| Abstract: | Accurately assessing the number of household phone lines inrandom-digit dialed (RDD) surveys for use in weighting has becomemore complicated over time. This study evaluates phone lineweighting by asking an in-depth battery of seven questions designedto measure the number of available land lines in the home moreprecisely. The results show that this weighting correction isnot so simple, and that inadequately parsing the type and useof household phone numbers produces an inaccurate weight. Failingexplicitly to remove irrelevant phone numbers, especially cellphones, produces a larger-than-appropriate weighting adjustment.Potentially more important on a practical level is that, whendone correctly, and even when "overdone," phone line weightinghad little impact across a diverse set of opinion and demographicvariables. |
