Contemporary survey industry faces two highly challenging problems: declining response rates and growing costs of data collection. The (re-)balancing of data quality and costs thus presents one of the central research efforts of modern survey methodology. This became even more apparent with the rise of web surveys, which offered a new potential for the cost reductions. However, the problem of non-coverage and even lower response rates than in traditional survey modes are the key factors preventing a higher penetration of the web mode into official and academic research of the general population. Investigations of mixed-mode designs and mechanisms for improving response rates (like incentives) are thus very important for a cost-effective and high-quality survey data collection.

This paper presents the results of a study on the optimal integration of the web mode into a probability sample survey of the general population in Slovenia. For the purpose of the study, we conducted an experiment in Slovenian implementation of an official Eurostat survey on the ICT use in households using a mixed-mode design. A probability sample of Slovenian citizens was divided into several experimental groups, manipulating different survey modes (web, telephone and mail) and different types of incentives (5 euros cash incentive, a small gift or no incentive). Individuals were initially invited to complete the questionnaire on the web. Those who did not respond were subsequently contacted using one of the traditional modes (telephone or mail survey).

In order to identify the optimal survey design, we developed an optimization model that takes into account response rates, errors and costs at different stages of each experimental design. Errors are here estimated using the Mean Squared Error (MSE) approach. The paper evaluates the results obtained by the model and discusses the effectiveness of mixedmode surveys and incentives for achieving the optimal balance between errors and costs.