Title
Inference From Multiple Frame Surveys
Speaker
Sharon Lohr, Arizona State University
Abstract
With the increasing demographic and technological diversity of the U.S. population, it is becoming more difficult for a single sample selected from a single sampling frame to adequately represent the population. Multiple frame surveys are increasingly used in situations where several sampling frames may provide better coverage or cost-efficiency for estimating population quantities of interest. Examples include combining a list frame of farms with an area frame, or using two frames to sample landline telephone households and cellular telephone households. We derive optimal linear estimators and pseudo-maximum likelihood estimators for the population total when samples are taken independently from each frame using probability sampling designs. The probability sampling designs used for the individual frames must be employed to obtain variance estimates and confidence intervals for quantities of interest, and we derive the properties of a jackknife method and two bootstrap methods for estimating variances in multiple frame surveys.
Meet the speaker in Room 212 Cockins Hall at 4:30 p.m. Refreshments will be served.
