Quality & Quantity (2005) 39:625–641 © Springer 2005
Sample Design and Allocation for Random
and M. QAMAR ISLAM
Department of Statistics, Middle East Technical University, Ankara, Turkey;
Department of Economics, C¸ ankaya University, Ankara, Turkey
Abstract. Sample design and sample allocation methods are developed for random digit
dialling in household telephone surveys. The proposed method is based on a two-way strat-
iﬁcation of telephone numbers. A weighted probability proportional to size sample alloca-
tion technique is used, with auxiliary variables about the telephone coverage rates, within
local telephone exchanges of each substrata. This makes the sampling design nearly “self-
weighting” in residential numbers when the prior information is well assigned. A computer
program generates random numbers for the local areas within the existing phone capacities.
A simulation study has shown greater sample allocation gain by the weighted probabilities
proportional to size measures over other sample allocation methods. The amount of dial-
ling required to obtain the sample is less than for proportional allocation. A decrease is also
observed on the gain in sample allocation for some methods through the increasing sample
Key words: auxiliary information, household telephone surveys, minimum dialling sample
allocation, prior information, random digit dialling, sample allocation, unequal sized clus-
ters, weighted probabilities proportional to size measures.
Recent developments in sample survey methodology are leading towards
obtaining household information by using recent technology. There is an
increasing demand for using household telephone surveys as a mode of
data collection in recent years. Along these lines, sample designs are also
developed for telephone surveys. Because of its advantages over other data
collection methods made telephone surveys as an efﬁcient method for
obtaining information from human populations.
Parallel to this demand, improvements in sample design and selection
techniques (i.e., random digit dialling, RDD) of individual sampling units
as well as recent developments in interviewing procedures (i.e., computer
Author for correspondence: H.
Oztas¸ Ayhan, Department of Statistics, Middle East Tech-
nical University, Ankara 06531, Turkey, E-mail: OAyhan@metu.edu.tr.