POLYGONAL DESIGNS FOR SAMPLING FROM NATURALLY ORDERED POPULATIONS
Loading...
Date
2015
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
INDIAN AGRICULTURAL STATISTICS RESEARCH INSTITUTE ICAR-INDIAN AGRICULTURAL RESEARCH INSTITUTE
Abstract
Balanced sampling plans excluding adjacent units {BSA (m) plans} are useful for
sampling from populations in which the nearer units provide similar observations due
to natural ordering of the units in time or space. The ordering of units in the
population may be circular or linear. For BSA (m) plans, all the first order inclusion
probabilities are equal where as second order inclusion probabilities for pairs of
adjacent units at a distance less than or equal to m are zero and constant for all other
pairs of non-adjacent units which are at a distance greater than m.
An important series of incomplete block designs called polygonal designs are useful
for obtaining BSA (m) plans. Considering the blocks of polygonal designs as
samples and the treatments as units, a BSA (m) plan can be obtained by assigning
equal probability of selection to the blocks. The computer algorithm based on linear
integer programming approach available for generating efficient binary incomplete
block designs has been modified for obtaining polygonal designs for both the circular
and linear ordered structure of population units. Computer aided search of polygonal
designs is made in the parametric range v ≤ 30, k ≤ 5, m ≤ 5. In this range 1037
designs satisfy the parametric relations for circular ordering of units and 817 for
linear ordering of units. Computer aided search gives almost all the existent
polygonal designs except 7 designs in case of circular ordering of units. Further 9
new polygonal designs for the situations in which units are arranged in circular order
and 16 new polygonal design for the situations in which units are arranged in linear
order are also obtained.
Description
t-9282
Keywords
null