Important notice about the Trips file

The core of the American Time Use Survey interview is the time diary, which contains information on the respondent’s activities on the day prior to the interview. Because the ATUS only asks respondents about “yesterday,” the survey may underestimate activities that occur on overnight trips away from home. Therefore, after the time diary is completed, respondents are asked a series of questions about trips away from home for 2 or more nights in a row. This information was collected and released in this file to provide researchers with some information about the number, duration, and purpose of overnight trips. This additional information about the purpose of trips may be used to adjust time-use estimates to correct for any bias that is introduced by the yesterday-report methodology.

Please note that this file does not contain weights. Therefore, these data should be used with caution:

• Results from using unweighted data will not be representative of the population.
• Neither the ATUS final weights nor the ATUS base weights, which are designed to be used with data in other ATUS files, are appropriate for use with the Trips file.

Unweighted ATUS data are not representative of the population due to differences between population groups in both sampling and non-response. To create weighted, representative estimates, the ATUS Respondent and Replicate Weights files contain two types of weights. The ATUS base weights (TUBWGT) account for differences in sampling intervals for respondents but not differences in non-response. The ATUS final weights (TUFINLWGT) account for differences in sampling and non-response between demographic groups. (See Chapter 3 of the Users' Guide for more information on sampling.)

Neither of these weights is appropriate for use with the trips data. Specifically, the ATUS final weights (TUFINLWGT) have been designed for time-diary data where the reference period is the previous day. The reference period for trips data is either the month before the initial contact attempt or two months prior to the interview month, whichever is most recent. Because weekdays are undersampled as diary reference days and are accordingly assigned larger weights, use of TUFINLWGT to weigh the trips data would give observations with weekday reference days disproportionate representation. There is also no simple correspondence between diary day and reference month for the trips data; respondents for the same diary date may have different reference months.

Researchers who use this file are encouraged to send feedback on the usefulness of the data by email.

Last Modified Date: January 12, 2007