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

The purpose of this paper was to introduce the calculation formulas and the SAS implementation of the analysis of variance of the univariate quantitative data with the Latin square design. The Latin square design could be divided into two categories： the general Latin square design and the Greek Latin square design. The former could be used for the experimental situation with one experimental factor and two block factors， the latter could be used for the experimental situation with two experimental factors and two block factors. In fact， Latin square designs could be further subdivided by whether or not the repeated experiments were performed and whether the block factor was a single individual type. Generally speaking， in addition to satisfying the requirements of "independence， normality and homogeneity of variance"， the interaction between all factors was required to be non-existent or negligible when performing an analysis of variance on the quantitative data with Latin square design. When the quantitative data did not meet the preconditions mentioned above， it was recommended to use a mixed-effects model to build the model and solve it， or to solve the estimated values of the parameters in the ANOVA model based on the generalized estimating equation method.

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

The purpose of the paper was to introduce the calculation formulas and the SAS implementation of the analysis of variance for the quantitative data of the crossover design. In the calculation， three test statistics were involved， namely Ftreatment， Fstage and Findividual. They were three test statistics used to evaluate the statistical significance of the effect of the treatment factor， the stage factor， and the individual factor on the quantitative outcome variable， respectively. In general， it was assumed that there was no or negligible interaction among the three factors in a crossover design， so there was no need to evaluate whether the interaction term was statistically significant. With the help of SAS software， this paper conducted the univariate analysis of variance for the quantitative data of crossover designs for three examples of 2×2 crossover design， 3×3 crossover design and three-stage crossover design， and presented the calculation results and drew the statistical and professional conclusions.

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

The purpose of this paper was to introduce the model， calculation formulas and the SAS implementation of the analysis of variance for the quantitative data with balanced incomplete block design. In the calculation， two test statistics were involved， namely FA and FB. Among them， the subscript "A" represented the experimental factor， and the subscript "B" represented the block factor B （i.e.， the important non-experimental factor）. In general， it was assumed that there was no or negligible interaction between the two factors in a balanced incomplete block design， so there was no need to evaluate whether the interaction term was statistically significant. Therefore， it was not necessary to do repeated experiments under each combination of two factors. With the help of SAS software， this paper conducted the analysis of variance for the quantitative data with balanced incomplete block design on two examples， and presented the calculation results and made the statistical and professional conclusions.

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

The purpose of this paper was to introduce the model， calculation formulas and the SAS implementation of the univariate analysis of variance for the quantitative data with randomized complete block design. In the calculation， two test statistics were involved， namely FA and FB. Among them， the subscript "A" represented the experimental factor， and the subscript "B" represented the block factor （i.e.， the important non-experimental factor）. In general， it was assumed that there was no or negligible interaction between the two factors in a randomized block design， so there was no need to assess whether the interaction term was statistically significant. Therefore， it was not necessary to do repeated experiments under each combination of two factors. With the help of SAS software， this paper conducted the analysis of variance for the quantitative data with randomized complete block design for two instances without and with repeated experiments， gave the calculation results， and made the statistical and professional conclusions.

How to use χ2 test correctly——the rank sum tests and the implementation of the SAS software / 四川精神卫生

The purpose of this article was to introduce the rank sum test and its SAS implementation. The concrete contents included the following three aspects： ①the simple linear rank test of two-sample data， ②the one-way ANOVA rank sum test of the multi-sample data， ③the "scoring methods" in the aforementioned two situations. In the third aspect above， there were 10 concrete scoring approaches. Based on an example and with the aid of the SAS software， the paper implemented the first-type rank sum test previously， explained the output results， and made statistical and professional conclusions.

El registro y la medición de la criminalidad. El problema de los datos faltantes y el uso de la ciencia para producir estimaciones en relación con el homicidio en Colombia, demostrado a partir de un ejemplo: el departamento de Antioquia (2003-2011) / Criminality registration and measurement. The problem of missing data, and the use of science to produce estimations relating to homicide in Colombia, as demonstrated with an example from one of its administrative and political divisions: the Department of Antioquia (2003-2011) / O registro e a medição da criminalidade. O problema dos dado faltantes e o uso da ciência para produzir estimativas com relação ao homicídio na Colômbia, demonstrado a partir de um exemplo: o departamento de Antioquia (2003-2011)

La integridad del ciclo de políticas públicas depende de la calidad de la información disponible para tomar decisiones en cualquiera de las fases. De manera preocupante, este ciclo -especialmente en el campo de la política criminal- se aparta del análisis técnico, que debería basarse en prueba empírica y sustento teórico. Este artículo retoma ejes clásicos (pero olvidados) de la medición de la criminalidad, con el propósito de resaltar la función esencial de datos confiables en el ciclo de políticas públicas. Brinda un análisis del proceso de registro y medición del crimen, y destaca los problemas y límites de cualquier ejercicio de registro delictivo. Resalta la necesidad de examinar el universo de lo desconocido por los diversos proyectos de registro, y explica las herramientas que se utilizan para dar cuenta de datos faltantes. Con el fin de ilustrar el potencial de la aplicación de estas herramientas en Colombia, ilustra los resultados del registro integrado de homicidios en el departamento de Antioquia, en el período 2003-2011, según cinco proyectos de registro (incluyendo el de la Policía Nacional), y presenta una estimación probabilística de los homicidios, que incorpora el cálculo de los datos faltantes según un técnica que se denomina Estimación por Sistemas Múltiples (ESM).

The integrity of the public policy cycle depends upon the quality of information available to make decisions in any of the relevant phases. In a disturbing manner, this cycle -and particularly in the field of criminal policy- diverges from the technical analysis that should be based on empiric proof and theoretical justification and support. This article retakes classical -though forgotten- axes of criminality measurement, for the purpose of stressing the essential function of reliable data in the public policy cycle. It offers an analysis of the registration and measurement process, and highlights both problems and limits involved in any crime registration exercise. It points out the need to examine the universe of what has been ignored in the diverse registration projects, and explains the tools used to account for the missing data. In order to illustrate the potential involved in the application of these tools in Colombia, it exemplifies the results found in the integrated homicide record keeper in one of the Colombian 32 administrative and political divisions: the Department of Antioquia, in the 2003-2011 period, pursuant to five registration projects (including that of the National Police); and it offers a probabilistic estimation of homicides incorporating the calculation of missing data, according to a technique known as the Multiple Systems Estimation (MSE).

A integridade do ciclo de políticas públicas depende da qualidade da informação disponível para fazer decisões em qualquer uma das fases. De maneira preocupante, este ciclo - especialmente no campo da política criminal - afasta-se da análise técnica, que teria que ser baseada no teste empírico e no apoio teórico. Este artigo retoma eixos clássico (mas esquecidos) da medição da criminalidade, a fim de enfatizar a função essencial de dados fiáveis no ciclo de políticas públicas. Oferece uma análise do processo do registo e medição do crime, e destaca os problemas e os limites de todo o exercício do registo criminal. Resalta a necessidade para examinar o universo do desconhecido pelos diversos projetos de registo, e explica as ferramentas que são usadas para apresentar os dados faltantes. A fim de ilustrar o potencial da aplicação destas ferramentas na Colômbia, ilustra os resultados do registro integrado dos homicídios no departamento de Antioquia, no período 2003-2011, de acordo com cinco projetos de registro (incluindo aquele da Polícias Nacional), e apresenta uma estimativa probabilística dos homicídios, que incorpora o cálculo dos dados faltantes de acordo com uma técnica chamada estimativa por múltiplos sistemas.

Exploración de la violencia sexual en la ciudad de Bogotá: una aplicación de técnicas de minería de datos / Exploration of sexual violence in the city of Bogota: aplication of a data mining technique / Exploração da violência sexual na cidade de Bogotá: uma aplicação das técnicas da mineração dos dados

Este estudio ofrece una aproximación a la violencia sexual utilizando datos de fuente secundaria y aplicando algunas técnicas de minería de datos. La fuente de datos utilizada es el Instituto Nacional de Medicina Legal y Ciencias Forenses, y los algoritmos aplicados son Selección por Características, C5.0 y K-Means. Antes de la aplicación de dichas técnicas se hace una aproximación teórica a la violencia sexual, para apreciar la forma como se ha abordado este tipo de violencia y la manera como se ha analizado. Seguidamente se realiza la evaluación de la calidad de los datos y se aplican algunos tratamientos para su mejoramiento. Una vez se llega a un dataset adecuado para el procesamiento y análisis, se aplican técnicas de minería de datos y se establece como variable objetivo o respuesta la relación del presunto agresor con la víctima. Las salidas que ofrece el procesamiento llevan a un análisis que establece como centro los niveles de proximidad con la víctima y cuestiona los análisis basados en la estructura de parentesco tradicional, al mismo tiempo que valida la distinción que establece una clasificación de la violencia sexual entre abuso sexual y asalto sexual. Los análisis del ejercicio de minería de datos permiten plantear claramente la configuración de dos clusters a los que se les puede señalar con dicha clasificación. Estos están acompañados de un tercero que, si bien no está muy definido, empieza a dibujarse. Los tres clusters se han llamado violencia sexual en situación de incesto, violencia sexual en situación de anonimia y violencia sexual en situación de estructura familiar. Se termina con algunas sugerencias en procura del mejoramiento de la calidad de los datos y se plantean las posibilidades que este tipo de análisis tiene al intentar dar respuesta a la conflictividad, la violencia y el delito

This study offers an approach to sexual violence by using secondary source data and applying some data mining techniques. The data source used is the ‘Instituto Nacional de Medicina Legal y Ciencias Forenses’ (National Institute of Legal Medicine and Forensic Sciences), and the algorithms applied are Selection by Characteristics, C5.0, and K-Means.Prior to applying these techniques, a theoretical approximation to sexual violence is made in order to appreciate how this kind of violence has been approached and analyzed. ubsequently, data quality is assessed and some improvement treatments are applied. Upon having reached a proper dataset for processing and analysis, data mining techniques are applied, and the relationship of the alleged aggressor to the victim is established as a variable objective or answer. The issues or solutions offered by the above data processing lead to an analysis which establishes as a core the levels of proximity with the victim, and questions those studies based on the traditional kinship structure, while it simultaneously validates the distinction that establishes a sexual violence rating between abuse and assault. Analyses of the data mining exercise facilitate a clear statement of the configuration of two clusters that can be pointed at with said classification. They are accompanied by a third one that, although not well defined yet, begins to appear. The three clusters have been designated as sexual violence in an incest situation, sexual violence in an anonymity situation, and sexual violence in a family structure situation.Finally, some suggestions are given in seeking to improve data quality, while the opportunities this type of analysis opens at attempting to give an answer to conflictivity, violence and crime are outlined

Este estudo oferece uma aproximação à violência sexual usando dados da fonte secundária e aplicando algumas técnicas da mineração dos dados. A fonte dos dados usada é ao Instituto Nacional de Medicina Legal e Ciências Forenses, e os algoritmos aplicados são Seleção por Característica, C5.0 e K-Means. Antes que a aplicação destas técnicas, uma aproximação teórica à violência sexual é feita, para apreciar o jeito como este tipo de violência é abordado e a maneira como foi analisado. A avaliação da qualidade dos dados é feita em seguida e alguns tratamentos para sua melhoria são aplicados. Uma vez que o dataset adequado é alcançado para o processamento e a análise, as técnicas da mineração dos dados são aplicadas e a relação do suposto agressor com a vítima é estabelecida com a variável alvo ou a resposta. As saídas que fornece o processamento leva a uma análise que estabelece como o centro os níveis da proximidade com a vítima e questiona as análises baseadas na estrutura do parentesco tradicional, ao mesmo tempo em que valida à distinção que estabelece uma classificação da violência sexual entre o abuso sexual e o assalto sexual. As análises do exercício da mineração dos dados permitem expor claramente a configuração de dois clusters aos quais é possível assinalar com esta classificação. Estes são acompanhados de um terceiro que, embora não esteja bem definido, começam a extrair-se. Os três clusters foram chamados violência sexual na situação do incesto, violência sexual na situação de anonímia e a violência sexual na situação da estrutura familiar. Termina com algumas sugestões nas tentativas da melhoria da qualidade dos dados e expor as possibilidades que este tipo de análise tem ao tentar dar resposta aos conflitos, à violência e ao crime

Discrimination and explanation of statistical errors in the analysis of quantitative data / 基础医学与临床

In this paper,a great many examples of misusing statistics analyzing the quantitative data are unveiled. Obviously,it is extremely important for people to process the quantitative data correctly by checking the preconditons of data and discriminating the types of experimental designs. It is necessary for researchers to learn more knowledge of how to analyze the quantitative data rationally, so it is important to develop qualified text book to support the education.