Telephones and Polling

From our reading of Polling and the Public, one thing I found especially interesting was chapter 4 "Sampling Techniques" and chapter 5 "Interviewing and Data Collection Techniques" especially in respect to telephone and internet polls. Growing up I can distinctly remember my parents purposefully avoiding telephone calls during dinner time because they didn't want to talk to telemarketers or pollsters, and I'm sure I'm not the only one. As Asher notes, this problem of the nonresponse is becoming increasingly common due to things like caller ID or simply avoidance. Furthermore, fewer people actually own landlines making it increasingly difficult to contact and poll people through their private cell phone numbers. I was curious to see how this issue was being discussed in other news sources and found a great article from National Journal. 

The article begins by simply asking "Who responds to telephone polls anymore?," and the answer seems to be "not many, really." The article includes this graph from The Pew Research Center: 

Their data: 

• Percentage of households in which an adult was reached at all: 90 percent in 1997, 62 percent in 2012
• Of those successfully contacted, cooperation rate: 14 percent, down from 43 percent 15 years earlier. 
• Pew’s overall response rate—the rate of completed interviews to the number of phone numbers dialed—was just 9 percent, one fourth of the 36 percent level from 1997

The article makes some interesting observations about some of the factors that complicate telephone polling:

• "Over the past decade or so, the number of firms that conduct so-called interactive voice-response polls, in which respondents are questioned by a recorded interviewer and answer questions via keypad or voice recognition, has increased dramatically"
• "It is illegal to conduct an automated poll over a wireless phone, so those “robo-polls” ignore the sizable number of cell-phone-only households"

There seems to be a divide then in the demographic of respondents: either older individuals with landlines, or younger individuals with cell phones. If this article is to be taken as at all representative of the larger discussion of the telephone polling issue, then there doesn't seem to be much of a consensus reached. While the respondent base for landlines are dropping the cost for cellphone polling is increasing. Researchers seem to be looking to other social media platforms accessible through cell phones for their answers, but I think we have to seriously consider how scientific a poll can be with data pulled from Facebook, Twitter, or text. Ultimately it seems that while telephone polling may not be going away soon, its legitimacy is definitely being called into question with the emergence of pre-recorded or automated polls and a dramatically decreasing respondent pool.