About ERF
ERF Affiliates
Research Activities
RIAD
Conferences / Workshops
Become an ERF Affiliate
Find out more >

Access
Online Services
Username


Password
Register | Forgot Password

Register For
Publications
Please enter your email:
 
|
 
Advanced Search

Palestine - Expenditure and Consumption Survey, PECS 1995/1996 (For documentation only)

Sampling
Sampling Procedure

===============================================================================
THE CLEANED AND HARMONIZED VERSION OF THE SURVEY DATA PRODUCED AND PUBLISHED BY THE ECONOMIC RESEARCH FORUM REPRESENTS 100% OF THE ORIGINAL SURVEY DATA COLLECTED BY THE PALESTINIAN CENTRAL BUREAU OF STATISTICS
===============================================================================

Sample and Frame:
============
In the absence of a population census since 1967, the major task, with regard to constructing master sample, was developing a frame of suitable units covering the whole country. Such units have been used as the PSUs (Primary Sampling Units) in the first stage of selection.
For the second stage of selection, all PSUs have been listed in the field at the household level.
This provided a sampling frame for selecting the households.

Sample design:
==========
The sample design is, therefore, a stratified two-stage design for households selected to be interviewed.
Four levels of stratification have been made:
1. Stratification by District.
2. Stratification by place of residence, which comprises:
(a) Municipalities (b) Villages (C) refugees camps
3. Stratification by locality size
4. Stratification by cell identification in that order

Sample size:
========
The sample size is about 4893 households allowing for non-response and related losses.

Target cluster size:
============
The target cluster size or "sample-take" is the average number of households to be selected per PSU. In this survey, the sample take is around 10 households.

Detailed information/formulas on the sampling design are available in the user manual.

Deviations from Sample Design

The standard errors for the main survey estimates were calculated to give the user an idea of their reliability or precision. Whereas, the variance was calculated using the method of ultimate clusters within any domain of estimation.

Detailed information on the sampling design deviation and calculation of the variance is available in the user manual.

Response Rate

Excluding the uninhabited housing units, the survey sample is (4806) households, from which (3422) households are in the West Bank, and (1384) households are in Gaza Strip. A total of (4584) households completed the questionnaire: (3213) household in the West bank and (1335) households in Gaza Strip. The non-response rate is, accordingly, 5.7% for all the Palestinian territory.

Weighting

Self-Weighting Design

Detailed weight formulas are available in the user manual attached to external resources.



Home   |   About ERF   |   ERF Affiliates   |   Research Activities   |  
Capacity Building   |   Conferences/Workshops   |   Publications   |   Online Journals   |   Datasets   |   Contact us