Page 42 - Contributed Paper Session (CPS) - Volume 1
P. 42
CPS798 Quindale E. C. et al.
Annualization of the Labor Force Survey in the
Philippines
1
1
1,2
Quindale E. Caraos , Sarah B. Balagbis , Abubakar S. Asaad ,
3
Divina Gracia L. del Prado , Erniel B. Barrios 4
1 Statistical Methodology Unit, Philippine Statistics Authority
2 College of Public Health, University of the Philippines Manila
3 Economic Sectoral Statistics Section, Philippine Statistics Authority
4 School of Statistics, University of the Philippines Diliman
Abstract
The 2016 Labor Force Survey (LFS) starting April round used the 2013 Master
Sample (MS) design. The 2013 MS was developed to produce reliable
estimates at the provincial/highly urbanized city (HUC) levels and rates at the
end of the year. With this new MS, there is a need to develop a new estimation
procedure for annualized provincial estimates. Annualized provincial estimates
of the LFS using the simple averaging method and bootstrap method were
explored. The bootstrap method (i.e., the weighted average of the four
bootstrap quarter estimates) is better compared to the simple averaging
method since it generally yields more reliable estimates.
Keywords
annualized, bootstrap, simple averaging, indicators, master sample
1. Introduction
The LFS is a nationwide quarterly survey conducted by the Philippine
Statistics Authority (PSA) during the months of January, April, July and
October. The survey was designed to provide statistics on levels and trends of
the key labor and employment indicators in the country and for each of the
administrative regions using 2003 Master Sample (MS)1. A stratified, three-
stage sampling design was employed in the 2003 MS: the selection of primary
sampling units (PSUs) for the first stage, sample enumeration areas (EAs) for
the second stage, and sampling units for the third stage. The regions were
used as domains2. The clamor of the local government in all provinces in the
country is to come up with provincial estimates but cannot be answered by
LFS which uses the 2003 MS. With the results of the 2010 Census of Population
and Housing (CPH 2010)3, the former 2003 MS was redesigned resulting to
the 2013 MS. A total of 117 major domains were considered consisting of 81
provinces (including the newly created province of Davao Occidental), 33
HUCs (including 16 cities in the National Capital Region), and 3 other areas
(Pateros, Isabela City and Cotabato City)4. This 2013 MS was developed to
provide reliable estimates not only at the national and regional levels but also
31 | I S I W S C 2 0 1 9