Cover Image

Not for Sale



View/Hide Left Panel
Click for next page ( 20


The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement



Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.

Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.

OCR for page 19
Summary of Recommended Standardized Procedures and Guidelines 19 households, with potential sample biases arising. On the other hand, too lenient a definition will likely result in poor estimation of household travel. Further discussion of this is to be found in Section 5.3 of the Technical Appendix. The following standardized procedures are recommended: 1. At least key household, person, and vehicle information be obtained. In other words, the minimum set of questions outlined in Section 2.1.1 of this report should be answered for a household response to be considered acceptable or valid. Other key information may also be required for the response to be considered complete, but this is dependent on the spe- cific objectives of the survey. 2. At least an adult from every age group represented in the household, as well as younger household members if eligible, should complete the trip/activity data items specified in Sec- tion 2.1.1. These age groups may be the following: 1517 (if household members under the age of 18 are eligible), 1864 years, 6574 years, and over 74 years. 3. For the last three age groups, proxy reports should not count towards determining com- pleteness of the household. 4. Partial responses should not be eliminated from the data set. Partial information can be useful and these households may be re-contacted in various follow-up exercises. Complete person information from incomplete households can be used in various applications. Also, it is a waste of resources to remove households from the data set. This is important given increasing survey costs. 2.2.4 D-6: Sample Replacement Refusals result in lost sample and require some sample make up or replacement. Procedures for sample replacement are critical in preserving the integrity of the initial sample. Two questions arise: 1. When should a sampled household or person be considered non-responsive and a replace- ment make-up household or person be selected? 2. How should replacements for the sample be provided? Detailed discussion of this issue is to be found in Section 5.4 of the Technical Appendix. The following standardized procedures are recommended: 1. Conduct a pilot survey. A pilot survey should be conducted to enable the estimation of the expected non-response rate. This will help with developing the required sample size. (See also Section 2.3.1 of this report.) 2. Draw a large initial sample. To overcome unanticipated sample loss, it is suggested that the initial sample that is drawn be much larger than the final required sample, taking into account the expected non-response rate, and then increasing beyond this to allow for unforeseen problems. 3. Preserve the draw order of numbers. The order in which numbers are drawn needs to be pre- served and contact made strictly in that order. For example, for a random digit dialing (RDD) list, numbers listed later in the list should not be recruited before numbers listed earlier in the list have either been recruited or discarded. 4. Create additional sample. If using RAND (RAND Corporation, 1955) random numbers, additional sample may be created and drawn after the initial sample has been exhausted. If using RDD lists, this should not be done because the two random samples will not be related and bias may be introduced.