With the increase of cell phones in the past years, traditional landline survey face a
new challenge to reach respondents who have only cell phone connections. Dualframe
telephone surveys that use both landline and cell phone sampling frames
can overcome the incompleteness of coverage. Designing a dual-frame telephone
survey requires a decision on the sample allocation. In this paper, we present
results that designers of dual-frame survey can use to determine an allocation of
samples that optimizes the precision of the survey estimates for a given cost by
using Taiwan data.