The ADM-Sampling-System for Telephone Surveys In Germany, no directory is available to market research agencies that contains the addresses of all private households or individuals, nor is there a directory of all the telephone numbers used by private households. Since even public telephone books are incomplete, there is no official source on which to base telephone surveys. Furthermore, no official statistical data is available describing this population adequately for a sampling frame. The “Arbeitsgemeinschaft ADM-Telefonstichproben” (a group of market research agencies responsible for the sampling system) has closed this gap by providing a sampling frame to member agencies. This frame allows telephone samples to be selected representatively with respect to all households with a telephone in Germany and to the persons living in those households. Furthermore, the sampling system contains the statistical data which is necessary to fully describe the population described above. The sampling frame itself – the so-called “ADM-Telefonstichproben-System” – is based on the range of numbers available in the German telephone network as updated, monitored and published on the Internet by the “Bundesnetzagentur” (the governmental agency for the German telephone network). This range of numbers covers all possible telephone numbers in Germany, whether actually in use or not. Based on methods developed by Sabine Häder and Siegfried Gabler to generate telephone numbers1), the “Bundesnetzagentur” data are used according to the following two rules: • Numbers from the German landline-based telephone network are generated on the basis of blocks of numbers with a range of 10 (so-called “Festnetzdatei”) • Numbers from the German cellular telephone network are generated on the basis of number blocks with a range of 10000 (so-called “Mobilfunkdatei”). As almost 100% of the households in Germany have a telephone and much more than 90% use at least one landline-based phone, representative telephone surveys of the German population can be conducted. Using the landline-based sampling frame has a further advantage. Due to the fact that the vast majority of these telephone numbers are listed with the owner's full address, the numbers in this sampling frame include regional markers. These allow stratified sampling procedures to be used, differentiating down to the community level or even to the district level in larger cities. Therefore the well-known, proven stratification method of face-to-facesurveys can be used here too. 1) Cf. S. Gabler, S. Häder; Ein neues Stichprobendesign für telefonische Umfragen in Deutschland; in: S. Gabler, S. Häder, J. H. P. Hoffmeyer-Zlotnik (Hrsg.); Telefonstichproben in Deutschland, S. 69 – 88, Opladen 1998 2) Cf. L. H. Cox; A constructive procedure for unbiased controlled rounding; in: Journal of the American Statistical Association 82, S.520 – 524, 1987 Due to the very small proportion of listed cellular phone numbers to non-listed numbers, the second sampling frame cannot be stratified according to regional strata. However since every provider of cellular telephone services has their own prefixes, this information can be used as a stratification criterion to improve the sampling design. To best utilize this stratification, sampling is done using the method for random allocation developed by L. H. Cox.2) A major advantage of this method is that it leads to stratified samples without any accumulation of rounding effects. As the sampling of the telephone sample, as well as the selection of the target persons within the households, is done randomly, the entire telephone survey is based on random sampling. Therefore surveys based on the ADM-Telephone-Sampling-System fully meet the scientific requirements regarding randomization based on statistical methods. Christian von der Heyde, Spokesperson of ADM Sampling Systems, July 2009 1) Cf. S. Gabler, S. Häder; Ein neues Stichprobendesign für telefonische Umfragen in Deutschland; in: S. Gabler, S. Häder, J. H. P. Hoffmeyer-Zlotnik (Hrsg.); Telefonstichproben in Deutschland, S. 69 – 88, Opladen 1998 2) Cf. L. H. Cox; A constructive procedure for unbiased controlled rounding; in: Journal of the American Statistical Association 82, S.520 – 524, 1987