Page 55 - Contributed Paper Session (CPS) - Volume 1

CPS863 Abubakar S. A. et al.
be optimal. Design-based estimation and modified bootstrap 1st stage are
comparable in terms of accuracy and are both better than modified bootstrap
2nd stage. Althought the best sampling design, based on simulation results, is
stratified-LH with PPS-SYS as the barangay selection method and SRSWOR as
the sample household selection method, PPS-SYS with corn farm area as the
measure of size is better over LH since the CVs of PPS-SYS and LH are very
close and the estimation procedure for PPS-SYS is easier to implement. It
follows that the selection method for barangays is systematic and SRSWOR is
the selection method for sample households.

References
1. countrystat.psa.gov.ph.
2. Compilation of Sampling Methodologies used in Agriculture and Fisheries
Survey. Survey Designs Research and Development Section, Philippine
Statistics Authority, March 2015
3. Corn Production of the Philippines (2013). Philippine Statistics Authority.
4. Census of Agriculture and Fisheries (2012). Philippine Statistics Authority.
5. Lavallee, P. and Hidiroglou, M.A. (1988). On the stratification of skewed
populations. Survey Methodology, 14, 33-43
6. Dalenius, T. and Hodges, J. L. (1959), “Minimum Variance Stratification,”
Journal of the American Statistical Association, 54, 88-101.
7. Chernick, M.R. (1999). Bootstrap Methods: A Practitioner’s Guide. New
York: John Wiley & Sons, Inc.
8. Gerpacio, R.V., J.D. Labios, R.V. Labios, and E.I. Diangkinay (2004). Maize in
the Philippines: Production Systems, Constraints and Research Priorities.
Mexico.

44 | I S I W S C 2 0 1 9