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 37
Summary of Recommended Standardized Procedures and Guidelines 37 a likely value for missing data with no assurance that the imputed value is correct on a case-by- case basis. For example, if the number of vehicles owned by a household is missing, a likely num- ber could be imputed by considering the household income, number of licensed drivers, and age of the members of the household. Imputation is expected to produce the correct distribution of values for each variable even though individual imputed values are not necessarily correct. Imputation is the last resort in replacing missing or faulty data items with valid values. Every effort is first made to limit missing or faulty data through good survey design, well-managed survey execution, and aggressive editing and call-back to respondents. However, when the best efforts to obtain accurate reported information on each item fails, inference--followed by imputation--should be applied. Inference should always precede imputation because inferred values are more accurate than imputed values. It is recommended that the following standardized procedures be adopted with respect to imputation in household travel surveys: 1. Data editing should be conducted in all travel surveys; 2. Inference should always precede imputation; 3. Any imputation procedure with the exception of overall mean imputation may be used; 4. If hot-deck imputation is employed, it should be conducted without replacement; and 5. Every inferred and imputed value should be flagged in the data to clearly indicate its nature. 2.6.4 A-4: Data Archiving Archiving data preserves the data for future use; it is considered a method for maintaining the value of data and allows space to be freed on expensive data storage mediums. Archiving was not conducted in the past because transport agencies did not feel this was part of their responsibil- ity, agencies were reluctant to make their data readily available to the public, and archiving was not accounted for in initial budgets of projects. A key to effective data archiving is the assign- ment of responsibility and adequate funding in the initial stages of project design. The issue of archiving data is discussed at some length in Section 9.4 of the Technical Appendix. It is recommended that the transportation profession adopt the following principles to archive transportation data: 1. The sponsoring agency should be the primary organization responsible for archiving the data, associated metadata, and any relevant archiving auxiliary data. 2. Maps of zones, locations, and networks should be included in the archive. The recognized standard for storing travel behavior data is the ASCII format in order to overcome prob- lems associated with archived spatial data networks due to rapidly changing software. 3. Adequate documentation of the data should be archived. Any changes made to the data should be documented, and codebooks and documentation of sampling and weighting procedures need to be archived with the data. 4. Transportation documentation, preservation metadata, and archives should utilize the document type definition (DTD) such as extended markup language (XML). 5. Raw data should be archived. Modified data sets do not need to be stored as long as statis- tical tests and modifications made to the data are thoroughly documented. 6. Telephone recruitment and telephone or mail-back data retrieval and call history files describing call dispositions of sampled households during the recruitment process should also be archived. 2.6.5 A-6: Documentation This section, and Section 9.5 of the Technical Appendix, deals with how to document a house- hold travel survey. Currently, very little has been written about documentation of travel data. The
OCR for page 37
38 Standardized Procedures for Personal Travel Surveys term "metadata" in European literature is what is generally referred to in U.S. transportation lit- erature as "data documentation." There has been some writing on metadata in recent literature, but there are no standardized procedures for documentation of household travel surveys. The following is a comprehensive list of the ideal requirements for travel survey documenta- tion and is recommended for adoption as a consistent procedure for household travel survey documentation: 1. Sponsorship for the survey--name of the agency, ministry, or organization sponsoring the travel survey and, if the data were collected by an external research organization, the name of fieldwork agency. 2. Survey purpose and objectives--description of why the survey is being conducted, what it hopes to achieve, and expected results. 3. Questionnaire and other survey documents--wording of all questions including specific interviewer and respondent instructions. It also includes aids such as recruitment scripts, interview script (telephone and personal interview), maps, travel diaries, memory joggers, etc. These should be provided as an appendix. 4. Other survey materials--interviewer instruction manuals, validation of results (techniques employed), codebooks, incentive descriptions (pre or post; type of incentive; if monetary, the level offered). 5. Population and sampling frame--a description of the population that the survey is intended to represent as well as why this population was selected and a description of the sampling frame used to identify this population. 6. Sample design--a complete description of the sample design: sample size, sampling frame, information on eligibility criteria, and screening procedures. 7. Sample selection procedures--methods by which respondents were selected by the researcher, details of how the sample was drawn, the levels of proxy reporting tolerated, what constituted a complete household, and the sample size. 8. Sample disposition--refusals, terminations, ineligibles, completed interviews, and non- contacts. Also a description of the level of item non-response accepted for key variables and why. 9. Response rates--how the eligibility rate for the unknown sample units was determined, a description of the response rate formula used, and the calculation of the overall response rate for a two or more stage survey. 10. Processing description--editing, data adjustment, and imputing procedures used. 11. Precision of estimates--sampling error, including other possible sources of error to inform user of accuracy or precision, and a description of weighting or estimating procedures. 12. Basic statistics--a description of all base percentages or estimates on which conclusions are made. 13. Data-collection methods--survey mode and procedures. 14. Survey period--dates of interviews of fieldwork or data collection and reference dates for reporting--e.g., time, day, and date when calls or other forms of contact were made. 15. Interviewer characteristics--number and background of fieldwork staff. 16. Quality indicators--results of internal validity checks and any other relevant information such as external research. 17. Contextual information--any other information required to make a reasonable assess- ment of the findings and data. 18. Conduct of geocoding--a description of how geocoding was conducted, including the level of data imputation and inference and how these values are flagged, etc. It is also important for the documentation to incorporate organizational documentation. This includes the request for proposals and proposal submission, contracts and modifications, all progress reports, key meetings results, costs, key personnel, and information about situations