In 2010, a task force commissioned by AAPOR produced a report that provided recommendations regarding how the survey research industry should approach the use of opt-in Internet panels. Their primary recommendation stated, ―Researchers should avoid nonprobability online panels when one of the research objectives is to accurately estimate population values‖ (AAPOR 2010, 52). Yet, the AAPOR task force also noted that, ―Despite the widespread use of online panels there is still a great deal that is not known with confidence‖ (54). Indeed, the mode study that arguably attracted the most attention in 2009 was conducted in 2004 (Yeager et al. 2009). Yet, studies conducted using data collected several years ago are unlikely to shed much light on the utility of opt-in Internet surveys today (or the increasing problems with RDD telephone polls). After all, Internet usage has increased significantly during the past several years while the use of landline telephones has declined. More importantly, the methods used to recruit panelists and generate representative samples from opt-in panels are undergoing constant innovation.

In this paper, we present data from a four-mode study carried out in 2010. National surveys were fielded at the same time over the Internet (using an opt-in Internet panel), by telephone with live interviews (using a national RDD sample of landlines and cell phones), by telephone with IVR (landline only), and by mail (using a national sample of residential addresses). Each survey utilized a nearly identical questionnaire soliciting information across a range of political and social indicators, many of which can be validated with surveys fielded by other organizations at the same time. Comparing the findings from the modes to each other and the external indicators, we demonstrate that carefully executed opt-in Internet panels are an increasingly valid way to measure public opinion in the United States.