Sampling Procedure
(a) The Selection of Establishments
The Employment and Earnings Survey of 2001 used the existing Central Register of Establishments (CRE) frame. The selection of establishments from the CRE frame falls under the following groups: -
(i) All establishments of public sectors found in the CRE frame of 2001 were taken.
(ii) All establishments of private sector with at least 50 employees found in the CRE frame of 2001 were taken.
(iii) The selection of establishments of private sector employing persons in the range of 5 to 49 was based on a sample.
(b) The Sample Design
(i) A sample of 10 percent of establishments was selected in the employment size group of 5 to 9 employees.
(ii) A sample of 33 percent of establishments was selected in the employment size group of 10 to 49 employees.
(c ) Sample Selection
A random sampling method was used to select the number of establishments to be enumerated according to the sample size in each employment group.
During the enumeration process enumerators were instructed to include in the survey, all new establishments in the public sector and those employing at least 50 persons in the private sectors that will be identified in the field but were not included in the provided list of establishments prepared for the survey.
Weighting
The weights were adjusted to suit the response status of the category of employment involved in the respective region.
The sampling weights for the strata were calculated by using the simple expansion method denoted as:
Weight = N/n
Where:
N = Total number of establishments before sampling
n = Total number of establishments sampled.
In the situation where non responding establishments exist, like in the 2001 survey, to account for the non response the weights for each cell has been expressed as:
Weight = Nhij*[1 - { ahij}/ nhij ] /{nhij - ahij}
Where:
Nhij = Total number of establishments before sampling in sector j of region i in stratum h
Where: j = 1…3, i = 1…20 and h = either 5 - 9 or 10 -49
nhij = Total number of establishments after sampling in sector j of region i in Stratum h
Where: j = 1…3, i = 1…20 and h = either 5 - 9 or 10 -49
ahij = Non-responding establishments in sector j of region i in Stratum h
Where: j = 1…3, i = 1…20 and h = either 5 - 9 or 10 -49
h = Stratum (the survey dealt with two strata).
i = Region (the survey dealt with 20 regions)
j = Private sector (the survey dealt with three sub sectors)
