Com fer una anàlisi quantitativa de dades de tipus descriptiu amb el paquet estadístic de l"SPSS?

En l"actualitat és difícil parlar de processos estadístics d"anàlisi quantitativa de dades sense fer referència a la informàtica aplicada a la recerca. Aquests recursos informàtics es basen sovint en paquets de programes informàtics que tenen l"objectiu d"ajudar al/a la investigador/a en la fase d"anàlisi de dades. En aquests moments un dels paquets més perfeccionats i complets és l"SPSS (Statistical Package for the Social Sciences). L"SPSS és un paquet de programes per tal de dur a terme l"anàlisi estadística de les dades. Constitueix una aplicació estadística força potent, de la qual s"han anat desenvolupant diverses versions des dels seus inicis, als anys setanta. En aquest manual les sortides d"ordinador que es presenten pertanyen a la versió 11.0.1. No obstant això, tot i que la forma ha anat variant des dels inicis, pel que fa al funcionament segueix essent molt similar entre les diferents versions. Abans d"iniciar-nos en la utilització de les aplicacions de l"SPSS és important familiaritzarse amb algunes de les finestres que més farem servir. En entrar a l"SPSS el primer que ens trobem és l"editor de dades. Aquesta finestra visualitza, bàsicament, les dades que anirem introduint. L"editor de dades inclou dues opcions: la Vista de les dades i la de les variables. Aquestes opcions es poden seleccionar a partir de les dues pestanyes que es presenten en la part inferior. La vista de dades conté el menú general i la matriu de dades. Aquesta matriu s"estructura amb els casos a les files i les variables a les columnes.

Empirical study of correlated survival times for recurrent events with proportional hazards margins and the effect of correlation and censoring.

Background: In longitudinal studies where subjects experience recurrent incidents over a period of time, such as respiratory infections, fever or diarrhea, statistical methods are required to take into account the within-subject correlation. Methods: For repeated events data with censored failure, the independent increment (AG), marginal (WLW) and conditional (PWP) models are three multiple failure models that generalize Cox"s proportional hazard model. In this paper, we revise the efficiency, accuracy and robustness of all three models under simulated scenarios with varying degrees of within-subject correlation, censoring levels, maximum number of possible recurrences and sample size. We also study the methods performance on a real dataset from a cohort study with bronchial obstruction. Results: We find substantial differences between methods and there is not an optimal method. AG and PWP seem to be preferable to WLW for low correlation levels but the situation reverts for high correlations. Conclusions: All methods are stable in front of censoring, worsen with increasing recurrence levels and share a bias problem which, among other consequences, makes asymptotic normal confidence intervals not fully reliable, although they are well developed theoretically.

Com optimitzar una matriu de dades? Utilitats bàsiques de l"SPSS

Una vegada es disposa de les dades introduïdes al paquet estadístic de l"SPSS (Statistical Package of Social Science) en una matriu de dades, és el moment de plantejar-se optimitzar aquesta matriu per poder extreure el màxim rendiment a les dades, segons el tipus d"anàlisi que es pretengui dur a terme. Per a això, el mateix SPSS té una sèrie d"utilitats que poden ser de gran utilitat. Aquestes utilitats bàsiques poden diferenciar-se segons la seva funcionalitat entre: les utilitats per a l"edició de dades, les utilitats per a la modificació de variables i les opcions d"ajuda que ens brinda. A continuació es presenten algunes d"aquestes utilitats.

Chemical characterization of tin-lead glazed ceramics from Aragon (Spain) by neutron activation analysis

Majolica pottery was the most characteristic tableware produced in Spain during the Medieval and Renaissance periods. A study of the three main production centers in the historical region of Aragon during Middle Ages and Renaissance was conducted on a set of 71 samples. The samples were analyzed by instrumental neutron activation analysis (INAA), and the resulting data were interpreted using an array of multivariate statistical procedures. Our results show a clear discrimination among different production centers allowing a reliable provenance attribution of ceramic sherds from the Aragonese workshops.

Exploring Compositional Data with the CoDa-Dendrogram

Within the special geometry of the simplex, the sample space of compositional data, compositional orthonormal coordinates allow the application of any multivariate statistical approach. The search for meaningful coordinates has suggested balances (between two groups of parts)—based on a sequential binary partition of a D-part composition—and a representation in form of a CoDa-dendrogram. Projected samples are represented in a dendrogram-like graph showing: (a) the way of grouping parts; (b) the explanatory role of subcompositions generated in the partition process; (c) the decomposition of the variance; (d) the center and quantiles of each balance. The representation is useful for the interpretation of balances and to describe the sample in a single diagram independently of the number of parts. Also, samples of two or more populations, as well as several samples from the same population, can be represented in the same graph, as long as they have the same parts registered. The approach is illustrated with an example of food consumption in Europe

Measuring Intermediary Determinants of Early Childhood Health: A Composite Index Comparing Colombian Departments

In recent years there has been growing interest in composite indicators as an efficient tool of analysis and a method of prioritizing policies. This paper presents a composite index of intermediary determinants of child health using a multivariate statistical approach. The index shows how specific determinants of child health vary across Colombian departments (administrative subdivisions). We used data collected from the 2010 Colombian Demographic and Health Survey (DHS) for 32 departments and the capital city, Bogotá. Adapting the conceptual framework of Commission on Social Determinants of Health (CSDH), five dimensions related to child health are represented in the index: material circumstances, behavioural factors, psychosocial factors, biological factors and the health system. In order to generate the weight of the variables, and taking into account the discrete nature of the data, principal component analysis (PCA) using polychoric correlations was employed in constructing the index. From this method five principal components were selected. The index was estimated using a weighted average of the retained components. A hierarchical cluster analysis was also carried out. The results show that the biggest differences in intermediary determinants of child health are associated with health care before and during delivery.

Measuring early childhood health : a composite index comparing Colombian departments

This paper presents a composite index of early childhood health using a multivariate statistical approach. The index shows how child health varies across Colombian departments, -administrative subdivisions-. In recent years there has been growing interest in composite indicators as an efficient analysis tool and a way of prioritizing policies. These indicators not only enable multi-dimensional phenomena to be simplified but also make it easier to measure, visualize, monitor and compare a country’s performance in particular issues. We used data collected from the Colombian Demographic and Health Survey, DHS, for 32 departments and the capital city, Bogotá, in 2005 and 2010. The variables included in the index provide a measure of three dimensions related to child health: health status, health determinants and the health system. In order to generate the weight of the variables and take into account the discrete nature of the data, we employed a principal component analysis, PCA, using polychoric correlation. From this method, five principal components were selected. The index was estimated using a weighted average of the components retained. A hierarchical cluster analysis was also carried out. We observed that the departments ranking in the lowest positions are located on the Colombian periphery. They are departments with low per capita incomes and they present critical social indicators. The results suggest that the regional disparities in child health may be associated with differences in parental characteristics, household conditions and economic development levels, which makes clear the importance of context in the study of child health in Colombia.

A measure of stability as a criterion for the verification and analysis of simulation models

The aim of this study is to define a new statistic, PVL, based on the relative distance between the likelihood associated with the simulation replications and the likelihood of the conceptual model. Our results coming from several simulation experiments of a clinical trial show that the PVL statistic range can be a good measure of stability to establish when a computational model verifies the underlying conceptual model. PVL improves also the analysis of simulation replications because only one statistic is associated with all the simulation replications. As well it presents several verification scenarios, obtained by altering the simulation model, that show the usefulness of PVL. Further simulation experiments suggest that a 0 to 20 % range may define adequate limits for the verification problem, if considered from the viewpoint of an equivalence test.

Análisis Discriminante mediante SPSS.

El análisis discriminante es un método estadístico a través del cual se busca conocer qué variables, medidas en objetos o individuos, explican mejor la atribución de la diferencia de los grupos a los cuales pertenecen dichos objetos o individuos. Es una técnica que nos permite comprobar hasta qué punto las variables independientes consideradas en la investigación clasifican correctamente a los sujetos u objetos. Se muestran y explican los principales elementos que se relacionan con el procedimiento para llevar a cabo el análisis discriminante y su aplicación utilizando el paquete estadístico SPSS, versión 18, para el desarrollo del modelo estadístico, las condiciones para la aplicación del análisis, la estimación e interpretación de las funciones discriminantes, los métodos de clasificación y la validación de los resultados.

Chemical characterization of tin-lead glazed pottery from the Iberian Peninsula and the Canary Islands: initial steps toward a better understanding of Spanish Colonial pottery in Americas

Majolica pottery was the most characteristic tableware produced in Europe during the Medieval and Renaissance periods. Because of the prestige and importance attributed to this ware, Spanish majolica was imported in vast quantities into the Americas during the Spanish Colonial period. A study of Spanish majolica was conducted on a set of 186 samples from the 10 primary majolica production centres on the Iberian Peninsula and 22 sherds from two early colonial archaeological sites on the Canary Islands. The samples were analysed by neutron activation analysis (NAA), and the resulting data were interpreted using an array of multivariate statistical approaches. Our results show a clear discrimination between different production centres, allowing a reliable provenance attribution of the sherds from the Canary Islands.