Scott Keeter of the Pew Research Center has an interesting research note in the current issue of Public Opinion Quarterly (Spring, 2006). He looked at whether the exclusion of cell phone only voters from telephone polls for the 2004 elections created any bias in the estimates. The answer: No. He points out that cell phone only households are primarily a life style choice of the 18-24 and 25-29 age groups. But , at least where political attitudes are concerned, they are not all that different from others in their age cohorts. So while the undercoverage is a potential problem, weighting by age seems to correct for it. Good news, for now.