The Sampling Standard specifies the reliability requirements and describes appropriate sampling methods and what is expected to be provided in a sampling plan. A sample is a subset of a population. For the purposes of the CDM the population could be, for example, all households included in a CDM project activity with the sample being a subset of these households. The characteristics of that population, such as average number of hours of operation of a biogas stove, represents the parameters.
The purpose of sampling is to obtain both an unbiased and reliable estimate of the mean value of parameters used in the calculations of the reduction or removal of green house gases in a CDM project activity.
An unbiased estimate is defined as:
One that does not systematically underestimate or overestimate the parameter value it is representing.
Reliability is expressed in terms of:
The probability that the population parameter value falls within a specified distance from the sample-based estimate.
Where not provided for in the applicable methodology, sampling requirements are detailed in the "Standard for Sampling and Surveys for CDM Project Activities and Programme of Activities" (EB 65, Annex 2).
A Project Participant has a broad discretion in the sampling approach that they use to obtain the estimates. It is the role of the DOE to validate the sampling plans to determine whether they will provide parameter value estimates in an unbiased and reliable manner.
For Programme of Activities, parameter values should be estimated by sampling in accordance with the requirements in the applied methodology separately and independently for each of the CPAs included in a PoA. However, there is an exception to this requirement when a single sampling plan covering a group of CPAs is undertaking applying 95/10 confidence/precision for the sample size calculation (EB 65, Annex 2).