A more recent challenge is faced by households that only have mobile phone connections but no fixed line access (so-called "mobile onlys"). The dual-frame method makes it possible to include this subgroup in a sample as well.
Mobile onlys have no probability of inclusion in a draw from the landline selection framework. According to recent surveys, this affects at least 13 percent of the population and at least 18 percent of households. Since these households differ in their composition from those with fixed net, so it is a systematic coverage problem that can not be ignored for many studies.
The gap is closed by an additional mobile phone sample of synthetically generated mobile phone numbers. A selection framework for this is also provided by the Arbeitsgemeinschaft ADM-Telefonstichproben. Even with the mobile numbers are generated numbers, because only the fewest mobile numbers are listed in a directory.
In this dual-frame approach, the drawing is not made from one, but from two frames or selection frames, which together cover the population completely: one with telephone numbers exclusively from the fixed network and the other with numbers of the mobile radio. The combination of the two samples then requires a suitable design weighting.
Only the negligible proportion of people who have neither a fixed line nor a mobile phone can not be included in the sample. Based on the method proposed by Häder / Gabler, the two samples can basically be combined like any sample from two frames.
A challenge with the dual-frame approach is the mixing ratio of the two samples. So the question of how high the proportion of mobile numbers and landline numbers must be. Here, detailed simulation calculations with different weighting models for merging the two samples infas has performed show that there is an optimal mixing ratio in the realized sample, where the weighting factors (design weights) have the least variance and the weights the highest effectiveness. From a cost point of view, alternative mixing ratios are conceivable in which the increase in the variance of the weighting factors and thus the increase in the sampling error are comparatively small.
For most studies, the sample's dual-frame approach is now required. Only with him can it be guaranteed that all parts of the population are taken into account in the sample. In collaboration with the ADM, infas has worked to ensure that the dual-frame method is scientifically tested and is increasingly established in market and social research.