• e.g., personal, government, health, .. macrodata about societies
• Uncovering insights, making predictions, decisions
• Understanding human societies

• Heterogeneous
• Decentralized
• Structured
• High volume
• Formats (e.g., CSV, Excel, PC-Axis, SDMX-ML, XML)

Clean? Synchronised? Comparable? Provenance? Trustable?

• Number of people who were born in Sydney before 1900
• List of project names in countries which are classified to have low to middle income that are situated above the equator

• analysis which is statistically significant, and has to do with GDP and health subjects
• a list of indicator pairs with strong correlations
• using the line of best fit of a regression analysis to predict or forecast possible outcomes
• countries which have less mortality rate than average with high corruption

• Central Statistics Office Ireland
• Eurostat

• World Bank (WB)
• Transparency International (TI)

• Organisation for Economic Co-operation and Development (OECD)
• Swiss Federal Statistics (BFS)
• Food and Agriculture Organization of the United Nations (FAO)
• European Central Bank (ECB)
• International Monetary Fund (IMF)

• Dataset: http://worldbank.270a.info/dataset/world-bank-finances
• Observation: http://ecb.270a.info/dataset/SEE/A/AT/WBR0/EXT/X/E/2011
• Dimension (property): http://oecd.270a.info/property/TIME
• Measure (property): http://ecb.270a.info/property/OBS_VALUE
• Attribute: http://transparency.270a.info/classification/attribute/matching-percentiles
• Concept: http://imf.270a.info/code/1.0/CL_AREA/CH
• Code list: http://fao.270a.info/code/0.1/CL_UN_COUNTRY
• Regression Analysis: http://stats.270a.info/analysis/worldbank:GC.DOD.TOTL.GD.ZS/transparency:CPI2009/2009

Cool URIs? 1, 5, 100, 10000 years?

• Identified resources with high value (i.e., "usefulness") e.g, reference areas, currencies
• Some manual linking
• Used LIMES to semi-automatically link (several threshold tests and reviewing)

• Shiny server (node)
• R (Shiny, SPARQL packages)
• Jena Fuseki
• Apache
• Linked Data Pages

• [Input] User-selects analysis (covariants, reference period):
  • Use Shiny server cache, else;
  • Check local RDF store, else;
  • Submit federated queries
• [Output] Federated query response:
  • Build (regression) analysis with R
  • Store analysis results, and provenance data to local RDF store
  • Generate a plot
  • Return analysis information and plot to UI

@prefix stats: <http://stats.270a.info/vocab#>

http://stats.270a.info/analysis/worldbank:SP.DYN.IMRT.IN/transparency:CPI2009/year:2009

http://stats.270a.info/analysis/worldbank:SP.DYN.IMRT.IN/transparency:CPI2009/year:2009

http://stats.270a.info/provenance/fa698e46868fe348865678884e89ef84b0be6c64

• Intended to be work with minimal endpoint knowledge (trade-off: it is dumb)
• Some queries are expensive (i.e., remote data transfer time from, local joins)

SELECT referenceArea measureX measureY
  SERVICE endpointX
     observation measure values for all referenceAreas
       from datasetX with reference period

  SERVICE endpointY
     observation measure values for all referenceAreas
       from datasetY with reference period

  FILTER referenceArea exactMatchXes from or to exactMatchYes
           or they are same

SELECT ?refAreaY ?x ?y ?identityX ?identityY
WHERE {
  SERVICE <http://example.org/sparql> {
    SELECT DISTINCT ?identityX ?refAreaX ?refAreaXExactMatch ?measureX
    WHERE {
      ?observationX qb:dataSet <http://example.org/dataset/X> .
      ?observationX ?propertyRefPeriodX exampleRefPeriod:1234 .
      ?propertyRefAreaX rdfs:subPropertyOf* sdmx-dimension:refArea .
      ?observationX ?propertyRefAreaX ?refAreaX .
      ?propertyMeasureX rdfs:subPropertyOf* sdmx-measure:obsValue .
      ?observationX ?propertyMeasureX ?x .
      <http://example.org/dataset/X>
        qb:structure/stats:identityDimension ?propertyIdentityX .
      ?observationX ?propertyIdentityX ?identityX .
      OPTIONAL {
        ?refAreaX skos:exactMatch ?refAreaXExactMatch .
        FILTER (REGEX(STR(?refAreaXExactMatch), "^http://example.net/"))
      }
    }
  }
  ...

  SERVICE <http://example.net/sparql> {
    SELECT DISTINCT ?identityY ?refAreaY ?refAreaYExactMatch ?measureY
    WHERE {
      ?observationY qb:dataSet <http://example.net/dataset/Y> .
      ?observationY ?propertyRefPeriodY exampleRefPeriod:1234 .
      ?propertyRefAreaY rdfs:subPropertyOf* sdmx-dimension:refArea .
      ?observationY ?propertyRefAreaY ?refAreaY .
      ?propertyMeasureY rdfs:subPropertyOf* sdmx-measure:obsValue .
      ?observationY ?propertyMeasureY ?y .
      <http://example.net/dataset/Y>
        qb:structure/stats:identityDimension ?propertyIdentityY .
      ?observationY ?propertyIdentityY ?identityY .
      OPTIONAL {
        ?refAreaY skos:exactMatch ?refAreaYExactMatch .
        FILTER (REGEX(STR(?refAreaYExactMatch), "^http://example.org/"))
      }
    }
  }
  ...

  FILTER (?refAreaYExactMatch = ?refAreaX 
          || ?refAreaXExactMatch = ?refAreaY
          || ?refAreaY = ?refAreaX)
}
ORDER BY ?identityY ?identityX ?x ?y

• Analysis - http://stats.270a.info/analysis/
  • {independentVariable}/{dependentVariable}/{referencePeriod}
  • {prefix}:{dataset}/{prefix}:{dataset}/{prefix}:{refPeriod}
  • worldbank:SP.DYN.IMRT.IN/transparency:CPI2009/year:2009
• PROV-O Activity - http://stats.270a.info/provenance/
  • {sha1(datasetX, datasetY, refPeriod)}

• analysis which is statistically significant, and has to do with Gross Domestic Product (GDP) and health subjects
• a list of indicator pairs with strong correlations
• using the line of best fit of a regression analysis to predict or forecast possible outcomes
• countries which have less mortality rate than average with high corruption

• Improve federated query performance
• Interlink more codelists and concept schemes
• Factor-in concept temporality
• Improve UI for variable selection
• Add other analysis and visualisations e.g., linear charts, multivariate analysis
• Allow developer to enter VoID URI