Prediction of Cell Phone versus Landline Use in the General Social Survey

The rise of cell-only households (those in which a cell phone is the household’s only telephone service) has decreased the coverage of the landline telephone and may have introduced bias into landline survey samples. This paper considers ways in which cell-only and cell-mostly households may differ from the landline-only and landline-mostly populations thereby identifying factors which, when added to the list of weighting factors, may increase the accuracy of landline samples and serve as a warning of where coverage bias may be a problem in the future. These factors were analyzed in an ordinal logistic regression, using data from the 2008 General Social Survey, in order to assess their ability to predict landline and cell phone use. In addition to age, other variables were found to predict phone use including income, homeownership, transitivity, and party identification. This article is available in Res Publica Journal of Undergraduate Research: http://digitalcommons.iwu.edu/respublica/vol15/iss1/7