Description: The output of the service is a sample drawn from the population frame according to the design and the parameters specified in the input. In addition, the service keeps state, i.e. information about the group population, about the administrative burden per population unit and about panels within the group, to be used in subsequent executions of the service.  

Organisation:  Statistics Netherlands

Contact:      

Country: Europe 

Status: In regular use 

Capability elements

Description

People

Methodologists

Methods

The first implementation of the service will support two methods of sampling: Panel and non-panel. Both methods apply stratified a-select sampling with target quota per stratum. In this implementation, panels may not (yet) be combined. Programs using panels therefore each have their own (single-program) group.

The basic methodologies used in this service are described in the attached document from 1993 and have been used by Statistics Netherlands since then. In the meantime, the following improvements have been made, that will also be included in the service.

  • Improved assignment of ED-values and panel-indicator for new units (births) and units changing stratum
  • Possibility to deviate from the Base Stratification by means of sub-stratification and the corresponding way of adapting ED-values.

Process

An important design goal of the service is to facilitate spreading the administrative burden across individual units of the population. For this, the service can be set up to recognize groups of Statistical Programs. The burden is then spread within each group. Groups may (and often will) have the same or overlapping populations, but there is no coordination across groups.
Each group also has a Base Stratification, that is used for all samples drawn under the group. For the dimensions of the Stratification, Correspondence Tables are defined to map the classifications of the population units to the strata. Each Program in a group may have a panel.
In the Design Phase, the groups of Statistical Programs are defined with their associated Base Stratification and Corrrespondence Tables. In this phase, for each group, rules are specified to be used in the Collect Phase for the initialisation of new units or the handling of units changing strata in the Base Stratification.
In the Collect Phase, for each Program Cycle, a sample is drawn using this service. Each time, a fresh Population Frame is provided with target quota for each cell in the Base Stratification. In addition, the input may specify Sub-stratifications, i.e. a further refinement of the Base Stratification with associated mappings and quota.

Technology


Service Definition
Service Specification
Service Implementation
See also CSPA Statistical Service Catalogue: https://www.statistical-services.org/

Standards and Frameworks



GSBPM Sub process:   4.1. Create frame and select sample

Capability Reference Model:   Primary data collection

Statistical Domain:  Methodology of data collection processing dissemination and analysis


Attached files:


File Size Creator Created Comment

EDS EN.PDF

3718204

[~8a92a40a4938c892014938c995fc0523]

24 Nov, 2015 07:20  

SS SSD.docx

31087

[~8a92a40a4938c892014938c995fc0523]

24 Nov, 2015 07:20  

SS SSS.docx

32176

[~8a92a40a4938c892014938c995fc0523]

24 Nov, 2015 07:20  

SSID Sample Selection.docx

15820

[~8a92a40a4938c892014938c995fc0523]

24 Nov, 2015 07:21