I have been quite intrigued by a couple of aspects in RDD telephone surveys, a mode that is generally marred by very limited (if any) information on sample numbers and limited techniques that could be applied to tackle nonresponse, relative to face to face surveys. First, there is some information that can be merged from other sources. Such data are either quite aggregated, such as census demographic estimates at the tract or block group levels, or have doubtful measurement properties, such as commercial data at the household or person level. Second, response propensity is not a property of a person. What is done on the first call attempt can affect later outcomes. An inexperienced interviewer may, for example, reduce the likelihood that a sample member is interviewed even if the best interviewer calls the case on the next call.
Based on these two premises, we have been running several experiments in this past quarter, in a continuous multi-phase telephone survey. Cases were randomly assigned (1) to be left a voicemail or an answering machine message on the first call, (2) to be called in different parts of the day and different days of the week based on census data and outcomes from previous quarters of data collection, and (3) assigning cases predicted to be less likely to participate to be called by more experienced and highly performing interviewers on the first call attempt.
So far it looks like only the last intervention, the most difficult to implement, made an impact on survey participation. More results to follow...
