Jay Stewart (2002) "Assessing the Bias Associated with Alternative Contact Strategies in Telephone Time-Use Surveys."

In most telephone time-use surveys, respondents are called on one day and asked to report on their activities during the previous day. Given that most respondents are not available on their initial calling day, this feature of telephone time-use surveys introduces the possibility that the probability of interviewing the respondent about a given reference day is correlated with the activities on that reference day. Further, noncontact bias is a more important consideration for time-use surveys than for other surveys, because time-use surveys cannot accept proxy responses. Therefore, it is essential that telephone time-use surveys have a strategy for making subsequent attempts to contact respondents. A contact strategy specifies the contact schedule and the field period. Previous literature has identified two schedules for making these subsequent attempts: a convenient-day schedule and a designated-day schedule. Most of these articles recommend the designated-day schedule, but there is little evidence to support this viewpoint. In this paper, I use computer simulations to examine the bias associated with the convenient-day schedule and three variations of the designated-day schedule. My results support using a designated-day schedule, and validate the recommendations of the previous literature. The convenient-day schedule introduces systematic bias: time spent in activities done away from home tends to be overestimated. More importantly, estimates generated using the convenient-day schedule are sensitive to the variance of the contact probability. In contrast a designated-day-with-postponement schedule generates very little bias, and is robust to a wide range of assumptions about the pattern of activities across days of the week.


Last Modified Date: July 19, 2008