Open Season for Data Fishing on the Web: The Challenges of the US PRISM Programme for the EU. CEPS Policy Brief No. 293, 18 June 2013

The revelation of the top-secret US intelligence-led PRISM Programme has triggered wide-ranging debates across Europe. Press reports have shed new light on the electronic surveillance ‘fishing expeditions’ of the US National Security Agency and the FBI into the world’s largest electronic communications companies. This Policy Brief by a team of legal specialists and political scientists addresses the main controversies raised by the PRISM affair and the policy challenges that it poses for the EU. Two main arguments are presented: First, the leaks over the PRISM programme have undermined the trust that EU citizens have in their governments and the European institutions to safeguard and protect their privacy; and second, the PRISM affair raises questions regarding the capacity of EU institutions to draw lessons from the past and to protect the data of its citizens and residents in the context of transatlantic relations. The Policy Brief puts forward a set of policy recommendations for the EU to follow and implement a robust data protection strategy in response to the affair.

Sur les tests lisses d'ajustement dans le context des series chronologiques

La plupart des modèles en statistique classique repose sur une hypothèse sur la distribution des données ou sur une distribution sous-jacente aux données. La validité de cette hypothèse permet de faire de l’inférence, de construire des intervalles de confiance ou encore de tester la fiabilité du modèle. La problématique des tests d’ajustement vise à s’assurer de la conformité ou de la cohérence de l’hypothèse avec les données disponibles. Dans la présente thèse, nous proposons des tests d’ajustement à la loi normale dans le cadre des séries chronologiques univariées et vectorielles. Nous nous sommes limités à une classe de séries chronologiques linéaires, à savoir les modèles autorégressifs à moyenne mobile (ARMA ou VARMA dans le cas vectoriel). Dans un premier temps, au cas univarié, nous proposons une généralisation du travail de Ducharme et Lafaye de Micheaux (2004) dans le cas où la moyenne est inconnue et estimée. Nous avons estimé les paramètres par une méthode rarement utilisée dans la littérature et pourtant asymptotiquement efficace. En effet, nous avons rigoureusement montré que l’estimateur proposé par Brockwell et Davis (1991, section 10.8) converge presque sûrement vers la vraie valeur inconnue du paramètre. De plus, nous fournissons une preuve rigoureuse de l’inversibilité de la matrice des variances et des covariances de la statistique de test à partir de certaines propriétés d’algèbre linéaire. Le résultat s’applique aussi au cas où la moyenne est supposée connue et égale à zéro. Enfin, nous proposons une méthode de sélection de la dimension de la famille d’alternatives de type AIC, et nous étudions les propriétés asymptotiques de cette méthode. L’outil proposé ici est basé sur une famille spécifique de polynômes orthogonaux, à savoir les polynômes de Legendre. Dans un second temps, dans le cas vectoriel, nous proposons un test d’ajustement pour les modèles autorégressifs à moyenne mobile avec une paramétrisation structurée. La paramétrisation structurée permet de réduire le nombre élevé de paramètres dans ces modèles ou encore de tenir compte de certaines contraintes particulières. Ce projet inclut le cas standard d’absence de paramétrisation. Le test que nous proposons s’applique à une famille quelconque de fonctions orthogonales. Nous illustrons cela dans le cas particulier des polynômes de Legendre et d’Hermite. Dans le cas particulier des polynômes d’Hermite, nous montrons que le test obtenu est invariant aux transformations affines et qu’il est en fait une généralisation de nombreux tests existants dans la littérature. Ce projet peut être vu comme une généralisation du premier dans trois directions, notamment le passage de l’univarié au multivarié ; le choix d’une famille quelconque de fonctions orthogonales ; et enfin la possibilité de spécifier des relations ou des contraintes dans la formulation VARMA. Nous avons procédé dans chacun des projets à une étude de simulation afin d’évaluer le niveau et la puissance des tests proposés ainsi que de les comparer aux tests existants. De plus des applications aux données réelles sont fournies. Nous avons appliqué les tests à la prévision de la température moyenne annuelle du globe terrestre (univarié), ainsi qu’aux données relatives au marché du travail canadien (bivarié). Ces travaux ont été exposés à plusieurs congrès (voir par exemple Tagne, Duchesne et Lafaye de Micheaux (2013a, 2013b, 2014) pour plus de détails). Un article basé sur le premier projet est également soumis dans une revue avec comité de lecture (Voir Duchesne, Lafaye de Micheaux et Tagne (2016)).

The Reallocation of Agricultural Labour across Sectors: An Empirical Strategy for Micro Data. Factor Markets Working Document No. 45, May 2013

This paper presents an empirical methodology for studying the reallocation of agricultural labour across sectors from micro data. Whereas different approaches have been employed in the literature to better understand the mobility of labour, looking at the determinants to exit farm employment and enter off-farm activities, the initial decision of individuals to work in agriculture, as opposed to other sectors, has often been neglected. The proposed methodology controls for the selectivity bias, which may arise in the presence of a non-random sample of the population, in this context those in agricultural employment, which would lead to biased and inconsistent estimates. A 3-step multivariate probit with two selection and one outcome equations constitutes the selected empirical approach to explore the determinants of farm labour to exit agriculture and switch occupational sector. The model can be used to take into account the different market and production structures across European member states on the allocation of agricultural labour and its adjustments.

Coreferentiality: A New Method for the Hypothesis-Based Analysis of Phenotypes Characterized by Multivariate Data

Many multifactorial biologic effects, particularly in the context of complex human diseases, are still poorly understood. At the same time, the systematic acquisition of multivariate data has become increasingly easy. The use of such data to analyze and model complex phenotypes, however, remains a challenge. Here, a new analytic approach is described, termed coreferentiality, together with an appropriate statistical test. Coreferentiality is the indirect relation of two variables of functional interest in respect to whether they parallel each other in their respective relatedness to multivariate reference data, which can be informative for a complex effect or phenotype. It is shown that the power of coreferentiality testing is comparable to multiple regression analysis, sufficient even when reference data are informative only to a relatively small extent of 2.5%, and clearly exceeding the power of simple bivariate correlation testing. Thus, coreferentiality testing uses the increased power of multivariate analysis, however, in order to address a more straightforward interpretable bivariate relatedness. Systematic application of this approach could substantially improve the analysis and modeling of complex phenotypes, particularly in the context of human study where addressing functional hypotheses by direct experimentation is often difficult.

Sur les tests lisses d'ajustement dans le context des series chronologiques

La plupart des modèles en statistique classique repose sur une hypothèse sur la distribution des données ou sur une distribution sous-jacente aux données. La validité de cette hypothèse permet de faire de l’inférence, de construire des intervalles de confiance ou encore de tester la fiabilité du modèle. La problématique des tests d’ajustement vise à s’assurer de la conformité ou de la cohérence de l’hypothèse avec les données disponibles. Dans la présente thèse, nous proposons des tests d’ajustement à la loi normale dans le cadre des séries chronologiques univariées et vectorielles. Nous nous sommes limités à une classe de séries chronologiques linéaires, à savoir les modèles autorégressifs à moyenne mobile (ARMA ou VARMA dans le cas vectoriel). Dans un premier temps, au cas univarié, nous proposons une généralisation du travail de Ducharme et Lafaye de Micheaux (2004) dans le cas où la moyenne est inconnue et estimée. Nous avons estimé les paramètres par une méthode rarement utilisée dans la littérature et pourtant asymptotiquement efficace. En effet, nous avons rigoureusement montré que l’estimateur proposé par Brockwell et Davis (1991, section 10.8) converge presque sûrement vers la vraie valeur inconnue du paramètre. De plus, nous fournissons une preuve rigoureuse de l’inversibilité de la matrice des variances et des covariances de la statistique de test à partir de certaines propriétés d’algèbre linéaire. Le résultat s’applique aussi au cas où la moyenne est supposée connue et égale à zéro. Enfin, nous proposons une méthode de sélection de la dimension de la famille d’alternatives de type AIC, et nous étudions les propriétés asymptotiques de cette méthode. L’outil proposé ici est basé sur une famille spécifique de polynômes orthogonaux, à savoir les polynômes de Legendre. Dans un second temps, dans le cas vectoriel, nous proposons un test d’ajustement pour les modèles autorégressifs à moyenne mobile avec une paramétrisation structurée. La paramétrisation structurée permet de réduire le nombre élevé de paramètres dans ces modèles ou encore de tenir compte de certaines contraintes particulières. Ce projet inclut le cas standard d’absence de paramétrisation. Le test que nous proposons s’applique à une famille quelconque de fonctions orthogonales. Nous illustrons cela dans le cas particulier des polynômes de Legendre et d’Hermite. Dans le cas particulier des polynômes d’Hermite, nous montrons que le test obtenu est invariant aux transformations affines et qu’il est en fait une généralisation de nombreux tests existants dans la littérature. Ce projet peut être vu comme une généralisation du premier dans trois directions, notamment le passage de l’univarié au multivarié ; le choix d’une famille quelconque de fonctions orthogonales ; et enfin la possibilité de spécifier des relations ou des contraintes dans la formulation VARMA. Nous avons procédé dans chacun des projets à une étude de simulation afin d’évaluer le niveau et la puissance des tests proposés ainsi que de les comparer aux tests existants. De plus des applications aux données réelles sont fournies. Nous avons appliqué les tests à la prévision de la température moyenne annuelle du globe terrestre (univarié), ainsi qu’aux données relatives au marché du travail canadien (bivarié). Ces travaux ont été exposés à plusieurs congrès (voir par exemple Tagne, Duchesne et Lafaye de Micheaux (2013a, 2013b, 2014) pour plus de détails). Un article basé sur le premier projet est également soumis dans une revue avec comité de lecture (Voir Duchesne, Lafaye de Micheaux et Tagne (2016)).

Maize Stress DIESI-MS Data and R Script

Climatic change is an increasing challenge for agriculture that is driving the development of suitable crops in order to ensure supply for both human nutrition and animal feed. In this context, it is increasingly important to understand the biochemical responses of cells to environmental cues at the whole system level, an aim that is being brought closer by advances in high throughput, cost-efficient plant metabolomics. To support molecular breeding activities, we have assessed the economic, technical and statistical feasibility of using direct mass spectrometry methods to evaluate the physiological state of maize (Zea mays L.) plants grown under different stress conditions.

Stickleback F2 generation transgenerational plasticity experiment: egg and body size data

Nongenetic inheritance mechanisms such as transgenerational plasticity (TGP) can buffer populations against rapid environmental change such as ocean warming. Yet, little is known about how long these effects persist and whether they are cumulative over generations. Here, we tested for adaptive TGP in response to simulated ocean warming across parental and grandparental generations of marine sticklebacks. Grandparents were acclimated for two months during reproductive conditioning, whereas parents experienced developmental acclimation, allowing us to compare the fitness consequences of short-term vs. prolonged exposure to elevated temperature across multiple generations. We found that reproductive output of F1 adults was primarily determined by maternal developmental temperature, but carry-over effects from grandparental acclimation environments resulted in cumulative negative effects of elevated temperature on hatching success. In very early stages of growth, F2 offspring reached larger sizes in their respective paternal and grandparental environment down the paternal line, suggesting that other factors than just the paternal genome may be transferred between generations. In later growth stages, maternal and maternal granddam environments strongly influenced offspring body size, but in opposing directions, indicating that the mechanism(s) underlying the transfer of environmental information may have differed between acute and developmental acclimation experienced by the two generations. Taken together, our results suggest that the fitness consequences of parental and grandparental TGP are highly context dependent, but will play an important role in mediating some of the impacts of rapid climate change in this system.

Raw-data to morphometric investigations about the Neogene planktonic foraminifer Globorotalia menardii and related forms from ODP Hole 154-925B (Céara Rise, western tropical Atlantic)

Evolutionary prospection is the study of morphological evolution and speciation in calcareous plankton from selected time-slices and key sites in the world oceans. In this context, the Neogene menardiform globorotalids serve as study objects for morphological speciation in planktic foraminifera. A downcore investigation of test morphology of the lineage of G. menardii-limbata-multicamerata during the past 8 million years was carried out in the western tropical Atlantic ODP Hole 925B. A total of 4669 specimens were measured and analyzed from 38 stratigraphic levels and compared to previous studies from DSDP Sites 502 and 503. Collection of digital images and morphometric measurements from digitized outlines were achieved using a microfossil orientation and imaging robot called AMOR and software, which was especially developed for this purpose. Most attention was given to the evolution of spiral height versus axial length of tests in keel view, but other parameters were investigated as well. The variability of morphological parameters in G. menardii, G. limbata, and G. multicamerata through time are visualized by volume density diagrams. At Hole 925B results show gradual test size increase in G. menardii until about 3.2 Ma. The combination of taxonomic determination in the light microscope with morphometric investigations shows strong morphological overlap and evolutionary continuity from ancestral to extant G. menardii (4-6 chambers in the final whorl) to the descendent but extinct G. limbata (seven chambers in the final whorl) and to G. multicamerata (>=8 chambers in the final whorl). In the morphospace defined by spiral height (dX) and axial length (dY) Globorotalia limbata and G. multicamerata strongly overlap with G. menardii. Distinction of G. limbata from G. menardii is only possible by slight differences in the number of chambers of the final whorl, nuances in spiral convexity, upper keel angles, radii of osculating circles, or by differences in reflectance of their tests. Globorotalia multicamerata can be distinguished from the other two forms by more than eight chambers in the final whorl. It appeared as two stratigraphically separate clusters during the Pliocene. Between 2.88 and 2.3 Ma G. menardii was severely restricted in size and abundance. Thereafter, it showed a rapid and prominent expansion of the upper test size extremes between 2.3 and 1.95 Ma persisting until present. The size-frequency distributions at Hole 925B are surprisingly similar to trends of menardiform globorotalids from Caribbean DSDP Site 502. There, the observations were explained as an adaptation to changes in the upper water column due to the emergence of the Isthmus of Panama. In light of more recent paleontological and geological investigations about the completion of the permanent land connection between North and South America since about 3 Ma the present study gives reason to suspect the sudden test size increase of G. menardii to reflect immigration of extra-large G. menardii from the Indian Ocean or the Pacific. It is hypothesized that during the Late Pliocene dispersal of large G. menardii into the southern to tropical Atlantic occurred during an intermittent episode of intense Agulhas Current leakage around the Cape of Good Hope and from there via warm eddy transport to the tropical Atlantic (Agulhas dispersal hypothesis).

Navigation and meteorological data during campaign TARA_20090926Z of the Tara Oceans expedition 2009-2013

The Tara Oceans Expedition (2009-2013) sampled the world oceans on board a 36 m long schooner, collecting environmental data and organisms from viruses to planktonic metazoans for later analyses using modern sequencing and state-of-the-art imaging technologies. Tara Oceans Data are particularly suited to study the genetic, morphological and functional diversity of plankton. The present dataset contains navigation and meteorological data measured during one campaign of the Tara Oceans Expedition. Latitude and Longitude were obtained from TSG data.

Navigation and meteorological data during campaign TARA_20091019Z of the Tara Oceans expedition 2009-2013

The Tara Oceans Expedition (2009-2013) sampled the world oceans on board a 36 m long schooner, collecting environmental data and organisms from viruses to planktonic metazoans for later analyses using modern sequencing and state-of-the-art imaging technologies. Tara Oceans Data are particularly suited to study the genetic, morphological and functional diversity of plankton. The present dataset contains navigation and meteorological data measured during one campaign of the Tara Oceans Expedition. Latitude and Longitude were obtained from TSG data.

Approaches and Strategy for Cancer Research and Surveillance Data: Integration, Information Pipeline, Data Models, and Informatics Opportunities

Thesis (Ph.D.)--University of Washington, 2016-04

Remotely sensed data for ecosystem analyses: Combining hierarchy and scene models

Remotely sensed data have been used extensively for environmental monitoring and modeling at a number of spatial scales; however, a limited range of satellite imaging systems often. constrained the scales of these analyses. A wider variety of data sets is now available, allowing image data to be selected to match the scale of environmental structure(s) or process(es) being examined. A framework is presented for use by environmental scientists and managers, enabling their spatial data collection needs to be linked to a suitable form of remotely sensed data. A six-step approach is used, combining image spatial analysis and scaling tools, within the context of hierarchy theory. The main steps involved are: (1) identification of information requirements for the monitoring or management problem; (2) development of ideal image dimensions (scene model), (3) exploratory analysis of existing remotely sensed data using scaling techniques, (4) selection and evaluation of suitable remotely sensed data based on the scene model, (5) selection of suitable spatial analytic techniques to meet information requirements, and (6) cost-benefit analysis. Results from a case study show that the framework provided an objective mechanism to identify relevant aspects of the monitoring problem and environmental characteristics for selecting remotely sensed data and analysis techniques.

The implications of simultaneous smoking initiation for inferences about the genetics of smoking behavior from twin data

We examined early social influences across stages of smoking within the context of a twin study using an environmental exposure specific to smoking: whether twins started smoking at the same time (simultaneous smoking initiation: SSI). We expected that SSI would be a good index of shared social influences on smoking initiation. Rates of SSI were indeed significantly higher in MZ twins and in twins who shared peers and classes, as well as in male twins. With the exception of regular smoking in females, we found no significant difference in estimates of genetic and environmental parameters between SSI and non-SSI pairs for any of the smoking measures that we examined (DSM-IV and Fagerstrom HSI measures of nicotine dependence; DSM-IV nicotine withdrawal; heavy smoking; and in males, regular smoking). For regular smoking in females, allowing for additional shared environmental influences associated with SSI only modestly reduced our estimates of additive genetic variance (56% vs. 68%). These results indicate the important social influences that may occur for smoking initiation do not appear to seriously bias estimates of genetic effects on later stages of smoking.

Context obfuscation for privacy via ontological descriptions

Context information is used by pervasive networking and context-aware programs to adapt intelligently to different environments and user tasks. As the context information is potentially sensitive, it is often necessary to provide privacy protection mechanisms for users. These mechanisms are intended to prevent breaches of user privacy through unauthorised context disclosure. To be effective, such mechanisms should not only support user specified context disclosure rules, but also the disclosure of context at different granularities. In this paper we describe a new obfuscation mechanism that can adjust the granularity of different types of context information to meet disclosure requirements stated by the owner of the context information. These requirements are specified using a preference model we developed previously and have since extended to provide granularity control. The obfuscation process is supported by our novel use of ontological descriptions that capture the granularity relationship between instances of an object type.