44 – Address Based, RDD and Cell Phone, and Respondent-Driven Sampling
A Review of the Cell Phone Sample Component of the California Health Interview Survey
J. Michael Brick
Westat
Ismael Flores Cervantes
Westat
David Grant
University of California at Los Angeles
Jennifer Kali
Westat
Greg Norman
Westat
Greg Norman
Westat
This paper describes the history of cell phone sample component of the California Health Interview Survey (CHIS). CHIS is a random digit dialing (RDD) telephone survey of California's population conducted since 2001. The objectives of CHIS are to examine issues in public health and health care and to monitor changes over time for Californians. In the last decade, the increasing noncoverage bias in landline surveys is mainly the result of the increased popularity of cell phone use accompanied by a rise in the number of cell phone-only households. This noncoverage problem has been formally addressed in CHIS beginning in 2007 after the completion of a pilot cell phone sample used to interview cell-only households in 2005. In 2007, an expanded cell phone sample was used to supplement the landline sample with cell-only households. In 2009 and 2011, the cell phone sample was modified to include respondents with both telephone services. In 2011, the cell phone sample was expanded to include targets at the county level. This paper describes our experience with the different methodologies used in sampling and estimation for this dual frame approach used in CHIS.
