Philippines - Monthly Palay and Corn Situation Reporting System 2016

The MPCSRS is a sub-sample of the Palay and Corn Production Survey (PCPS) which employs a two-stage stratified sampling design with the barangay as the primary sampling unit (psu) and the household as the secondary sampling unit (ssu). One replicate of the PCPS sample barangays is selected to represent MPCSRS sample barangays covering farming households.

Under the enhanced MPCSRS, the number of sample barangays is pre-determined in the province using one replicate (any of the four or combination of replicates) of the PCPS as samples, such that:

For major palay provinces, one replicate consisting of ten (10) barangays is taken from the PPS samples

For major corn provinces, one replicate consisting of ten (10) barangays is taken from the CPS samples

For minor palay or corn provinces, one replicate consisting of five (5) barangays are taken as samples.

In each barangay, 4-25 sample households are taken as select. The selection of the sample households is the same with that of the PCPS.


MPCSRS response rate for palay samples is 99%, while response rate for corn samples is 95%


Sample weights are applied to all variables at the household-level. These are determined as a function of the uniform raising factor for the province, denoted by Rk, and the adjusted household weights.

Rk is computed from the following characteristics: average total area planted to palay/corn per stratum, average total area planted to palay/corn per barangay, average number of farming households per barangay, average number of sample farming households per barangay and average number of sample barangays per stratum.

Sample size for the sample barangay is determined based on the following information: Rk, total number of farm households in the sample barangay, total palay/corn area of the sample barangay, aggregate palay/corn area in the stratum and number of sample barangays in the stratum.

For operational purposes, sample size per barangay is limited to a minimum of four (4) and a maximum of 25. To correct for this limitation, the use of a uniform sample weight for all sample households in the same sample barangay is instituted. Household weights are determined as a function of the computed sample size and the 'desired' sample size for the barangay, that is:

a) 1.00 if the computed sample size is between 4 and 25;
b) less than 1.00 if computed sample size is less than 4
c) more than 1.00 if computed sample size is more than 25,and
d) based on computed sample size and number of farming households in the barangay if computed sample size is less than 25 and said sample size is greater than total number of farming households in the barangay.

Household weights are encoded together with other household level data. In the course of data table generation, weighting adjustment is being done to correct for unit non-response such as refusals, not-at-home, unknown and transferred to another barangay.

Computation of adjusted household weights as well as the final weight is done for each sample barangay. The adjusted weight is calculated as the product of the original household weight and the inverse of the actual response rate for the barangay. Afterwards, the final weight is determined by multiplying the adjusted weight by Rk.