9
Sampling from a Complex Design
PPSSystematic. This is a first-stage method thatsystematically selects units with probability
proportional to size. They are selected without replacement.
PPSSequential. This is a first-stage method that sequentially selects units with probability
proportional to cluster sizeand without replacement.
PPSBrewer. This is a first-stage methodthat selects two clusters from each stratum with
probability proportionalto cluster size and without replacement. Acluster variable must be
specified to use this method.
PPSMurthy. This is a first-stage method that selects two clusters from each stratum with
probability proportionalto cluster size and without replacement. Acluster variable must be
specified to use this method.
PPSSampford . This is a first-stage method that selects more than two clusters from each
stratum with probability proportional to clustersize and without replacement. It is an
extension of Brewer’smethod. Acluster variable must be specified to use this method.
UseWR estimation for analysis.By default, an estimation method is specified in the plan file
that isconsistent with the selected sampling method. Thisallows you to use with-replacement
estimation even if the sampling method implies WOR estimation. This option is available
only in stage 1.
Measureof Size (MOS). If a PPS method is selected, you must specify a measure of size that defines
the size of each unit. These sizes can be explicitly defined in a variable or theycan be computed
from the data. Optionally,you can set lower and upper bounds on the MOS, overriding any values
foundin the MOS variable or computed from the data. Theseoptions are available only in stage 1.