When zero doesn't mean it and other geomathematical mischief

There is almost not a case in exploration geology, where the studied data doesn’tincludes below detection limits and/or zero values, and since most of the geological dataresponds to lognormal distributions, these “zero data” represent a mathematicalchallenge for the interpretation.We need to start by recognizing that there are zero values in geology. For example theamount of quartz in a foyaite (nepheline syenite) is zero, since quartz cannot co-existswith nepheline. Another common essential zero is a North azimuth, however we canalways change that zero for the value of 360°. These are known as “Essential zeros”, butwhat can we do with “Rounded zeros” that are the result of below the detection limit ofthe equipment?Amalgamation, e.g. adding Na2O and K2O, as total alkalis is a solution, but sometimeswe need to differentiate between a sodic and a potassic alteration. Pre-classification intogroups requires a good knowledge of the distribution of the data and the geochemicalcharacteristics of the groups which is not always available. Considering the zero valuesequal to the limit of detection of the used equipment will generate spuriousdistributions, especially in ternary diagrams. Same situation will occur if we replace thezero values by a small amount using non-parametric or parametric techniques(imputation).The method that we are proposing takes into consideration the well known relationshipsbetween some elements. For example, in copper porphyry deposits, there is always agood direct correlation between the copper values and the molybdenum ones, but whilecopper will always be above the limit of detection, many of the molybdenum values willbe “rounded zeros”. So, we will take the lower quartile of the real molybdenum valuesand establish a regression equation with copper, and then we will estimate the“rounded” zero values of molybdenum by their corresponding copper values.The method could be applied to any type of data, provided we establish first theircorrelation dependency.One of the main advantages of this method is that we do not obtain a fixed value for the“rounded zeros”, but one that depends on the value of the other variable.Key words: compositional data analysis, treatment of zeros, essential zeros, roundedzeros, correlation dependency

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

Ratio maps and correspondence analysis

We compare two methods for visualising contingency tables and developa method called the ratio map which combines the good properties of both.The first is a biplot based on the logratio approach to compositional dataanalysis. This approach is founded on the principle of subcompositionalcoherence, which assures that results are invariant to considering subsetsof the composition. The second approach, correspondence analysis, isbased on the chi-square approach to contingency table analysis. Acornerstone of correspondence analysis is the principle of distributionalequivalence, which assures invariance in the results when rows or columnswith identical conditional proportions are merged. Both methods may bedescribed as singular value decompositions of appropriately transformedmatrices. Correspondence analysis includes a weighting of the rows andcolumns proportional to the margins of the table. If this idea of row andcolumn weights is introduced into the logratio biplot, we obtain a methodwhich obeys both principles of subcompositional coherence and distributionalequivalence.

Measuring subcompositional incoherence

Subcompositional coherence is a fundamental property of Aitchison s approach to compositional data analysis, and is the principal justification for using ratios of components. We maintain, however, that lack of subcompositional coherence, that is incoherence, can be measured in an attempt to evaluate whether any given technique is close enough, for all practical purposes, to being subcompositionally coherent. This opens up the field to alternative methods, which might be better suited to cope with problems such as data zeros and outliers, while being only slightly incoherent. The measure that we propose is based on the distance measure between components. We show that the two-part subcompositions, which appear to be the most sensitive to subcompositional incoherence, can be used to establish a distance matrix which can be directly compared with the pairwise distances in the full composition. The closeness of these two matrices can be quantified using a stress measure that is common in multidimensional scaling, providing a measure of subcompositional incoherence. The approach is illustrated using power-transformed correspondence analysis, which has already been shown to converge to log-ratio analysis as the power transform tends to zero.

Geochemistry and 40Ar/39Ar geochronology of pseudotachylyte associated with UHP whiteschists from the Dora Maira massif, Italy

In situ UV-Iaser ablation Ar-40/(39) Ar geochronological and geochemical data, together with rock and mineral compositional data, have been determined from pseudotachylyte and surrounding mylonitic gneiss associated with the UHP whiteschists of the Dora Maira Massif, Italy. Several generations of fresh pseudotachylyte occur as irregular veins up to a few cur thick both parallel and at high angles to the foliation. Whole rock XRF data collected from representative lithologies of mylonitic gneiss are uniformly consistent with a mildly alkalic granitic protolith. Minimal compositional variation is observed between the pseudotachylyte and its surrounding mylonitic gneiss. The pseudotachylyte contains newly crystallized grains of biotite and K-feldspar in a matrix of glass with partially fused grains of quartz, zircon, apatite, and titanite. Electron microprobe analyses of the glass show significant compositional variation that is probably strongly influenced by micrometer-scale changes in mineralogy. UV-Iaser ablation ICP-MS traverses across the mylonitic gneiss-pseudotachylyte contact are consistent with cataclastic communition of REE carriers such as epidote, monazite, allanite, zircon, and apatite before melting as an efficient mechanism of REE homogenization in the pseudotachylyte. The 40Ar/39Ar data from one band of pseudotachylyte indicate formation at 20.1 +/- 0.5 Ma, when the mylonitic gneisses were already in a near surface position. The variable effects of top-to-the-west shear deformation within outcrops of the coesite-bearing unit are reflected in localized zones of protomylonite, cataclasite, ultracataclasite, and pseudotachylyte. Preservation of several generations of pseudotachylyte suggests that seismic events may have played a significant role in triggering late unroofing of the UHP rocks. It is speculated that deeper crustal seismic events potentially played a role in the unroofing of the UHP rocks at earlier stages in their exhumation history. (c) 2005 Elsevier B.V. All rights reserved.

The normal distribution in some constrained sample spaces

Phenomena with a constrained sample space appear frequently in practice. This is the case e.g. with strictly positive data, or with compositional data, like percentages or proportions. If the natural measure of difference is not the absolute one, simple algebraic properties show that it is more convenient to work with a geometry different from the usual Euclidean geometry in real space, and with a measure different from the usual Lebesgue measure, leading to alternative models which better fit the phenomenon under study. The general approach is presented and illustrated using the normal distribution, both on the positive real line and on the D-part simplex. The original ideas of McAlister in his introduction to the lognormal distribution in 1879, are recovered and updated

Técnicas composicionales para concentraciones geoquímicas por debajo del límite de detección

In most geochemical analyses log-ratio techniques are required to analyse compositional data sets. When a chemical element is present at a low concentration in is usally identified as a value below the detection límit and added to the data set either as zero or simply by attaching a less-than label. In any case, the occirrence of such concentration prevents us from applying the log-ratio approach. We review here the tehoretical bases of the most recent proposals for dealing with these types of observation, give some advice on their practical application and illustrate their performance throgh some examples using geochemical data

Chemical and isotopic equilibrium between CO2 and CH4 in fumarolic gas discharges: Generation of CH4 in arc magmatic-hydrothermal systems

The chemical and isotopic composition of fumarolic gases emitted from Nisyros Volcano, Greece, and of a single gas sample from Vesuvio, Italy, was investigated in order to determine the origin of methane (CH,) within two subduction-related magmatic-hydrothermal environments. Apparent temperatures derived from carbon isotope partitioning between CH4 and CO2 of around 340degreesC for Nisyros and 470degreesC for Vesuvio correlate well with aquifer temperatures as measured directly and/or inferred from compositional data using the H2O-H-2-CO2-CO-CH4 geothermometer. Thermodynamic modeling reveals chemical equilibrium between CH4, CO2 and H2O implying that carbon isotope partitioning between CO2 and CH, in both systems is controlled by aquifer temperature. N-2/(3) He and CH4/(3) He ratios of Nisyros fumarolic gases are unusually low for subduction zone gases and correspond to those of midoceanic ridge environments. Accordingly, CH4 may have been primarily generated through the reduction of CO, by H, in the absence of any organic matter following a Fischer-Tropsch-type reaction. However, primary occurrence of minor amounts of thermogenic CH4 and subsequent re-equilibration with co-existing CO2 cannot be ruled out entirely- CO2/He-3 ratios and delta(13)C(CO2) values imply that the evolved CO2 either derives from a metasomatized mantle or is a mixture between two components, one outgassing from an unaltered mantle and the other released by thermal breakdown of marine carbonates. The latter may contain traces of organic matter possibly decomposing to CH4 during thermometamorphism. Copyright (C) 2004 Elsevier Ltd.

Balancing guava nutrition with liming and fertilization

Guava response to liming and fertilization can be monitored by tissue testing. Tissue nutrient signature is often diagnosed against nutrient concentration standards. However, this approach has been criticized for not considering nutrient interactions and to generate numerical biases as a result of data redundancy, scale dependency and non-normal distribution. Techniques of compositional data analysis can control those biases by balancing groups of nutrients, such as those involved in liming and fertilization. The sequentially arranged and orthonormal isometric log ratios (ilr) or balances avoid numerical bias inherent to compositional data. The objectives were to relate tissue nutrient balances with the production of "Paluma" guava orchards differentially limed and fertilized, and to adjust the current patterns of nutrient balance with the range of more productive guava trees. It was conducted one experiment of 7-yr of liming and three experiments of 3-yr with N, P and K trials in 'Paluma' orchards on an Oxisol. Plant N, P, K, Ca and Mg were monitored yearly. It was selected the [N, P, K | Ca, Mg], [N, P | K], [N | P] and [Ca | Mg] balances to set apart the effects of liming (Ca-Mg) and fertilizers (N-K) on macronutrient balances. Liming largely influenced nutrient balances of guava in the Oxisol while fertilization was less influential. The large range of guava yields and nutrient balances allowed defining balance ranges and comparing them with the critical ranges of nutrient concentration values currently used in Brazil and combined into ilr coordinates.

Nutrient signature of Quebec (Canada) cranberry (Vaccinium macrocarpon Ait.)

Fertilizer recommendations for cranberry crops are guided by plant and soil tests. However, critical tissue concentration ranges used for diagnostic purposes are inherently biased by nutrient interactions and physiological age. Compositional data analysis using isometric log ratios (ilr) of nutrients as well as time detrending can avoid numerical biases. The objective was to derive unbiased nutrient signature standards for cranberry in Quebec and compare those standards to literature data. Field trials were conducted during 3 consecutive years with varying P treatments at six commercial sites in Quebec. Leaf tissues were analyzed for N, P, K, Ca, Mg, B, Cu, Zn, Mn and Fe. The analytical results were transformed into ilr nutrient balances of parts and groups of parts. High-yield reference ilr values were computed for cranberry yielding greater than 35 Mg ha-1. Many cranberry fields appeared to be over-supplied with K and either under-supplied with Mn or over-supplied with Fe as shown by their imbalanced [K | Ca, Mg] and [Mn | Fe] ratios. Nutrient concentration ranges from Maine and Wisconsin, USA, were combined into ilr values to generate ranges of balances. It was found that these nutrient ranges were much too broad for application in Quebec or outside the Quebec ranges for the [Ca | Mg] and the [Mn | Fe] balances, that were lower compared to those of high yielding cranberry crops in Quebec.

Alteration and Contamination of Archaeological Ceramics: the Perturbation Problem

Alteration and contamination processes modify the chemical composition of ceramic artefacts. This is not restricted solely to the affected elements, but also affects general concentrations. This is due to the compositional nature of chemical data, enclosed by the restriction of unit sum. Since it is impossible to know prior to data treatment whether the original compositions have been changed by such processes, the methodological approach used in provenance studies must be robust enough to handle materials that might have been altered or contaminated. The ability of the logratio transformation proposed by Aitchison to handle compositional data is studied and compared with that of present data treatments. The logaratio transformation appears to offer the most robust approach

Searching for consensus in ahp-group decision making. A bayesian perspective

This paper sets out to identify the initial positions of the different decisionmakers who intervene in a group decision making process with a reducednumber of actors, and to establish possible consensus paths between theseactors. As a methodological support, it employs one of the most widely-knownmulticriteria decision techniques, namely, the Analytic Hierarchy Process(AHP). Assuming that the judgements elicited by the decision makers follow theso-called multiplicative model (Crawford and Williams, 1985; Altuzarra et al.,1997; Laininen and Hämäläinen, 2003) with log-normal errors and unknownvariance, a Bayesian approach is used in the estimation of the relative prioritiesof the alternatives being compared. These priorities, estimated by way of themedian of the posterior distribution and normalised in a distributive manner(priorities add up to one), are a clear example of compositional data that will beused in the search for consensus between the actors involved in the resolution ofthe problem through the use of Multidimensional Scaling tools

The normal distribution in some constrained sample spaces

Phenomena with a constrained sample space appear frequently in practice. This is the case e.g. with strictly positive data, or with compositional data, like percentages or proportions. If the natural measure of difference is not the absolute one, simple algebraic properties show that it is more convenient to work with a geometry different from the usual Euclidean geometry in real space, and with a measure different from the usual Lebesgue measure, leading to alternative models which better fit the phenomenon under study. The general approach is presented and illustrated using the normal distribution, both on the positive real line and on the D-part simplex. The original ideas of McAlister in his introduction to the lognormal distribution in 1879, are recovered and updated

Análisis composicional de datos en Ciencias Geoambientales

Compositional data (concentrations) are common in geosciences. Neglecting its character mey lead to erroneous conclusions. Spurious correlation (K. Pearson, 1897) has disastrous consequences. On the basis of the pioneering work by J. Aitchison in the 1980s, a methodology free of these drawbacks is now available. The geometry of the símplex allows the representation of compositions using orthogonal co-ordinares, to which usual statistical methods can be applied, thus facilating computation ans analysis. The use of (log) ratios precludes the interpretation of single concentrations disregarding their relative character. A hydro-chemical data set is used to illustrate the point

Hilbert space on probability density functions with Aitchison geometry

Compositional data analysis motivated the introduction of a complete Euclidean structure in the simplex of D parts. This was based on the early work of J. Aitchison (1986) and completed recently when Aitchinson distance in the simplex was associated with an inner product and orthonormal bases were identified (Aitchison and others, 2002; Egozcue and others, 2003). A partition of the support of a random variable generates a composition by assigning the probability of each interval to a part of the composition. One can imagine that the partition can be refined and the probability density would represent a kind of continuous composition of probabilities in a simplex of infinitely many parts. This intuitive idea would lead to a Hilbert-space of probability densities by generalizing the Aitchison geometry for compositions in the simplex into the set probability densities