How to use analysis of variance correctly——an analysis of variance for the univariate quantitative data collected from the nested design / 四川精神卫生

The purpose of this paper was to introduce the nested design and its quantitative data analysis of variance and the SAS implementation. If one of the following two characteristics existed in a specific experimental study， a nested design could be considered to arrange the experiment. Firstly， there was a nested relationship between factors in natural attributes. Secondly， with professional knowledge as the basis， the impact of each factor on the quantitative observation results was divided into primary and secondary. The first feature mentioned above meant that the factors related to the subjects had the conditions for grouping and regrouping. The second feature mentioned above meant that the status of each factor was unequal. In the variance analysis of quantitative data， the calculation formulas of variable error mean square was required to use. Based on four examples and with the help of the SAS software， this paper implemented the univariate analysis of variance for the quantitative data of the nested design， and gave the detailed explanations for the output results of SAS software.

How to use χ2 test correctly——the analysis of common relative risk for the data of a multiway table and the implementation of SAS software / 四川精神卫生

The purpose of the paper was to introduce the relative risk analysis method of g×2×2 table data and the calculation method based on SAS software. The contents included the following aspects： firstly， the homogeneity test of the data in the g×2×2 table was performed； secondly， when the data met the homogeneity requirements， the point estimation and confidence interval estimation of the common relative risk based on the correction method were implemented； thirdly， when the data did not meet the requirements of homogeneity， the common relative risk RRDL and its 95% confidence interval were estimated， based on the DerSimonian-Laird method （DL method for short）； fourthly， when the data met and did not meet the requirements of homogeneity， the hypothesis of "whether the common relative risk equals to 1" was tested. Combining two examples and based on SAS software， the paper completed the following three tasks： ① the homogeneity test for the relative risk； ② the point estimation of the common relative risk； ③the confidence interval estimation of the common relative risk. The last two tasks were performed under the conditions of the data met and did not meet the homogeneity requirements， respectively. The output results of SAS software were explained， and the statistical and professional conclusions were made.

Genetic and environmental factors that affect tick infestation in Nelore x Angus crossbreed cattle / Fatores genéticos e ambientais que afetam a infestação de carrapatos em bovinos cruzados Nelore x Angus

ABSTRACT: This study evaluated the effects of seasons and latitude on tick counting and determined the best model to estimate genetic parameters for tick count and hair coat. Records of animals naturally exposed to ticks on farms in several Brazilian states and in Paraguay were used. The ANOVA was used to verify the effects of seasons and latitude on the tick count trait. Spring was the season with the highest average, followed by summer and autumn, which showed no differences between them. The winter presented the lowest average values. Latitude -11° had the highest mean value followed by latitude -18°. The Bayesian approach was used to evaluate tick count and hair coat and to identify a suitable model for estimating genetic parameters for use in genetic evaluations. The data were analyzed using an animal model with four different specifications for "fixed" purposes. The inference was based on a Markov chain Monte Carlo (MCMC). The criteria for selection of the Bayesian model indicated that the M1 model, which considered the breed composition in the contemporary group, was superior to the other models, both for tick count and hair coat. Heritability estimates for tick count and hair coat obtained using the M1 model were 0.14 and 0.22, respectively. The rank correlations between the models for tick count and hair coat were estimated and reordering was verified for tick count. The estimated genetic correlation between tick count and hair coat traits was negative (-0.12). These findings suggest that different genes regulate tick count and hair coat.

RESUMO: Os objetivos foram avaliar os efeitos das estações e latitude na contagem de carrapatos e determinar o melhor modelo para estimar parâmetros genéticos para contagem de carrapatos e pelame. Foram utilizados registros de animais expostos naturalmente a carrapatos em fazendas em vários estados brasileiros e no Paraguai. A ANOVA foi utilizada para verificar os efeitos das estações e da latitude na característica de contagem de carrapatos. A primavera foi a estação com a maior média, seguida pelo verão e outono, que não mostraram diferenças entre eles. O inverno apresentou os menores valores médios. A latitude -11° teve o maior valor médio seguido pela latitude -18°. A abordagem bayesiana foi usada para avaliar a contagem de carrapatos e o pelame e identificar o modelo adequado para estimar parâmetros genéticos e para uso em avaliações genéticas. Os dados foram analisados usando um modelo animal com quatro especificações diferentes para efeitos "fixos". A inferência foi baseada em uma cadeia de Markov Monte Carlo (MCMC). Os critérios de seleção do modelo bayesiano indicaram que o modelo M1, que considerou a composição racial no grupo contemporâneo, foi superior aos demais modelos, tanto na contagem de carrapatos e para pelame. As estimativas de herdabilidade para contagem de carrapatos e pelame obtidas usando o modelo M1 foram de 0,14 e 0,22, respectivamente. As correlações de ranking entre os modelos para a contagem de carrapatos e pelame foram estimadas e a reordenação foi verificada para a contagem de carrapatos. A correlação genética estimada entre a contagem de carrapatos e pelame foi negativa (-0,12). Esses achados sugerem que genes diferentes regulam a contagem de carrapatos e pelame.

Comparison of Two Meta-Analysis Methods: Inverse-Variance-Weighted Average and Weighted Sum of Z-Scores

The meta-analysis has become a widely used tool for many applications in bioinformatics, including genome-wide association studies. A commonly used approach for meta-analysis is the fixed effects model approach, for which there are two popular methods: the inverse variance-weighted average method and weighted sum of z-scores method. Although previous studies have shown that the two methods perform similarly, their characteristics and their relationship have not been thoroughly investigated. In this paper, we investigate the optimal characteristics of the two methods and show the connection between the two methods. We demonstrate that the each method is optimized for a unique goal, which gives us insight into the optimal weights for the weighted sum of z-scores method. We examine the connection between the two methods both analytically and empirically and show that their resulting statistics become equivalent under certain assumptions. Finally, we apply both methods to the Wellcome Trust Case Control Consortium data and demonstrate that the two methods can give distinct results in certain study designs.

Estimation of Pharmacokinetic Parameters Using Nonlinear Fixed Effects One Compartment Open Model.

Pharmacokinetics (PK) is the science of the kinetics of drug absorption, distribution and elimination. Statistical methods are usually used for PK parameter estimation producing nonlinear responses where drug effect mechanism is modeled using compartmental approach. In the present study, PK parameters were estimated with nonlinear fixed effects one compartment open model where drug dose and sampling time are covariates and the plasma drug concentration is dependent variable. The PK parameters namely absorption rate constant (a), elimination rate constant (b) and apparent volume of distribution (V) were estimated using nonlinear least square method for each individual separately and for all individuals collectively with longitudinal or multiple response plasma drug concentration-time data obtained from 24 healthy human volunteers with reference drug product of Atorvastatin. The estimates for combined data were â =0.13±0.13hr-1, 􀜾􀷡 =0.49±0.13hr-1, 􀜸􀷡 =248±0.05L. All the individuals were again stratified into three categories based on Body Mass Index (BMI) and the PK parameters were estimated for each stratum accordingly (stratum-normal: â=0.12±0.17hr-1, 􀜾 􀷠 =0.47±0.17hr-1, 􀜸 􀷠 =250.24±0.07L; stratum-overweight: â =0.15±0.24hr-1, 􀜾􀷡 =0.47±0.25hr-1, 􀜸􀷡 =267.25±0.09L; stratumunderweight: â =0.13±0.13hr-1, 􀜾 􀷠 =0.49±0.13hr-1, 􀜸 􀷠=245±0.05L).

Comparación de cuatro modelos de regresión para el estudio de factores de riesgo de hato para datos binomiales correlacionados / Comparison of four regression models for the study of herd risk factors for binomial correlated data

The objectives of this study were to compare four linear or logistic regression models and to determine their effects on the level of significance and parameter estimates, using the data from a study on seroprevalence of brucellosis in goats. Information on 5 114 does tested during 2002-2003 from 79 herds in the Bajio region in Michoacan, Mexico was used. The models were: the prevalence of seropositive animals per herd (V1), analyzed by a general linear model (GLM), herds with at least one seropositive animal, analyzed by standard logistic regression (SLRH); V1 analyzed by standard logistic regression (SLR), assuming independence among results within a same herd (SLRA); and V1 analyzed by mixed LR, considering the herd as random effect (MLR). The risk factors included in the four models were: the presence of abortions the year previous to the study, cleanness of the corral (hygiene) and length of lactation. The V1 variable transformed to arcsine-square root did not show a normal distribution. SLRH model (SLR assuming the herd as the unit of interest) and MLR were not compared because they were not nested models. MLR model adjusted the data better than the SLRA model. The deviance (-2LL) from model SLRH (70.6) was similar to their degrees of freedom (75), suggesting that the model adjusted the data very well. Levels of significance for the risk factors were different, depending of the model used. GLM and SLRH models showed significant effects (P < 0.02) only for the presence of abortions; SLRA model showed significant effect (P < 0.05) for the three risk factors, and MLR, effects of the presence of abortions and lactation length, but not for hygiene. The values for the odd ratios (OR) for the SLRA and MLR models were different; the narrowest confidence intervals corresponded to the SLRA model, and the widest to the SLRH model.

Los objetivos de este estudio fueron comparar cuatro modelos de regresión lineal o logística y determinar sus efectos sobre los niveles de significancia y parámetros, utilizando los datos de un estudio de seroprevalencia de brucelosis en cabras. Se utilizó la información de 5 114 cabras en 79 hatos de la región del Bajío, en Michoacán, México, durante 2002-2003. Los modelos fueron: la prevalencia de animales seropositivos por hato (V1), analizados mediante un modelo lineal general (MLG); hatos con al menos un animal seropositivo, analizados mediante regresión logística estándar (RLEH), V1 analizada mediante RLE, suponiendo independencia entre resultados dentro de un mismo hato (RLEA) y V1 analizada mediante RL mixta, considerando al hato como efecto aleatorio (RLM). Los factores de riesgo incluidos en los cuatro modelos fueron: presencia de abortos el año anterior al estudio, limpieza del corral (higiene) y duración de la lactancia. La variable V1 transformada a arcoseno-raíz cuadrada no mostró distribución normal. El modelo RLEH (RL estándar considerando al hato como la unidad de interés) y RLM no se compararon por no ser modelos anidados. El modelo RLM ajustó mejor los datos que el modelo RLEA. La deviance (-2LL) del modelo RLEH (70.6) fue similar a sus grados de libertad (75), ello sugiere que este modelo ajustó estadísticamente bien los datos. Se encontraron niveles de significancia diferentes para los factores de riesgo, según el modelo estadístico utilizado. Los modelos MLG y RLEH mostraron efectos significativos (P < 0.02) sólo de presencia de abortos; el modelo RLEA mostró efecto significativo (P < 0.05) para los tres factores de riesgo, y el RLM, efectos de presencia de abortos y duración de la lactancia, pero no de higiene. Los valores de la razón de momios (OR) para los modelos RLEA y RLM fueron diferentes; los intervalos de confianza más estrechos correspondieron al modelo RLEA, y los más amplios, al RLEH.

The Acquisition, Analyses and Interpretation of fMRI Data: A Study on Functional Specialisation in Primary Auditory Cortices

In this study, functional magnetic resonance imaging (fMRI) is used to investigate func-tional specialisation in human auditory cortices during listening. A silent fMRI paradigm was used to reduce the scanner sound artefacts on functional images. The subject was instructed to pay attention to the white noise stimulus binaurally given at an inten-sity level of 70 dB higher than the hearing level for normal people. Functional speciali-sation was studied using the Matlab-based Statistical Parametric Mapping (SPM5) software by means of fixed effects (FFX), random effects (RFX) and conjunction analyses. Individual analyses on all subjects indicated asymmetrical bilateral activation of the left and right hemispheres in Brodmann areas (BA) 22, 41 and 42, involving the primary and secondary auditory cortices. The percentage of signal change is larger in the BA22, 41 and 42 on the right as compared to the ones on the left (p>0.05). The average number of activated voxels in all the respective Brodmann areas are higher in the right hemisphere than in the left (p>0.05). FFX results showed that the point of maximum intensity was in the right BA41 whereby 599±1 activated voxels were ob-served in the right temporal lobe as compared to 485±1 in the left temporal lobe. The RFX results were consistent with that of FFX. The analysis of conjunction which fol-lowed, showed that the right BA41 and left BA22 as the common activated areas in all subjects. The results confirmed the specialisation of the right auditory cortices in pro-cessing non verbal stimuli.

Brain Activations Evoked by Passive and Active Listening: A Preliminary Study on Multiple Subjects / Jurnal Sains Kesihatan Malaysia

A functional magnetic resonance imaging (fMRI) study was conducted on 4 healthy male and female subjects to investigate brain activation during passive and active listening. Two different experimental conditions were separately used in this study. The first condition requires the subjects to listen to a simple arithmetic instruction (e.g. one-plus-two-plus-three-plus-four) – passive listening. In the second condition, the subjects were given the same series of arithmetic instruction and were required to listen and perform the calculation – active listening. The data were then analysed using the Statistical Parametric Mapping (SPM5) and the MATLAB 7.4 (R2007a) programming softwares. The results obtained from the fixed (FFX) and random effects analyses (RFX) show that the active-state signal intensity was significantly higher (p < 0.05) than the resting-state signal intensity for both conditions. The results also indicate significant differences (p < 0.001) in brain activation between passive and active listening. The activated cortical regions during passive listening, as obtained from the FFX of the first condition is symmetrical in the left and right temporal and frontal lobes covering the cortical auditory areas. However, for the second condition, which was active listening, more activation occurs in the left hemisphere with a reduction in the number of activated voxels and their signal intensity in the right hemisphere. Activation mainly occurs in the middle temporal gyrus, precentral gyrus, middle frontal gyrus, superior temporal gyrus and several other areas in the frontal lobes. The point of maximum signal intensity has been shifted to a new coordinates during active listening. It is also observed that the magnetic resonance signal intensity and the number of activated voxel in the right and left superior temporal lobes for the second condition have been reduced as compared to that of the first condition. The results obtained strongly suggest the existence of functional specialisation. The results also indicate different networks for the two conditions. These networks clearly pertain to the existence of functional connectivity between activation areas during listening and listening while performing a simple arithmetic task.