ABSTRACT
Introducción: el análisis estadístico se divide en dos componentes: el análisis descriptivo y el análisis inferencial, las pruebas estadísticas, se fraccionan en paramétricas y no paramétricas. Sin embargo, la elección de una prueba estadística apropiada, representa un reto. Objetivo: proponer una herramienta, que sirva para seleccionar una prueba estadística a aquellos no expertos en bioestadística, para las investigaciones biomédicas. Métodos: se realizó un estudio tipo revisión bibliográfica narrativa. Se partió de una revisión de la literatura sobre las principales pruebas estadísticas que se utilizan en la actualidad, disponibles en la literatura de las bases de datosbibliográficas como Pubmed/Medline, SciELO, SCOPUS, Springer, Web of Science, EBSCOhost entre otras. Dicha herramienta fue validada por criterio de expertos. Resultados: se diseñó un esquema, el que puede utilizarse de dos maneras: la primera consiste seguir el esquema hasta descubrir cuál es la técnica estadística apropiada para sus datos y la segunda: siguiendo el esquema hacia atrás, determinar si la prueba fue una elección lógica para los datos analizados. Para usarla, debe identificar variables dependientes e independientes, después llegará a una medida de síntesis o a una estimación puntual útil para sus datos, que irá seguida de una clasificación general de las pruebas estadísticas. Conclusiones: la guía propuesta es un intento de aportar una guía útil para seleccionar una técnica estadística para el análisis de datos en las investigaciones biomédicas.
Introduction: statistical analysis is divided into two components: descriptive analysis and inferential analysis, statistical tests, are divided into parametric and nonparametric. Choosing an appropriate statistical test, however, is challenging. Objective: to propose a tool, which serves to select a statistical test to those not experts in biostatistics, for biomedical research. Methods: a narrative literature review study was conducted. It was based on a review of the literature on the main statistical tests currently used, available in the literature of bibliographic databases such as Pubmed/Medline, SciELO, SCOPUS, Springer, Web of Science, EBSCOhost among others. This tool was validated by expert criteria. Results: a scheme was designed, which can be used in two ways: the first is to follow the scheme until discovering which is the appropriate statistical technique for your data and the second: following the scheme backwards, determine if the test was a logical choice for the analyzed data. To use it, you must identify dependent and independent variables, then you will arrive at a synthesis measure or a useful point estimate for your data, which will be followed by a general classification of statistical tests. Conclusions: the proposed guideline is an attempt to provide a useful guide to select a statistical technique for data analysis in biomedical research.
Introdução: a análise estatística é dividida em dois componentes: análise descritiva e análise inferencial, testes estatísticos, são divididos em paramétricos e não paramétricos. Escolher um teste estatístico apropriado, no entanto, é um desafio. Objetivo: propor uma ferramenta, que sirva para selecionar um teste estatístico para aqueles que nãosão especialistas em bioestatística, para pesquisa biomédica. Métodos: realizou-se um estudo de revisão narrativa da literatura. Baseou-se em uma revisão da literatura sobre os principais testes estatísticos atualmente utilizados, disponíveis na literatura de bases de dados bibliográficas como Pubmed/Medline, SciELO, SCOPUS, Springer, Web of Science, EBSCOhost entre outras. Esse instrumento foi validado por critérios de especialistas. Resultados: foi elaborado um esquema, que pode ser utilizado de duas formas: a primeira é seguir o esquema até descobrir qual é a técnica estatística apropriada para seus dados e a segunda: seguindo o esquema de trás para frente, determinar se o teste foi uma escolha lógica para os dados analisados. Para usá-lo, você deve identificar variáveis dependentes e independentes, então você chegará a uma medida de síntese ou uma estimativa pontual útil para seus dados, que será seguida por uma classificação geral de testes estatísticos. Conclusões: a diretriz proposta é uma tentativa de fornecer um guia útil para selecionar uma técnica estatística para análise de dados em pesquisa biomédica.
ABSTRACT
Aim: Physicochemical assessment of the surface water sourced from River Ebenyi and its tributaries in Eha-Amufu and environs, Isu-Uzo Local Government Area of Enugu State of Nigeria. Place and Duration: Eha-Amufu and environs, Isu-Uzo Local Government Area of Enugu State of Nigeria. May to July, 2017. Study Design: Experimental design. Methodology: Water samples were spatially collected along the river and stream channels in Eha-Amufu and the adjoining Ihenyi, Amaede, Mgbuji, Umuhu, Agamede and Odobudo villages. Parameters analysed include pH, dissolved oxygen (DO), biological oxygen demand (BOD), chemical oxygen demand (COD), Total hardness (TH), Lead (Pb), Copper (Cu), Cadmium (Cd), Chromium (Cr), Zinc (Zn), Nitrate, Phosphate, Chloride, and Sulphate. Results: The concentrations of Cd (0.02-0.05 mg/l) and Pb (0.37-0.77 mg/l) exceeded the maximum limit of the range of values considered as safe by the World Health Organisation (WHO). Conductivity (37.14 – 63.30 µs/cm), Total dissolved solids (TDS) (10.80 – 30.80 mg/l), Total suspended solids (TSS) (10.60 – 21.20 mg/l) and Total solid (TS) (20.60-41.00 mg/l) were within the lower limit of the permissible range of values. Chromium (0.26 ± 0.00 mg/l) exceeded the maximum permissible limit at Agamede village. Sulphate was statistical significantly higher (χ2 = 25.697, p < 0.001) relative to the spatial concentrations of nitrate (4.28 – 11.18 mg/l), sulphate (13.68 – 25.23 mg/l), phosphate (0.00 – 0.28 mg/l) and chloride (9.11 – 15.50 mg/l) in the area. Conclusions: The baseline results obtained from this study with regards to Cd, Cr and Pb demands that effective health education programme should be organised to emphasize on the effect of anthropogenic activities that releases pollutants. However, long term sampling covering all the months of the year is needed in order to confirm the reproducibility of our results.
ABSTRACT
In the past decade,based on the “common disease-common variant” hypothesis,genomewide association studies (GWAS) have been extensively used to dissect the genetic components of complex diseases and quantitative traits.However,the identified disease-associated common variants by GWASs can only explain small part of the corresponding disease heritability.“Common disease-rare variant” hypothesis has been proposed to explore the missed heritability.With the development of the next generation sequencing technology,various association studies of less common variants are ongoing.This paper provides an overview of the study designs and statistical tests of these variants.
ABSTRACT
In the past decade,based on the “common disease-common variant” hypothesis,genomewide association studies (GWAS) have been extensively used to dissect the genetic components of complex diseases and quantitative traits.However,the identified disease-associated common variants by GWASs can only explain small part of the corresponding disease heritability.“Common disease-rare variant” hypothesis has been proposed to explore the missed heritability.With the development of the next generation sequencing technology,various association studies of less common variants are ongoing.This paper provides an overview of the study designs and statistical tests of these variants.
ABSTRACT
Resumen Los estudios sobre los equinodermos de la costa del Pacifico de México se han enfocado en la taxonomía y biogeografía y hay escasos datos sobre ecología comunitaria o poblacional del grupo. En el presente trabajo analizamos los cambios estacionales de la densidad poblacional y la distribución espacial de cuatro especies de erizos regulares (Diadema mexicanum, Echinometra mathaei oblonga. Eucidaris thouarsii y Tripneustes depressus) en tres bahías de la Isla Socorro, Archipiélago de Revillagigedo, México. Las especie más abundante en la isla fue E. mathaei oblonga (3.96 + 0.83 ind m-2; promedio y error típico), seguida de D. mexicanum (2.13 + 0.59 ind m-2), T. depressus y E. thouarsii (entre 0.50 y 0.11 ind m-2, respectivamente). La Bahía Binners tuvo la mayor densidad con 15.98 + 0.43 ind m-2, en gran medida debido a la alta incidencia de E. mathaei oblonga en el sitio. Estacionalmente, T. depressus y E. thouarsii no variaron significativamente su abundancia durante el año, pero D. mexicanum fue más abundante en invierno-primavera, y E. mathaei oblonga en el otoño. En relación al patrón de distribución espacial, dos de las especies (D. mexicanum y E. mathaei oblonga) presentaron una distribución agregada a lo largo del año y en las tres localidades de estudio, pero los otros dos equinoideos se dispusieron de forma azarosa. Hay varias razones para explicar el comportamiento de agregación en erizos de mar, pero para el caso de Isla Socorro aquí se argumenta a favor de que es un modo de defensa contra los abundantes peces depredadores que habitan los arrecifes. En contraste, las especies que no muestran agrupaciones residen en refugios durante el día (E. thouarsii) o bien su morfología y tamaño dificultan su captura por los peces (T. depressus).
Abstract The studies on echinoderms of the Mexican Pacific have focused on taxonomy and biogeography, and there are limited data on their ecology. We used transect to study Diadema mexicanum, Echinometra mathaei oblonga, Eucidaris thouarsii and Tripneustes depressus at three bays in Socorro Island, Revillagigedo Archipelago, Mexico (1989 and 1990). The most abundant species in the island was E. mathaei oblonga (3.96 + 0.83 ind m-2; average and standard error), followed by D. mexicanum (2.13 + 0.59 ind m-2), T. depressus and E. thouarsii (between 0.50 and 0.11 ind m-2, respectively). Binners Bay had the highest density with 15.98 + 0.43 ind m-2, mostly due to the high incidence of E. mathaei oblonga at the site. Seasonally, T. depressus and E. thouarsii did not significantly varied its abundance during the year, while D. mexicanum was more abundant in winter-spring, and E. mathaei oblonga in the fall. Two species (D. mexicanum and E. mathaei oblonga) had an aggregated distribution along the year and in the three study locations, but the other two echinoids followed a random distribution. This may be a defense against the abundant predatory fishes. In contrast, the species that do not aggregate inhabit in refuges during the day (E. thouarsii), or their shape and size makes them difficult to capture by fishes (T. depressus). Rev. Biol. Trop. 63 (Suppl. 2): 221-232. Epub 2015 June 01.
Subject(s)
Animals , Sea Urchins/growth & development , Population Density , MexicoABSTRACT
Key Message: Statistics Open For All (SOFA) is a free, open-source statistical software. It contains a component to help choose the appropriate statistical test. This article describes that component from the perspective of a novice user. We also discuss the pros and cons of this tool, and make appropriate recommendations for its use.
Subject(s)
Models, Statistical , Software/methods , Software/statistics & numerical data , Statistics, Nonparametric , Teaching/methodsABSTRACT
Drying kinetics of quinoa-supplemented feed for laboratory rats during processing at 50, 60, 70, 80 and 90ºC was studied and modeled in this work. Desorption isotherm was obtained at 60ºC giving a monolayer moisture content of 0.04 g water/g d.m. The experimental drying curves showed that drying process took place only in the falling rate period. Several thin-layer drying equations available in the literature were evaluated based on determination coefficient (r²), sum squared errors (SSE) and Chi-square (χ2) statisticals. In comparison to the experimental moisture values, the values estimated with the Logarithmic model gave the best fit quality (r² >0.994, SSE < 0.00015 and χ2 < 0.00018), showing this equation could predict very accurately the drying time of rat feed under the operative conditions applied.
ABSTRACT
Statistical tests are commonly reported in papers published in the journal. The interpretation of the statistical results, however, is not necessarily proper, which may invalidate the conclusions. This paper describes the issues regarding the interpretation of the results of statistical tests in the journal, and refers to the proper use of statistical test and estimation.