Data collection for March Omnibus Household (HH) Survey began on March 7, 2001, and continued until March 13, 2001. Calls were placed between 9:00 a.m. and 9:00 p.m. local time in all regions of the country. Approximately 64 interviewers were trained for the study. Data was collected from households in the U.S. using a random-digit-dialed telephone survey method. The final data set includes 1,137 completed cases, and a total of 172 variables. Battelle collected the data under contract with BTS.
For this survey, 11,721 telephone numbers were purchased from Marketing Systems Group's GENESYS Sampling System. Of these, 7,000 were identified as working, residential telephone numbers and were divided into 28 replicates of approximately 250 households. Nine of the sample replicates were not needed, resulting in 4,750 numbers being released for use by the telephone interviewers. For this survey, the total number of telephone numbers in the sampling frame was 246,870,500.
The procedure for response rate calculation is based on the guidelines established by the Council of American Survey Research Organizations (CASRO). The final response rate for the survey was obtained using the following formula:
Table 1. Distribution of Household Cases by Disposition
|Number of Telephone Numbers Released||4,750|
|Number of Out of Scope Numbers (ineligible)||1,156|
|Number of No Contacts (Scope Undetermined)||807|
|Number of Households In scope||2,787|
|Number of Completes||1,137|
|Number of Partial Completes||39|
|Number of Language Problems||148|
|Number Not Screened||136|
|Number of Refusals||1,056|
|Number of Parental Refusals||0|
|Number of Respondents Identified, Cases not Finalized||181|
|Number Unavailable During Study Period||90|
|Household Response Rate||33.9%|
Follow-up efforts were limited to 15 attempts to determine whether a telephone number was residential, an additional ten attempts to identify an eligible respondent, and a final ten attempts to secure a completed interview or refusal. Therefore, the maximum number of call attempts to any household was 35. Once contact was made with a household, follow-up attempts followed a loose callback schedule established at the initial contact. That is, good times and days to call back were requested at the initial contact, but follow-up calls also were attempted before these appointment times, unless otherwise told not to do so by the household. This allowed for making the maximum number of attempts within the study period.
The March survey included refusal conversion interviews during March 11-13, 2001, to increase response rates. Fourteen highly experienced refusal conversion specialists attempted to complete the interview with 938 households that had previously refused to participate. From those attempts, 115 households completed the survey.
Prior to the start of actual data collection, a pretest was conducted to test the usability of the survey instrument. Particular focus was placed on testing questions that were new to the March survey. Qualified data collection and data preparation staff performed this pretest by first reviewing the questionnaire and then using it in simulated data collection situations. They looked for vague or confusing instructions; inconsistent questions or answer categories; incomplete or redundant sections; and poor pace, tone, flow, and format of questions. They also tested the interview length and determined that the survey questionnaire could be administered in approximately 12 minutes.
For the March Household Survey a pre-contact letter was included in the study protocol. Address information matching the sampled telephone numbers was purchased from Marketing Systems Group's GENESYS Sampling System for approximately 46% of the sample. A letter introducing the survey was then mailed to each of these addresses about five days before telephone interviews were conducted. The letter explained the procedures of the survey, encouraged participation, and was endorsed by Dr. Ashish Sen, Director of the Bureau of Transportation Statistics.