How to use analysis of variance correctly——the multiple comparisons among the multiple means / 四川精神卫生

The purpose of the paper was to introduce the multiple comparison method among multiple means and the SAS implementation. The multiple comparison approaches could be subdivided into the pairwise comparisons， the comparisons of all treatment groups with a control group， the comparisons of the mean of each treatment group with the average of all groups， the approximate and simulation-based approach， the multi-stage testing and Bayesian method. Except for the Bayesian approach， the difference between other multiple comparison methods lied in the types of error that were controlled. Error types could be roughly divided into the following three categories， the comparisonwise error rate， the experimentwise error rate and the maximum experimentwise error rate. The multiple comparison methods constructed based on the control of different error rates were not all the same in the strength of inference to draw conclusions. This paper used the SAS software to analyze the examples and explained the output results.

Multiple hypothesis testing in radiobiological omics study / 中华放射医学与防护杂志

With the development of high-throughput sequencing technology, the high-dimensional massive data obtained in omics study puts forward new requirements for statistical analysis. In this case, the traditional theory of single hypothesis testing is no longer applicable, and the issue of multiple hypothesis testing has received increasing attention. This paper introduced three commonly used error measures in multiple testing-family-wise error rate (FWER), false discovery rate (FDR), and positive false discovery rate (pFDR), and the control process in radiobiological omics data analysis, in order to provide a reference for statistical analysis of radiobiological data.

A study on the dimensional error of 3D printing maxilla models / 重庆医学

Objective To measure the dimensional error of three dimensional printing maxilla models for the clinical application to oral and maxillofacial surgery.Methods The FDM 3D printing was employed to make standard geometric shape models and maxillary models.After the surface finish of both models being observed,the contour data and fineness of geometric models,as well as the distance error of bony markers between maxillary models and jaw bones specimen were measured.Results Within the 3D printing standard geometric model,the fiber arrange horizontally in X-Z,Y-Z surface and crosswise in X-Y surface,and the accuracy errors range from-1.67％ to 1.47％.Moreover,the maximum resolution was 0.25 mm in X and Y axis,and 0.50 mm in Z axis.Within the maxillary model,the distance error of bony markers range from-0.08 ％ to 1.96 ％,and the mean errors were 1.59 ％,0.86％,0.42％ in X,Y and Z axis respectively.The mean error in X axis was significantly larger than that in Y or Z axis (P＜0.05).Conclusion 3D printing maxilla models may possess high accuracy and apply to clinical practice.

Application of QCC in Reduction of Error Rate of Inventory in Automated Pharmacy / 中国药房

OBJECTIVE:To reduce the error rate of inventory in the automated pharmacy of our hospital. METHODS:Activi-ties were designed and implemented by the management method of quality control circles(QCC)-PDCA(Plan,Do,Check and Ac-tion)cycle. The reasons for the errors of inventory in the automated pharmacy were analyzed to investigate and implement counter-measures. Visible and invisible achievements were evaluated,and then standardized processes were made. RESULTS:The errors of inventory in the automated pharmacy mainly included those of drug dispensing,drug shelving,drug return sheet,automatic medi-cine dispensing machine and system. In view of the above reasons,relevant standards were formulated and performed,including the process of warehouse-out check and shelving of drugs,drug dispensing process for the automated pharmacy,the process of sec-ondary check,etc. After the implementation of the activities,the error rate of inventory in the automated pharmacy reduced from 9.17% to 3.77%,which was visible achievement;and the above-mentioned standardized processes could ensure continuous run-ning of PDCA cycle. The practice,sense of responsibility,communication and coordination of management members in PDCA cy-cle namely invisible achievements were improved to some extent. CONCLUSIONS:The management method of QCC-PDCA cycle is feasible in reduction of the error rate of inventory in the automated pharmacy,which can provide a reference for automated phar-macy management.

Influence of Attention Training on Chinese Character Processing Capability in Poststroke Nonfluent Aphasiacs / 中国康复理论与实践

@#Objective To explore the influence of attention training on Chinese character processing capability in poststroke nonfluent aphasiacs. Methods 60 stroke patients with nonfluent aphasia and cognition dysfunction were divided into control group (n=30) and experimental group (n=30). The trainings (attention training and cognition training) were respectively 30 minutes each time, 5 times each week for 4 weeks. The change of reaction time and error rate were compared before and after they were performing the orthographic, semantic and phonological tasks. Results In the dual-task paradigm the change of reaction time and error rate in orthographic and semantic tasks of the experimental group were all higher than the control group (P<0.001). But there was no difference between the two groups in the phonological task (P>0.05). In the single task paradigm there was no difference between the two groups (P>0.05). Conclusion 1. Attention training can improve the processing capacity significantly in orthographic and semantic tasks in the dual-task paradigm because the volume and distributive ability of attention improve significantly. 2. Attention training can't improve the processing capacity in phonological tasks in the dual- task paradigm because reading aloud and judging are required to process the vowel simultaneously. So that the competion intensifies and it is more difficult to finish the task. 3. In the single task paradigm, there is no significant difference between the influence of the two trainings in poststroke nonfluent aphasiac because the single task needs little attention and the change in the control group is enough.

Influence of Attention Training on Chinese Character Processing Capability in Poststroke Nonfluent Aphasiacs / 中国康复理论与实践

Objective To explore the influence of attention training on Chinese character processing capability in poststroke nonfluent aphasiacs. Methods 60 stroke patients with nonfluent aphasia and cognition dysfunction were divided into control group (n=30) and experi-mental group (n=30). The trainings (attention training and cognition training) were respectively 30 minutes each time, 5 times each week for 4 weeks. The change of reaction time and error rate were compared before and after they were performing the orthographic, semantic and phonological tasks. Results In the dual-task paradigm the change of reaction time and error rate in orthographic and semantic tasks of the ex-perimental group were all higher than the control group (P0.05). In the single task paradigm there was no difference between the two groups (P>0.05). Conclusion 1. Attention training can improve the processing capacity significantly in orthographic and semantic tasks in the dual-task paradigm because the volume and distribu-tive ability of attention improve significantly. 2. Attention training can't improve the processing capacity in phonological tasks in the du-al-task paradigm because reading aloud and judging are required to process the vowel simultaneously. So that the competion intensifies and it is more difficult to finish the task. 3. In the single task paradigm, there is no significant difference between the influence of the two train-ings in poststroke nonfluent aphasiac because the single task needs little attention and the change in the control group is enough.

Quality Assurance of Intensity Modulated Radiation Therapy: Site-Specific Results of Eulji University Hospital / 대한방사선종양학회지

PURPOSE: To analyze our quality assurance (QA) data for intensity modulated radiation therapy (IMRT) according to treatment site and to possibly improve QA for IMRT in Hospital. MATERIALS AND METHODS: We performed QA on 50 patients (head and neck, 28 patients; Breast, 14 patients; Pelvis, 8 patients) for IMRT. The calculated dose from RTP was compared with the measured value film, gamma index, and ionization chamber for dose measurement in each case. RESULTS: The point dose measurement results in 45 of 50 patients showed good agreement with the calculation dose (+/-3%). The largest error measured thus far has been 3.60%, with a mean of only -0.17% (SD, 2.25%). Each treatment site showed an error rate of -0.13% (SD, 1.93%) for head and neck cases, -0.26% (SD, 2.79%) for breast cases, and -0.24% (SD, 2.44%) for pelvis cases. The gamma index verified with the error rate of head and neck cases (6%), breast (10%), and pelvis (6%), which corresponded to a tolerance of 3 mm (3% for the head and neck, 2%, for the breast 1% for the pelvis, and 0% in the region where the isodose curve was greater than 90%. CONCLUSION: We recognize the cause of errors for each treatment site of IMRT QA and so we maximize our efforts to reduce error and increase accuracy.

Comparações múltiplas bayesianas em modelos normais homocedásticos e heterocedásticos / Bayesian multiple comparisons in homocedastic and heterocedastic normal models

Procedimentos de comparações múltiplas são utilizados para comparar médias de níveis de um fator, porém, os testes mais populares apresentam problemas de ambiguidade dos resultados e de controle do erro tipo I, além de terem seus desempenhos influenciados negativamente no caso de heterogeneidade de variâncias e não balanceamento. Objetivou-se, neste trabalho propor alternativas bayesianas para comparações múltiplas considerando os casos de homogeneidade e heterogeneidade de variâncias. A metodologia utilizada nesse trabalho foi baseada na distribuição a posteriori t multivariada. Foram geradas k cadeias de médias, utilizando o método de Monte Carlo. Foi obtida a amplitude padronizada sob H0, obtida na distribuição a posteriori das médias, contemplando a possibilidade de se analisar tanto o caso de variâncias heterogêneas como o caso de variâncias homogêneas. Os procedimentos de comparações múltiplas bayesianos foram propostos com sucesso.

Multiple comparison procedures are used to compare factor's levels means, since the most popular tests show problems related to ambiguous results and to the control of the type I error rates. Moreover, their performance is worst in heterocedastics and unbalanced cases. The objective of this work is to propose a Bayesian alternative for multiple comparisons considering the homocedastic and heterocedastic normal models. The methodology adopted in this paper was based on a posteriori multivariate t distribution. It was used k Monte Carlo chains of the mean factor to make inferences. The standardized range was obtained, under H0, from the posteriori distribution of the means, for the analysis of homocedastic and heterocedastic cases. The bayesian procedures of multiple comparisons were successfully proposed.

Discrepancies between Human Leukocyte Antigen Registry Typing and Confirmatory Typing Results of Unrelated Hematopoietic Stem Cell Donors / 대한진단검사의학회지

BACKGROUND: In unrelated hematopoietic stem cell transplantation, the accuracy of HLA registry typing (RT) of donors is important for timely search and coordination of HLA-matched donors. We analyzed discrepancies between HLA RT and confirmatory typing (CT) results of stem cell donors in Korean and foreign registries. METHODS: We analyzed the HLA typing results of 834 donors for whom CT was performed at Seoul National University Hospital between April 1997 and March 2010. For CT, DNA typing was used in majority of the cases and HLA-A and HLA-B serological typing was used in some early cases. The discrepancies between the typing results were analyzed at the serological/generic level. RESULTS: The overall discrepancy rate (RT error rate) was 3.2%, and the rate was similar in the Korean and foreign registries. The discrepancy rates in the Korean and foreign registries were more than 10% in the 1997-2001 searches, but decreased to less than 3% in the 2002-2010 searches. Analysis of 19 cases of RT errors in the Korean registry revealed 3 cases of sample switchover errors and 16 cases of typing errors in one of the HLA-A, HLA-B, or HLA-DR loci. The RT error rate in Japan Marrow Donor Program was lower than those in other foreign registries. CONCLUSIONS: The error rate of HLA RT results of unrelated stem cell donors in the Korean registry was similar to those in the foreign registries, and has decreased in the recent searches following the change in the typing method from serological to DNA typing.

Robustness of asymptotic and bootstrap tests for multivariate homogeneity of covariance matrices / Robustez de testes assintóticos e de Bootstrap para homogeneidade de covariâncias em populações multivariadas

The present work emphasizes the importance of testing hypothesis on homogeneity of covariance matrices from multivariate k populations. The violation of the assumption of the homogeneity of covariance matrices affects the performance of the tests and the coverage probability of the confidence regions. This work intends to apply two tests of homogeneity of covariance and to evaluate type I error rates and power using Monte Carlo simulation in normal populations and robustness in non normal populations. Multivariate Bartlett's test (MBT) and its bootstrap version (MBTB) were used. Different configurations are tested combining sample sizes, number of variates, correlation and number of populations. Results show that the bootstrap test was considered superior to the asymptotic test and robust, since it controls the type error I rate.

O presente trabalho ressalta a importância da aplicação de testes sobre a hipótese de igualdade de matrizes de covariâncias de k populações. A violação da pressuposição da homogeneidade das covariâncias afeta diretamente a qualidade dos testes e a probabilidade de cobertura das regiões de confiança. Por essa razão, neste trabalho propõe-se aplicar dois testes de homogeneidade de covariâncias e avaliar as suas performances mediante uso de simulação Monte Carlo em populações normais e a robustez em situações não-normais avaliando-se o erro tipo I e o poder. Os testes utilizados foram: teste de Bartlett multivariado e a sua versão bootstrap. Foram feitas combinações entre os tamanhos amostrais, número de variáveis, correlação e número de populações. Os resultados obtidos permitiram concluir que o teste de bootstrap foi considerado superior aos assintótico e robusto, controlando o erro tipo I.

Desempenho de testes de normalidade multivariados avaliado por simulação Monte Carlo / Monte Carlo evaluation of the performance of multivariate normality tests

Neste trabalho, objetivou-se avaliar a performance do teste multivariado de normalidade de Shapiro-Wilk implementado no R comparando o seu desempenho com os testes de assimetria e curtose de Mardia (1970, 1974, 1975) utilizando simulação Monte Carlo. Foram mensuradas e comparadas as taxas de erro tipo I e poderes dos testes. Pode-se concluir que o teste de Shapiro-Wilk multivariado do programa R, função mshapiro.test do pacote mvnormtest, tem fraco desempenho (liberal) e não é recomendado para uso rotineiro.

This work aimed to evaluate the performance of the multivariate normality test of Shapiro-Wilk implemented in R in the library mvnormtest and to compare it with the asymmetry and kurtosis normality test proposed by Mardia (1970, 1974, 1975) using Monte Carlo simulation. The multivariate normality test of Shapiro-Wilk is not recommended for regular use.

Basic Cognitive Abilities of Developmental Stutterers in Processing Chinese Character / 中国康复理论与实践

@#Objective To examine the performance of developmental stutterers in processing Chinese character to determine their basic cognitive abilities of Chinese language.Methods The reaction time and error rates of developmental stutterers and fluent speakers were compared when they performed orthographic,phonetic and semantic judging tasks in the manual reaction time paradigm.Results The differences of reaction time in orthographic,phonetic and semantic judgment and the error rates in orthographic and semantic judgment between both groups were not significant(P>0.05);however,the difference of error rate in phonetic judgment between the both groups were nearly significant(P=0.053).Conclusion The only disability existed in developmental stutterers seems to be the in phonetic abstracting or encoding processes,which is partly in accordance with the covert repair hypothesis.

Air Traffic Controller Shiftwork: What are the Implications for Aviation Safety? A Review

Most civilian and air traffic control facilities in the United States use rapid shift schedules. These schedules have generally been chosen for social reasons. Safety concerns have been raised because the air traffic controllers (ATCs) often carry an acute sleep dept onto the night-shift where they have little active work to do as they sit in the dark at the nadir of their circadian rhythms. This paper reviews advancing and delaying rapid shiftwork schedules, ATC workload factors as they relate to error rates and safety, and potential countermeasures. Recent studies indicate that ATC performance declines on the night-shift and that ATCs may be falling asleep while on-duty. There is indirect evidence that ATC error rates are highest on the night-shift. There are only limited studies which have evaluated potential countermeasures. The operational significance of the problems associated with ATC shiftwork is not yet clear. Further study is needed