In our pre-election survey on the strength of Americans’ social networks, we found that nearly one in five Americans (17 percent) reported having no one they were close with, marking a 9 percentage point increase from 2013.1...
[T]here is good reason to believe that the polls might be missing some of these people who don’t have strong social ties. Social isolation, or the lack of social integration, has long been thought to reduce willingness to participate in surveys. Americans who feel alienated or isolated from society do not feel compelled to participate in surveys out of a sense of civic obligation.
Researchers at the University of Nebraska-Lincoln and Hiroshima University have shown that Americans with weaker social connections are less inclined to cooperate with survey requests and that some survey estimates may be “systematically biased due to nonparticipation from socially isolated people.” Our survey was not suited to uncover the reasons for why people didn’t participate, but we did find that those with smaller social networks are far less politically engaged. For example, Americans with at least four social ties are three times more likely than those with none to have contacted an elected official in the last 12 months.
However, there may not be an easy solution to this problem. Providing financial incentives to bolster cooperation might help, as would increasing the duration of the survey field period. These are standard practices in survey research to increase representation among difficult to reach groups. But it’s not clear at this point whether incentivizing respondents or lengthening the interviewing period would increase participation rates among Americans who are socially isolated. A 2000 study found that increasing an interview period from five days to eight weeks made little difference in the final results — although perceptions of the Republican Party were more positive in the survey that included the longer interviewing schedule.