While nationwide face-to-face conducted samples are regarded as representative for the total population, online-samples are regarded as biased, especially in terms of age, sex and education. To consider this bias, the data can be weighted in order to receive a representative sample. In case of online surveys, older women with low education receive a very high weight and young men with high education a very low one. Instead of weighting the data, for this study a stratified random sample was drawn out from over 20.000 participants of an online panel. Thereby, older women with relatively low formal education had a very high likelihood to enter the sample, young men with high education a very low one. For comparing these data with representative, face-to-face conducted data, we used a set of questions from the German General Social Survey 2002. On the basis of more than 1.500 cases each that are equivalent in terms of age, sex and education, we compare the results of the two studies.