Relevance & Research Question:
The usage of incentives is a widely accepted measure in survey business to enhance response rates. The impact of incentives is extensively tested in the context of mail survey and interviewer mediated modes of data collection. Less is known about incentives in the context of panel recruitment especially for offline-recruited online panels. Furthermore most experimental studies on incentives focus on the response rate as the only outcome variable. The effect of paying respondents on the sample composition has not been given much attention. Even though there is some evidence that some groups that are usually underrepresented in surveys (e.g. low educated) are motivated by the incentive.
Methods & Data:
We conducted three experiments within a telephone recruitment interview for a probability-based online panel during January 2011 and August 2011. At the end of the interview all respondents were asked whether they are willing to join a scientific online panel and fill out online questionnaires on a monthly basis.
In the first experiment we tested conditions 1) and 2). In the second and third experiment conditions 3 through 5 were tested. The interviews of experiment 2 and 3 were conducted by two different institutes and varied in specific interview aspects.
1. 5 Euros + additional 20 Euros bonus for filling out all eight online interviews of the study
2. 10 Euros + 20 Euros bonus
3. 5 Euros, no bonus
4. 2 Euros, no bonus
5. No incentives (control)
The dependent variables are willingness to participate in the online panel, the rate of actual participation in the first online interview, and the overall response rate. The effect of incentive on sample composition is analyzed as well.
Results: First analyses show interesting results. The expected tendency that higher incentives produce higher response rates is confirmed. However, we cannot find any differences in sample composition between the experimental groups.
Added Value: The experiments shed light on usage of incentives during the panel recruitment process. It can be shown that using incentives in the second step of a multistep recruitment process has no (further) implication on panel composition.