Serveis Tècnics de Recerca. Unitat d'Assessorament Estadístic

La Unitat d’Assessorament Estadístic es va crear el passat mes de març i es va incorporar als Serveis Tècnics de Recerca. La seva creació respon a la necessitat cada vegada més gran que hi ha a la Universitat de Girona d’una gestió i interpretació eficaç dels resultats que proporcionen les bases de dades. També era una necessitat per a institucions i empreses del territori, perquè a Girona no hi havia cap servei d’aquestes característiques

Aitchison Geometry for Probability and Likelihood as a new approach to mathematical statistics

The Aitchison vector space structure for the simplex is generalized to a Hilbert space structure A2(P) for distributions and likelihoods on arbitrary spaces. Centralnotations of statistics, such as Information or Likelihood, can be identified in the algebraical structure of A2(P) and their corresponding notions in compositional data analysis, such as Aitchison distance or centered log ratio transform.In this way very elaborated aspects of mathematical statistics can be understoodeasily in the light of a simple vector space structure and of compositional data analysis. E.g. combination of statistical information such as Bayesian updating,combination of likelihood and robust M-estimation functions are simple additions/perturbations in A2(Pprior). Weighting observations corresponds to a weightedaddition of the corresponding evidence.Likelihood based statistics for general exponential families turns out to have aparticularly easy interpretation in terms of A2(P). Regular exponential families formfinite dimensional linear subspaces of A2(P) and they correspond to finite dimensionalsubspaces formed by their posterior in the dual information space A2(Pprior).The Aitchison norm can identified with mean Fisher information. The closing constant itself is identified with a generalization of the cummulant function and shown to be Kullback Leiblers directed information. Fisher information is the local geometry of the manifold induced by the A2(P) derivative of the Kullback Leibler information and the space A2(P) can therefore be seen as the tangential geometry of statistical inference at the distribution P.The discussion of A2(P) valued random variables, such as estimation functionsor likelihoods, give a further interpretation of Fisher information as the expected squared norm of evidence and a scale free understanding of unbiased reasoning

Aitchison Geometry for Probability and Likelihood as a new approach to mathematical statistics

The Aitchison vector space structure for the simplex is generalized to a Hilbert space structure A2(P) for distributions and likelihoods on arbitrary spaces. Central notations of statistics, such as Information or Likelihood, can be identified in the algebraical structure of A2(P) and their corresponding notions in compositional data analysis, such as Aitchison distance or centered log ratio transform. In this way very elaborated aspects of mathematical statistics can be understood easily in the light of a simple vector space structure and of compositional data analysis. E.g. combination of statistical information such as Bayesian updating, combination of likelihood and robust M-estimation functions are simple additions/ perturbations in A2(Pprior). Weighting observations corresponds to a weighted addition of the corresponding evidence. Likelihood based statistics for general exponential families turns out to have a particularly easy interpretation in terms of A2(P). Regular exponential families form finite dimensional linear subspaces of A2(P) and they correspond to finite dimensional subspaces formed by their posterior in the dual information space A2(Pprior). The Aitchison norm can identified with mean Fisher information. The closing constant itself is identified with a generalization of the cummulant function and shown to be Kullback Leiblers directed information. Fisher information is the local geometry of the manifold induced by the A2(P) derivative of the Kullback Leibler information and the space A2(P) can therefore be seen as the tangential geometry of statistical inference at the distribution P. The discussion of A2(P) valued random variables, such as estimation functions or likelihoods, give a further interpretation of Fisher information as the expected squared norm of evidence and a scale free understanding of unbiased reasoning

Lliçó inaugural: "Girona, universitat europea"

En l'acte d'inauguració del curs acadèmic de la Universitat de Girona 2008-2009, el senador i president de l'Assemblea del Consell d'Europa, Lluís Maria de Puig, parla de la construcció europea i del desig que la Universitat de Girona s'insereixi plenament en aquest procés. Desenvolupa aquesta idea a partir de tres aspectes: el paper de la universitat avui, el procés de Bolonya, i la Universitat de Girona i Europa

La Universitat Lliure de Girona (1870-1874)

La manera com s'han tractat jurídicament els principis d'igualtat i llibertat educativa en el segle XIX ens mostra aquells espais on Església i Estat, conservadors i revolucionaris, s'enfrontaren pel control de la joventut i de l'educació com aquell element del que se'n fa dependre el progrés de la societat. En aquest context, i a l'empara de la política educativa liberal del sexenni revolucionari, sorgeix i viu durant els quatre cursos que van de 1870 a 1874 una universitat, la qual, alhora que reclamava ser l'hereva dels estudis universitaris gironins clausurats per Felip V, pretenia fer-se un lloc en el complex mapa universitari i ideològic català i espanyol. Amb aquesta recerca veurem si efectivament es va poder instituir una universitat lluny dels cànons de l'ortodòxia científica i acadèmica marcats per l'Església i l'Estat en l'època isabelina, si van cobrir-se les necessitats educatives reals de la Girona del darrer terç del segle XIX i mantenir-se les prescripcions i exigències de l'ensenyament superior.

Mirades turístiques a la ciutat. Anàlisi del comportament dels visitants del Barri Vell de Girona

Mirades Turístiques a la ciutat és un estudi sobre el comportament del turisme en les ciutats monumentals, a partir de l'experiència viscuda pels visitants del Barri Vell de Girona. Una recerca que ha pretès determinar, precisament, la forma com els visitants entren en contacte amb el patrimoni monumental de la ciutat medieval. A partir, d'identificar quins factors influeixen (i quins no) en el comportament dels turistes durant la seva visita, tant pel que fa referència als factors ambientals generals (la meteorologia, la congestió, la informació...) com els factors singulars de cada visitant. Per tal d'assolir aquests objectius, en hem plantejat una sèrie d'hipòtesis de treball: 1. Existeix una manera turística d'apropar-se al patrimoni que té les seves pròpies regles, les seves estructures específiques i en conseqüència la necessitat d'uns instruments de gestió particulars. 2. L'aproximació del turista al patrimoni monumental és el resultat de dues forces aparentment contradictòries. D'una banda, el turista tendeix a reproduir pautes de comportament socialment construïdes que prenen la forma d'un ritual. D'altra banda, més enllà d'aquest patró comú, cada visitant viu una experiència singular. Per tant, la relació amb el patrimoni és el resultat d'un subtil equilibri entre experiència i ritual. 3. El consum turístic del patrimoni depèn de la relació entre quatre factors. El primer, la imatge del lloc, és la projecció (sovint idealitzada) de l'espai de visita, una metàfora de la ciutat. El segon, el codi d'interpretació turístic , actua com una mena de ritual, un guió no escrit de la pràctica turística. En tercer lloc, el substrat material que són els components artístics, històrics o culturals de la destinació: la geometria del casc, les visuals, el pes de la història o el valor estètic de les peces condicionen, com és obvi, la mirada turística. Finalment, l'experiència està condicionada per la gestió (pública i privada) del turisme: informació, fluxos, interpretació... L'estudi s'ha sustentat en una metodologia inèdita basada en l'observació directa a partir del seguiment dels visitants durant els seus recorreguts. Hem observat el visitants i hem recollit la informació bàsica de la seva visita: l'itinerari, els monuments visitats, les actituds manifestades, els temps d'estada... Aquesta metodologia ha estat ja implementada en alguns estudis de públic de diversos museus. S'han recollit tres tipus de dades: dades relacionades amb els arcs (segment de carrer entre dues interseccions), dades relacionades amb els nodes (els elements d'interès) i dades relacionades amb el visitant. Les tres fonts estan unides per un identificador comú, que és el codi del turista. Això ens ha permès vincular les dades dels visitants amb el seu recorregut i la seva visita als monuments de la ciutat. Els resultats de l'estudi ens han permès identificar els factors que singularitzen l'apropament dels visitants al patrimoni i que el diferencien d'altres formes de relació o ús. És a dir, els factors que incideixen en el comportament dels visitants de Girona. Així mateix, hem pogut definir models d'itineraris amb una estructura interna molt compacta però molt diferents entre ells; que ens evidencien que, malgrat les regularitats detectades en les visites dels turistes de la ciutat, també existeixen elements diferencials en el seu comportament. Hem detectat quatre models de recorreguts urbans que hem anomenat: itinerari bàsic, comercial, complex i de les muralles, que a l'hora es poden subdividir en varies categories. Finalment, els estadístics multivariants ens han permès demostrar que la relació entre el turista i el patrimoni respon almenys a quatre formes de consum diferenciades, que hem anomenat "no turistes", "rituals", "interessats" i "erudits".

Hardy-Weinberg Equilibrium and the Ternary Plot

The Hardy-Weinberg law, formulated about 100 years ago, states that under certainassumptions, the three genotypes AA, AB and BB at a bi-allelic locus are expected to occur inthe proportions p2, 2pq, and q2 respectively, where p is the allele frequency of A, and q = 1-p.There are many statistical tests being used to check whether empirical marker data obeys theHardy-Weinberg principle. Among these are the classical xi-square test (with or withoutcontinuity correction), the likelihood ratio test, Fisher's Exact test, and exact tests in combinationwith Monte Carlo and Markov Chain algorithms. Tests for Hardy-Weinberg equilibrium (HWE)are numerical in nature, requiring the computation of a test statistic and a p-value.There is however, ample space for the use of graphics in HWE tests, in particular for the ternaryplot. Nowadays, many genetical studies are using genetical markers known as SingleNucleotide Polymorphisms (SNPs). SNP data comes in the form of counts, but from the countsone typically computes genotype frequencies and allele frequencies. These frequencies satisfythe unit-sum constraint, and their analysis therefore falls within the realm of compositional dataanalysis (Aitchison, 1986). SNPs are usually bi-allelic, which implies that the genotypefrequencies can be adequately represented in a ternary plot. Compositions that are in exactHWE describe a parabola in the ternary plot. Compositions for which HWE cannot be rejected ina statistical test are typically “close" to the parabola, whereas compositions that differsignificantly from HWE are “far". By rewriting the statistics used to test for HWE in terms ofheterozygote frequencies, acceptance regions for HWE can be obtained that can be depicted inthe ternary plot. This way, compositions can be tested for HWE purely on the basis of theirposition in the ternary plot (Graffelman & Morales, 2008). This leads to nice graphicalrepresentations where large numbers of SNPs can be tested for HWE in a single graph. Severalexamples of graphical tests for HWE (implemented in R software), will be shown, using SNPdata from different human populations

La evaluación de la reducción de amenazas en el Parque Natural de la Zona Volcánica de la Garrotxa (Girona)

En este artículo se presenta la metodología y los resultados derivados de la aplicación de una adaptación del denominado modelo de evaluación de reducción de amenazas (Threat Reduction Assesment) en el Parque Natural de la Zona Volcánica de la Garrotxa (PNZVG). Endefinitiva, se pretende valorar la efectividad de la gestión a partir del grado de reducción de amenazas en el PNZVG. El estudio se realizó a partir de la elaboración de una evaluación externa e independiente, que ha contado a la vez con una estrecha colaboración de los órganos gestores y rectores del Parque, así como con una activa participación de distintos agentes sociales clave. Se concluye que, después de veinticinco años de existencia del Parque, muchas de las amenazas iniciales sólo se han reducido de forma modesta e incluso a partir del índice adaptado, considerado un enfoque más realista; con lo cual se llega a la preocupante conclusión de que algunas de las amenazas más importantes se han incrementado

Coherent forecasting of multiple-decrement life tables: a test using Japanese cause of death data

Planners in public and private institutions would like coherent forecasts of the components of age-specic mortality, such as causes of death. This has been di cult toachieve because the relative values of the forecast components often fail to behave ina way that is coherent with historical experience. In addition, when the group forecasts are combined the result is often incompatible with an all-groups forecast. It hasbeen shown that cause-specic mortality forecasts are pessimistic when compared withall-cause forecasts (Wilmoth, 1995). This paper abandons the conventional approachof using log mortality rates and forecasts the density of deaths in the life table. Sincethese values obey a unit sum constraint for both conventional single-decrement life tables (only one absorbing state) and multiple-decrement tables (more than one absorbingstate), they are intrinsically relative rather than absolute values across decrements aswell as ages. Using the methods of Compositional Data Analysis pioneered by Aitchison(1986), death densities are transformed into the real space so that the full range of multivariate statistics can be applied, then back-transformed to positive values so that theunit sum constraint is honoured. The structure of the best-known, single-decrementmortality-rate forecasting model, devised by Lee and Carter (1992), is expressed incompositional form and the results from the two models are compared. The compositional model is extended to a multiple-decrement form and used to forecast mortalityby cause of death for Japan

Mixing compositions and other scales

Theory of compositional data analysis is often focused on the composition only. However in practical applications we often treat a composition together with covariableswith some other scale. This contribution systematically gathers and develop statistical tools for this situation. For instance, for the graphical display of the dependenceof a composition with a categorical variable, a colored set of ternary diagrams mightbe a good idea for a first look at the data, but it will fast hide important aspects ifthe composition has many parts, or it takes extreme values. On the other hand colored scatterplots of ilr components could not be very instructive for the analyst, if theconventional, black-box ilr is used.Thinking on terms of the Euclidean structure of the simplex, we suggest to set upappropriate projections, which on one side show the compositional geometry and on theother side are still comprehensible by a non-expert analyst, readable for all locations andscales of the data. This is e.g. done by defining special balance displays with carefully-selected axes. Following this idea, we need to systematically ask how to display, explore,describe, and test the relation to complementary or explanatory data of categorical, real,ratio or again compositional scales.This contribution shows that it is sufficient to use some basic concepts and very fewadvanced tools from multivariate statistics (principal covariances, multivariate linearmodels, trellis or parallel plots, etc.) to build appropriate procedures for all these combinations of scales. This has some fundamental implications in their software implementation, and how might they be taught to analysts not already experts in multivariateanalysis

Statistical modeling on (α, +∞)

Observations in daily practice are sometimes registered as positive values larger then a given threshold α. The sample space is in this case the interval (α,+∞), α & 0, which can be structured as a real Euclidean space in different ways. This fact opens the door to alternative statistical models depending not only on the assumed distribution function, but also on the metric which is considered as appropriate, i.e. the way differences are measured, and thus variability

Conditional compositional biplots: theory and application

The biplot has proved to be a powerful descriptive and analytical tool in many areasof applications of statistics. For compositional data the necessary theoreticaladaptation has been provided, with illustrative applications, by Aitchison (1990) andAitchison and Greenacre (2002). These papers were restricted to the interpretation ofsimple compositional data sets. In many situations the problem has to be described insome form of conditional modelling. For example, in a clinical trial where interest isin how patients’ steroid metabolite compositions may change as a result of differenttreatment regimes, interest is in relating the compositions after treatment to thecompositions before treatment and the nature of the treatments applied. To study thisthrough a biplot technique requires the development of some form of conditionalcompositional biplot. This is the purpose of this paper. We choose as a motivatingapplication an analysis of the 1992 US President ial Election, where interest may be inhow the three-part composition, the percentage division among the three candidates -Bush, Clinton and Perot - of the presidential vote in each state, depends on the ethniccomposition and on the urban-rural composition of the state. The methodology ofconditional compositional biplots is first developed and a detailed interpretation of the1992 US Presidential Election provided. We use a second application involving theconditional variability of tektite mineral compositions with respect to major oxidecompositions to demonstrate some hazards of simplistic interpretation of biplots.Finally we conjecture on further possible applications of conditional compositionalbiplots

Meaning of the λ parameter of skew–normal and log–skew normal distributions in fluid geochemistry

The literature related to skew–normal distributions has grown rapidly in recent yearsbut at the moment few applications concern the description of natural phenomena withthis type of probability models, as well as the interpretation of their parameters. Theskew–normal distributions family represents an extension of the normal family to whicha parameter (λ) has been added to regulate the skewness. The development of this theoreticalfield has followed the general tendency in Statistics towards more flexible methodsto represent features of the data, as adequately as possible, and to reduce unrealisticassumptions as the normality that underlies most methods of univariate and multivariateanalysis. In this paper an investigation on the shape of the frequency distribution of thelogratio ln(Cl−/Na+) whose components are related to waters composition for 26 wells,has been performed. Samples have been collected around the active center of Vulcanoisland (Aeolian archipelago, southern Italy) from 1977 up to now at time intervals ofabout six months. Data of the logratio have been tentatively modeled by evaluating theperformance of the skew–normal model for each well. Values of the λ parameter havebeen compared by considering temperature and spatial position of the sampling points.Preliminary results indicate that changes in λ values can be related to the nature ofenvironmental processes affecting the data

Assessing the Precision of Compositional Data in a Stratified Double Stage Cluster Sample: Application to the Swiss Earnings Structure Survey

Precision of released figures is not only an important quality feature of official statistics,it is also essential for a good understanding of the data. In this paper we show a casestudy of how precision could be conveyed if the multivariate nature of data has to betaken into account. In the official release of the Swiss earnings structure survey, the totalsalary is broken down into several wage components. We follow Aitchison's approachfor the analysis of compositional data, which is based on logratios of components. Wefirst present diferent multivariate analyses of the compositional data whereby the wagecomponents are broken down by economic activity classes. Then we propose a numberof ways to assess precision