320 likes | 330 Views
Tuulikki Sillajõe outlines Estonia's data collection organization, production systems, and future plans discussed at the UN ECE Seminar on Statistical Data Collection. The Central Data Collection Department, functional ADAM system, and eSTAT functionality are key for improving efficiency. The milestones of Estonia's data collection from 2000 to 2012 and functionalities for internal and external users are crucial aspects detailed in the seminar leading to successful statistical data collection in Estonia. Statistical questionnaires, pre-filling methods, and different data collection channels also play a vital role. Attendees learned about Estonia's remarkable progress in statistical data collection during this informative seminar.
E N D
Statistics Estonia on its way to improving efficiency UN ECE Seminar on New Frontiers for Statistical Data Collection Geneva, 31.10‒02.11.2012 Tuulikki Sillajõe
Outline • Organization of the data collection • Production system as a whole • Conclusions and future plans Seminar on New Frontiers for Statistical Data Collection
Central Data Collection Department since 2004 Data Collection Department Manager Data Collection Development Manager Fieldwork Organisation Service Data Entry Service Data Collection Service Seminar on New Frontiers for Statistical Data Collection
Collection of administrative data (I) • Data Collection Department is not responsible for collection of administrative data • Data Processing Systems Department • is responsible for a single entry point for administrative data • runs pre-agreed data processing • makes the data available for statistical domains Seminar on New Frontiers for Statistical Data Collection
Collection of administrative data (II) • Methodology Department • consolidates the needs of statistical domains • conducts negotiations with the holders of administrative registers • organises the conclusion of agreements with these holders • is in charge of the description of data in a central metadata system • Statistics Estonia used about 100 different administrative registers (2012) Seminar on New Frontiers for Statistical Data Collection
Functionalities of ADAM (data collecting system for administrative data) • Automatic extraction of detailed personalized data from administrative sources using • X-road (data exchange layer) • ftp, etc. • Storing data in raw data databases • Data processing • coding • duplicate removal • Making data available for in-house applications Seminar on New Frontiers for Statistical Data Collection
Milestonesof Data Collection in Statistics Estonia, 2000‒2012 HOUSEHOLDS PHC 2011 PAPER-LESS CAPI FAILURE WITH 1st CAWI OTHER CAWI PILOTS 1st MIXED MODE CAPI+ CATI PILOT PHC 2011 CAWI+CAPI AGRI-CENSUS CAWI+CAPI CENTRAL DEPARTMENT ENTERPRISES CALL CENTER FOR ENTERPRISES ABOLISHMENT OF REGIONAL BUREAUS TERMINATION OF SENDING Q.-S PRE-FILLING WITH ADMIN-DATA WEB-BASED COLLECTION (eSTAT) Seminar on New Frontiers for Statistical Data Collection
Functionality of eSTAT for external users (I) • to view the list of statistical questionnaires, which a particular economic entity has to present to Statistics Estonia during the current year • to view deadlines for presenting these statistical questionnaires • to order reminders, which notify by e-mail about upcoming deadlines • to compile statistical questionnaires, i.e. to fulfil cells on the web with dataor download and upload CSV-files • to run controls, i.e. check whether they have compiled the statistical questionnaires required Seminar on New Frontiers for Statistical Data Collection
Functionality of eSTAT for external users (II) • to correct statistical questionnaires immediately upon compilation thereof • to submit statistical questionnaires • to look at all earlier statistical questionnaires submitted to Statistics Estonia via eSTAT by a respondent concerned • to print out a paper copy of a compiled statistical questionnaire • to administer users, i.e. to create, change and cancel rights and access • to accept or correct one’s contact information Seminar on New Frontiers for Statistical Data Collection
Functionality of eSTAT for internal users (I) • to define statistical questionnaires in the system, i.e. to describe and add them • to define controls for statistical questionnaires described in the system • to follow the inflow of statistical questionnaires and send reminders • to register contacts with respondents • to see the time and the content of contacts with respondents • to see the same information as external user and help them online Seminar on New Frontiers for Statistical Data Collection
Functionality of eSTAT for internal users (II) • to see and correct contact information of economic entity who can deliver questionnaires via the system • to compile statistical questionnaires (e.g. when receiving them by phone) • to view and correct statistical questionnaires compiled by respondents • to administer external main users and internal users • to create empty statistical questionnaires in pdf-format for printing out or saving them as a file for different administrative purposes Seminar on New Frontiers for Statistical Data Collection
Questionnaires received from economic entities by channel, 2008–2012 Seminar on New Frontiers for Statistical Data Collection
Pre-filling of questionnaires (I) • Annual statistical questionnaires for the year 2012, i.e. for the reference year 2011 data collection, are prefilled using administrative data • structural business statistics (EKOMAR) • agriculture, forestry and fishing • financial intermediation and activities auxiliary to financial services and insurance activities • non-profit institutions • Data providers have to fill in only the gaps, i.e. information not available from annual bookkeeping report Seminar on New Frontiers for Statistical Data Collection
Pre-filling of questionnaires (II) • The information from annual reports is preloaded to eSTAT every hour • First results • 52% of the questionnaires for structural business statistics had been pre-filled from annual reports • 80% of the fields were pre-filled, and respondents had to fill in the remaining 20% (only fields filled in with a number other than zero are taken into account) • Average compiling time of a statistical questionnaire has been reduced twice (from 3 hours to 1,5 hour) compared to previous year Seminar on New Frontiers for Statistical Data Collection
Mixed mode was used for PHC 2011 • Modes of questioning • e-Census on the web (CAWI) → 66% • Interview (CAPI) • Institutions filled in a special questionnaire • Different data sources • Population and Housing Census 2000 • Administrative registers • Data collection from persons • New software was developed next to eSTAT Seminar on New Frontiers for Statistical Data Collection
New software for data collection (VVIS) • Supports data collection process for various surveys and census, dividing it into three sub-processes • Preparation work for data collection • Data collection on the web (CAWI) and fieldwork (CAPI) • Support and management of the whole process Seminar on New Frontiers for Statistical Data Collection
Applications of VVIS • Questionnaire definition application • Interviewers’ (enumerators’) application • Public web application • Management application • Interfaces with external systems Seminar on New Frontiers for Statistical Data Collection
Questionnaire definition application • A tool for preparing questionnaires • Built on top of Eclipse • Functionality • Every survey can use a different, custom data model • Several questionnaires can be built on top of data model (e.g. different questionnaires for CAWI and CAPI) • Advanced navigation and validation rules within questionnaires • Use of common classifications in different surveys (e.g. occupations: ISCO, education: ISCED, etc.) • Data model and questionnaires saved in open XML format • Multi-language support for questionnaires Seminar on New Frontiers for Statistical Data Collection
Interviewers’ application • Stand-alone desktop application can be used in laptop or desktop computer (Delphi) • Synchronises all data for offline work over encrypted channel (HTTPS) • Functionality • Advanced validation and navigation rules within questionnaire • Navigation between different questionnaires • Questionnaires in multiple languages • Planning / scheduling of work • Reminders • Communication with direct supervisor • Map info for location of subjects, GPS positioning, work planning • Overview of general fieldwork progress for interviewers • Help information for interviewers • Automatic software updates (distributed from central server) Seminar on New Frontiers for Statistical Data Collection
Public web application • Used by survey subjects independently • Public system, accessible over the web (Java, Weblogic) • Functionality: • Authentication with IDcard or through bank link • Choice between questionnaires assigned to the subject • Support for all rules used in questionnaires, the same questionnaires can be used that are defined for interviewers’ application • Background information and help texts about the surveys and questionnaires Seminar on New Frontiers for Statistical Data Collection
Management application • Used by fieldwork management, statisticians, help desk • Internal web application (Java, Weblogic), accessible from within internal network • Functionality: • Authentication using LDAP or any other authentication method • Creation of survey object, configuration of methodology, fieldwork hierarchy and other characteristics of survey • Role management • Possibility to work simultaneously with several surveys • Overview of fieldwork progress, task management • Definition of milestones (deadlines) for fieldwork organisation • Help desk functionality • Data processing tools (e.g. for classification of data) • Communication (messages from one user to another) Seminar on New Frontiers for Statistical Data Collection
Interfaces with external systems • Information database • Meta-info about surveys • Background survey information (displayed on the web) • Classifications used in questionnaires • Authentication system (e.g. Active Directory) • Statistical register • Import of sample • Pre-filling of questionnaires • Export of sample (changes in subjects’ information) • GIS database • Maps • Location info of buildings • Hierarchy of district division Seminar on New Frontiers for Statistical Data Collection
Generic StatisticalBusiness Process Model Seminar on New Frontiers for Statistical Data Collection
Architecture of the information system Metadata system iMETA Economic entities KUNDE Users Persons eSTAT Data collection Statistical analysis Dissemination Processing PX-Web VAIS Analyse VVIS Census-HUB eGeostat ADAM Administrative registers Statistical registers Data Warehouse SRS Seminar on New Frontiers for Statistical Data Collection
2002Statistical Farm Register 2001metadata management 1994Statistical Business Register project started2011 system for statistical registers 2011iMeta 2006economic entities project started2011 persons 1993 2004 project started 2012 planned 2004economicentities 1993 1994economic entities project started2011 2004persons Generic Statistical Business Process Model Seminar on New Frontiers for Statistical Data Collection
Sources for efficiency gains of Statistics Estonia • Central data collection department, i.e. standardisation of processes • Generic office-wide software • Administrative data instead of survey data if applicable • Pre-filling of statistical questionnaires with administrative data Seminar on New Frontiers for Statistical Data Collection
Small developments, big efforts • Reminders sent before the deadline instead of after the deadline • Informing economic entities simultaneously about all the questionnaires they have to fill in next year • Centralisation of the preparation of questionnaires from statistical departments to IT Department and within a few years to Methodology Department • Standardisation and simplification of instructions about questionnaires for economic entities • Creation of a list of input variables Seminar on New Frontiers for Statistical Data Collection
Next practical steps • Introduction of CAWI as the main data collection method for surveys on individuals (2013) • Introduction of CATI for data collection from both types of respondents: economic entities and individuals (step by step, starting from 2012) • Implementation of generic office-wide software for other functions than data collection • Reuse of data within the statistical office Seminar on New Frontiers for Statistical Data Collection
Strategic directions • Training of data suppliers (economic entities, individuals, registers, etc.), incl. about their personal and public gains • Closer cooperation between the data collection function and dissemination function within the organisation, for better communication with data suppliers (based on the experience of PHC 2011) • Simplification of statistical reports (harmonisation of concepts, deadlines, practices, etc.) • Development of infrastructure for selling data collection services Seminar on New Frontiers for Statistical Data Collection
Further challenges • Wider use of administrative and commercial data • Do we need two data collection tools? • Centralization of data processing function? Seminar on New Frontiers for Statistical Data Collection
Thank you for your attention! tuulikki.sillajoe@stat.ee Seminar on New Frontiers for Statistical Data Collection