Metadata to Support the Survey Life Cycle

1
Metadata to Support the Survey Life Cycle

• Alice Born, Statistics Canada
• Joint UNECE/Eurostat/OECDWork Session on
  Statistical Metadata(METIS)Geneva, April 3-5,
  2006

2
Outline

• Description of STCs Integrated Metadatabase
  (IMDB)
• Common metatdata set for a survey life cycle
• Tools for entering metadata
• Time travel versioning rules
• Complete model

3
Corporate metadata at Statistics Canada

• Integrated Metadatabase (IMDB)
• Collection of information about each of
  Statistics Canadas 560 current surveys
• Aimed at helping users interpret statistical
  data
• Survey description
• Survey instrument
• Methodology
• Data accuracy
• Variables, classifications

4
What is the IMDB based on?

• ISO 11179 Specification and Standardization of
  Data Elements
• Corporate Metadata Repository (CMR) USBC (D.
  Gillman)
• Extension of ANSI X3.285 for the management of
  statistical information (American National
  Standards Institute metamodel)

5
Surveys - definition

• Metadata in the IMDB is organized around the
  survey entity
• Refers to collection, compilation and publication
  of data measuring characteristics of a population
• Three types of surveys
• Direct
• Administrative
• Derived

6
Statistical Activities

• Group of surveys that share common feature,
  common explanatory text
• E.g., System of National AccountsThe Canadian
  System of National Accounts (CSNA) provides a
  conceptually integrated framework of statistics
  and analysis for studying the state and behaviour
  of the Canadian economy. The accounts are
  centered on the measurement of activities
  associated with production of goods and services,
  the sales of goods and services in final markets,
  the supporting financial transactions and the
  resulting wealth positions.

7
Regions
Statistical Activity
Organization
Survey
Contact
Stewardship
Universe
Documentation
Frame
Identification
Survey instance
Identification
Time Frame
Instrument
Keyword
Question
Classification
Theme
Data file
Methodology
Data Element
Instrument designSamplingData sourceError
detectionImputationEstimationQuality
evaluationDisclosure controlRevisions and
seasonal adjustmentData accuracy
Data Element Concept
Object Class
Property
Formula
Conceptual Domain
Value Domain
8
Common metadata set for survey life cycle

• Statistical activity
• Survey (direct, administrative, derived)
• Target population (population, statistical
  unit)
• Survey instance (each survey process)
• Collection instrument Methodology
• Data accuracy
• Documentation
• Data file
• (Data elements, value domains)

9
Common metadata set for survey life cycle

• Methodology
• Instrument design
• Sampling
• Collection method
• Error detection
• Imputation
• Estimation
• Quality evaluation
• Disclosure control
• Revisions and seasonal adjustment

10
Common metadata set for survey life cycle
Survey
Survey Instance- questionnaires- variables
(DE)- methodology- data accuracy
11
Common metadata set for survey life cycle
Survey Instruments
12
Common metadata set for survey life cycle
Data elements
13
Common metadata set for survey life cycle
Methodology
Target population
Instrument design
14
Tools for loading metadata into IMDB
15
Statistical Activity - Identification Tab
16
Statistical Activity and Survey- DescriptionTab

17
Survey Instance (cycle) Times Frames
18
Data sources Description
19
Versioning (time-travel)

• Metadata change over time each survey instance,
  survey or statistical activity
• Rules for revisions and versioning of
  administered items
• Three functions
• Create
• Update
• Version

20
Versioning (time-travel)

• Survey
• Changes to mandate or subject of survey new
  survey (new IMDB record and new SDDS number)
• Changes to characteristics of surveys new
  version of survey
• Survey instance
• Each reference period new version of the
  instance
• Now it coincides with release of data in the
  Daily
• Demand for the new instance version to coincide
  with collection start dates
• Central link to versioning of other administered
  items (instrument, methodology and data file)

21
Versioning (time-travel)

• Target population
• Changes result in a new version of the survey and
  target population
• Statistical activity
• Changes to program mandate or structure (addition
  or removal of surveys) results in new version of
  statistical activity

22

StatisticalActivity
Applications/Software
Survey
Frame and Sample
Target population
Survey Instance
Methodology
Products(COR)
Data File
Instrument
Data elements