed lower nonlinearity.

Análisis factorial confirmatorio del NEO-FFI utilizando parcelización de ítems y método bootstrap / Análise fatorial confirmatória do NEO-FFI utilizando parcelização de itens e método bootstrap / Confirmatory factor analysis of NEO-FFI using item parceling and bootstrap method

La teoría de los cinco grandes factores (FFM) constituye actualmente uno de los modelos teóricos de mayor aceptación en el estudio de la personalidad. En argentina se cuenta con la versión española de un instrumento que permite medir los 5 grandes factores, el NEO-PIR y su versión abreviada, el NEO-FFI. El presente trabajo se propuso realizar un análisis factorial confirmatorio en una muestra de 396 estudiantes universitarios argentinos a los fines de evaluar la estructura factorial del NEO-FFI. Asimismo se complementó el análisis con métodos de parcelización de ítems y con bootstrap. Se observó que el modelo construido con parcelas estadísticas y que contempla a los factores como oblicuos, si bien presentaron los mejores índices de ajuste en comparación al resto de los modelos evaluados, no fueron óptimas. Finalmente se sugieren estudios adicionales para mejorar el funcionamiento de algunos ítems, especialmente los del factor Amabilidad.

A teoria dos cinco grandes fatores (FFM) constitui atualmente um dos modelos teóricos de maior aceitação no estudo da personalidade. Na Argentina, se usa a versão espanhola de um instrumento que permite medir os 5 grandes fatores, o NEOPIR e sua versão abreviada, o NEO-FFI. O presente trabalho se propôs a realizar uma análise fatorial confirmatória em uma amostra de 396 estudantes universitários argentinos para avaliar a estrutura fatorial do NEO-FFI. A análise foi complementada com métodos de parcelização de itens e com bootstrap. Observou-se que o modelo construído com parcelas estatísticas e que contempla os fatores como oblíquos, embora tenha apresentado os melhores índices de ajuste em comparação ao resto dos modelos avaliados, não foram ótimas. Finalmente, são sugeridos estudos adicionais para melhorar o funcionamento de alguns itens, especialmente os do fator Amabilidade.

The Five Factor Model represents currently one of the biggest developments in the study of the personality. In Argentina, there is the spanish version of an instrument which allows assess the five big factors, the NEO-PIR and his abbreviated version, the NEO-FFI. The present study has proposed to carry out a confirmatory factor analysis on a sample of 396 argentine university students to evaluate the factor structure of the NEO-FFI. Also the analysis was complemented with item parceling methods and bootstrap. It was observed that the model built with statistics parcels and that considers the factors as oblique, although having higher rates of adjustment, these are not optimal. Finally, further studies are suggested to improve the performance of some items, especially those of the Amiability factor.

Número de anos para a estimação da média decendial de duração diária do brilho solar no Rio Grande do Sul / Number of years to estimate the ten-day average of daily sunshine duration in Rio Grande do Sul State, Brazil

O objetivo deste trabalho foi determinar o tamanho de amostra (número de anos) para a estimação da média decendial de duração diária de brilho solar em 30 locais do Rio Grande do Sul. Com os dados de duração de brilho solar do período de 1960 a 2007, formaram-se 1.080 séries temporais (30 locais x 36 decêndios) de média decendial de duração diária de brilho solar. Testou-se a aleatoriedade e a normalidade dos dados, de cada série temporal, por meio dos testes de sequência (run test) e de Lilliefors, respectivamente. Para cada decêndio e local, foi determinado o tamanho de amostra por meio de reamostragem bootstrap, com reposição de 3.000 amostras. Vinte e cinco anos de observações são suficientes para a estimação da média decendial de duração diária de brilho solar, com amplitude do intervalo de confiança de bootstrap de 95% igual a 2,00 horas dia-1.

The objective of this research was to determine the sample size (number of years) to estimate the ten-day average of daily sunshine duration in 30 locations of the Rio Grande do Sul State, Brazil. With sunshine data duration of the period from 1960 to 2007, 1,080 time series (30 locations x 36 ten-days) of ten-day of daily sunshine duration average were formed. The aleatory and normality, in each time series, was verified through the run test and Lilliefors test, respectively. For each ten-day and locality, it was determined the sample size using bootstrap resampling with replacement of 3,000 samples. Twenty-five years of data are enough to predict the ten-day average of daily sunshine duration, with amplitude of bootstrap confidence interval of 95%, equal to 2.00 hour day-1.

Tamanhos de parcela e de ensaio de uniformidade em nabo forrageiro / Plot sizes and uniformity assays in turnip

Os objetivos deste trabalho foram determinar o tamanho ótimo de parcela e o tamanho de ensaio de uniformidade para a estimação do tamanho ótimo de parcela, a fim de avaliar a massa verde de nabo forrageiro (Raphanus sativus L.). Foram usados os dados de massa verde de 3.456 unidades experimentais básicas de 0,5m x 0,5m (0,25m²) e planejados 46 tamanhos de ensaio de uniformidade. O tamanho ótimo de parcela foi determinado por meio do método da curvatura máxima do modelo do coeficiente de variação. O tamanho de ensaio de uniformidade foi determinado a partir de bootstrap, com reposição de 2.000 amostras de cada tamanho de ensaio planejado. O tamanho ótimo de parcela para avaliar a massa verde de nabo forrageiro é de 4,82 unidades experimentais básicas de 0,25m² (1,20m²). Ensaios de uniformidade com 225 unidades experimentais básicas de 0,25m² (56,25m²) são suficientes para a estimação do tamanho ótimo de parcela, para uma amplitude do intervalo de confiança de bootstrap de 95 por cento, igual a uma unidade experimental básica.

The objectives of this research was to determine the optimum plot size and uniformity assay size for estimating the optimum plot size to evaluate the fresh weight of turnip (Raphanus sativus L.). Data were used from the fresh weight of 3,456 basic experimental units of 0.5m x 0.5m (0.25m²) and 46 uniformity assays sizes were planned. The optimum plot size was determined by the method of maximum curvature of the coefficient of variation model. The uniformity assay size, based on bootstrap with replacement of 2,000 samples, of each planned uniformity assay size, was determined. The optimum plot size to evaluate the fresh weight of turnip is the basic experimental units 4.82 (1.20m²). Uniformity assays with 225 basic experimental units (56.25m²) are sufficient to estimate the optimum plot size, in the bootstrap confidence interval of 95 percent, equal to one basic experimental unit.

Spatial and temporal dynamics of coffee-leaf-miner and predatory wasps in organic coffee field in formation / Dinâmica espacial e temporal do bicho-mineiro do cafeeiro e da vespa predadora em plantação de café orgânico em formação

The coffee production is an economic mainstay for many countries in the world. Brazil is the world's largest producer and exporter of coffee, being responsible for about 25 percent of the world production. It is well known that coffee plantations are susceptible to more than 850 fungal and insect pests. Among these pests, the most important significant throughout Brazil is the coffee-leaf-miner, [Leucoptera coffeella (Guérin-Mèneville & Perrottet, 1842) (Lepidoptera: Lyonetiidae)]. It is estimated that the loss in yield due to infestation by L. coffeella moths can increase to as much as 80 percent in areas where the coffee-leaf-miner larvae are not controlled. Though it is effective, the chemical control of the pest substantially increases the cost of production and constitutes a risk to the environment. The knowledge about the spatial-temporal dynamics of coffee-leaf-miner and predatory wasps may provide valuable information about the biological management pest context. One way to investigate the spatial-temporal synchronism of predator and prey is to calculate and compare an index of spatial randomness within a sequence time. This paper advocates using the Morisita's index, coupled with the bootstrap method, in a temporal sequence to characterize the spatial- temporal dynamics of coffee-leaf-miner and predatory wasp (Hymenoptera: Vespidae) in one hectare of an organic coffee plantation. The results showed that coffee-leaf-miner and predatory wasps presented a seasonal behavior with a temporal synchronism. The results also showed that both new and preyed mines were aggregated during the peak population (dry season). There was little evidence for space-time interaction between coffee-leaf-miner and predatory wasps.

A produção do café é, economicamente, muito importante para vários países do mundo. O Brasil é o maior produtor e exportador de café do mundo, sendo responsável por, aproximadamente, 25 por cento da produção mundial. Sabe-se que as plantações de café são suscetíveis ao ataque de mais de 850 tipos de fungos e insetos. Entre essas pragas, a mais importante em todo Brasil é o bicho mineiro do cafeeiro [Leucoptera coffeella (Guérin-Mèneville & Perrottet, 1842) (Lepidoptera: Lyonetiidae)]. Estima-se que a perda no rendimento devido à infestação do bicho mineiro pode chegar a 80 por cento em plantações onde não existe controle da praga. Embora o controle químico seja eficaz para combatê-la, ele acarreta um aumento no custo da produção e constitui um risco para o meio ambiente. O conhecimento da dinâmica espacial-temporal do bicho-mineiro e da vespa predadora (Hymenoptera: Vespidae) pode fornecer informações valiosas para o controle biológico da praga. Uma maneira de investigar o sincronismo espacial-temporal entre presa e predador é calcular algum índice para análise de completa aleatoriedade espacial e compará-lo ao longo do tempo. Este artigo sugere o uso do índice de Morisita, juntamente com o método bootstrap, em uma sequência temporal para caracterizar a dinâmica espacial-temporal do bicho-mineiro e da vespa predadora em um hectare de uma plantação orgânica de café. Os resultados revelaram que o bicho-mineiro e a vespa predadora apresentaram um comportamento sazonal com um sincronismo temporal. Além disso, observou-se que minas novas e predadas apresentavam agrupamentos durante a estação mais seca do ano. Existem poucas evidências de interação espaço-temporal entre minas predadas e vespas predadoras.

Bootstrap method-based estimation on the confidence interval for additive interaction in cohort studies / 中华流行病学杂志

Interaction assessment is an important step in epidemiological analysis. When etiological study is carried out, the logarithmic models such as logistic model or Cox proportional hazard model are commonly used to estimate the independent effects of the risk factors. However,estimating interaction between risk factors by the regression coefficient of the product term is on multiplicative scale, and for public-health purposes, it is supposed to be on additive scale or departure from additivity. This paper illustrates with a example of cohort study by fitting Cox proportional hazard model to estimate three measures for additive interaction which presented by Rothman.Adopting the S-Plus application with a built-in Bootstrap function, it is convenient to estimate the confidence interval for additive interaction. Furthermore, this method can avoid the exaggerated estimation by using ORs in a cohort study to gain better precision. When using the complex combination models between additive interaction and multiplicative interaction, it is reasonable to choose the former one when the result is inconsistent.

Interaction between continuous variables in logistic regression model / 中华流行病学杂志

Rothman argued that interaction estimated as departure from additivity better reflected the biological interaction. In a logistic regression model, the product term reflects the interaction as departure from multiplicativity. So far, literature on estimating interaction regarding an additive scale using logistic regression was only focusing on two dichotomous factors. The objective of the present report was to provide a method to examine the interaction as departure from additivity between two continuous variables or between one continuous variable and one categorical variable.We used data from a lung cancer case-control study among males in Hong Kong as an example to illustrate the bootstrap re-sampling method for calculating the corresponding confidence intervals.Free software R (Version 2.8.1) was used to estimate interaction on the additive scale.

Comparação de matrizes de covariâncias de populações normais dependentes: um estudo de caso / Comparing the covariance matrices of dependent normal populations: a case study

Inferências sobre comparações de matrizes de covariâncias em populações normais dependentes são usualmente obtidas considerando testes assintóticos baseados na maximização de funções de verossimilhanças. Entretanto, se o número de populações e/ou de variáveis consideradas é excessivo pode-se ter problemas na convergência dos métodos numéricos utilizados para obtenção dos estimadores de máxima verossimilhança. Face a esse problema, objetivou-se, neste trabalho, ilustrar por meio de um conjunto de dados reais, a aplicação de um teste para comparar matrizes de covariâncias de populações correlacionadas, usando uma estatística baseada na razão de variâncias generalizadas, cuja distribuição empírica foi obtida por meio da técnica bootstrap.

Inferences about dependent normal populations are usually obtained considering asymptotic tests based on the maximization likelihood functions. However, if the number of populations and/or variables considered are too high one way have convergence problems with the numerical methods used to obtain the maximum likelihood estimators. This work aimed to illustrate, using a real data set, the application of a test to compare covariance matrices of correlated populations using a statistic based on generalized variances ratio, whose empirical distribution was obtained via bootstrap methods.