Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
The importance of sampling frames in producing core data items for agricultural and rural statistics. It covers the purpose of sampling frames, their structure, types, construction, maintenance, and updating. The document also explores desirable properties of sampling frames and provides examples of list frames, area frames, multi-stage frames, and frames for series of surveys.
Typology: Study notes
1 / 17
This page cannot be seen from the preview
Don't miss anything!
Second Regional Training Course on Sampling Methods for Producing Core Data Items for Agricultural and Rural Statistics
Module 2: Review of Basics of Sampling Methods
9 – 20 November 2015, Jakarta, Indonesia
3
Statistical Survey Design – Issues involved
Probability Sampling
Target Population
Collection of elements of interest as defined by survey objectives Needs to be clearly specified: Content‐ type and characteristics of elements Extent in space‐ boundaries of geographical coverage Extent in time‐ period over which survey measurements are valid
7
Sampling Frame
Target population Frame population
Not eligible for survey
Not reachable Refusals Other non- responses
Not included in sampling frame
Sampling Frame
9
Structure
Desirable Properties
List Frame Area/Area‐based Frame Multi‐stage Frame Frames for series of surveys
15
Types
Consists of a list of observational unit Usually used for single stage sampling or complete enumeration Often covers only the large units, which are few in number but have substantial share in the population total. Examples:
Types
Types
21
Construction Maintenance and Updating
Choice of frame units Cost consideration in establishing and maintaining Availability of type of information for frame units Stability of frame units over time Time needed to construct frame
Validation of frame Coverage achieved Quality of information
Development of frame Construction of database including maps for area frames
Construction Maintenance and Updating
Maintenance
Updating Master Samples
Removing duplicates Removing ‘deaths’, such as— Closed establishments Burned down or demolished housing units Incorporating ‘births’, such as New establishments New housing units in enumeration areas Updating auxiliary information
To reflect population changes so it continues to be ‘representative’ Prepare new listings of households in sample clusters Periodical update of entire frame to account for post-censal high-growth areas
Desirable Structure of a MSF
For such master samples,
the MSF consists of lists of holdings or some other appropriate units within a selected FSU.
the lists of holdings ought to be updated periodically.
the MSF thus have provision of recording details of updating.
25
Identifiers
For each record,
Primary identifiers of the selected FSU
Secondary identifiers of the selected FSU
Sampling particulars of the FSU, such as First‐stage stratum, FSU order of selection, in case of PPS selection, FSU‐size, stratum size etc.
Primary identifier of the SSUs and USUs – identification particulars of the holder, type of holder, ID numbers of constituent plots, etc.
Unit Characteristics
Different characteristics of the holdings that could be used for sample selection and estimation, such as
Operated area classified by agricultural and non‐ agricultural use No. of plots and parcels in the holding Agricultural activities of the holding Number of livestock and poultry by kind etc.
27
Operational Data
Sample selection indicator
Change indicator
Integration for selection of Master Sample of FSUs requires ‐
linking FSU‐level (i.e. village‐ or cluster‐level ) data from different sources – such as Population Census, Agricultural Census, Livestock Census, Administrative land use data, etc.
31
Integration for MSF
Integration for creation of MSF for selection of SSUs requires Linking SSU‐level (i.e. holding‐ or household‐level) data from different sources Usually, reference periods of censuses (sources) are different. If SSUs are the same, their IDs may be developed chronologically in different censuses If SSUs be different (for example households, agricultural holdings, livestock holdings etc.), there should be provision of establishing links between different types of units. [An illustrative format is given on the next slide]
33
FSU ID
SSU ID Agricultural activities Hhd. ID Holding ID Holdingtype code crop Vege. fruits livestock
{indiv., Joint, Multiple, institu‐ tional}
