Cover Image

Not for Sale

View/Hide Left Panel
Click for next page ( 31

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 30
30 Standardized Procedures for Personal Travel Surveys Verifying that one trip starts where the other finishes; and Cross checking reported distances and times with those calculated from geocoded points. 2.5.2 C-2: Level of Geocoding To Be Performed It is theoretically possible to geocode 100% of all trip ends in a survey, but in practice this is difficult, if not impossible. Most travel surveys will encounter some difficulties in geocoding, so there is a need to determine a reasonable minimum match rate that could be achieved in most survey settings. The reader is referred to Section 8.2 of the Technical Appendix for further infor- mation on this topic. It is recommended that standardized procedures be adopted so that 1. Surveys should successfully geocode no less than 99% of household addresses, 95% of school and workplace addresses, and 90% of other locations to latitude/longitude. 2. Any locations that cannot be geocoded to latitude/longitude should be referenced at least to a TAZ to avoid systematic bias. 3. Where it is not possible to match out of region locations with a TAZ, it is proposed they be assigned to a representative point outside the study area. 2.5.3 C-4: Missing Values, Use of Zero, Etc. There is considerable variability in how missing data are recorded in transport surveys and even variability within the same survey. The issues in this item, which are discussed in detail in Section 8.3 of the Technical Appendix, relate to standardizing the ways in which missing data are flagged and how zeroes and blanks are to be used in coding. It is recommended that the following standardized procedures be adopted together as a group because adoption of some without others will actually increase ambiguities in the data: 1. No blanks: Blanks should never be a legitimate code, and all data fields must contain alphanumeric data. 2. Missing data: Missing data--whether as the result of a respondent refusal, an indication that the respondent does not know the answer, or a legitimate skip of the question--should receive a coded numeric value. These values should be negative values (because negative values will not normally occur in a data set) and should be -99 for a refusal. For "don't know" responses, it should be set as -98. For legitimate skips or non-applicability of a ques- tion, the value -97 should be entered. 3. Correspondence between numeric values and codes: In any question where a legitimate response could be zero, the code for that response will be the number zero (0). This will normally apply to any question requesting a count of elements, where a count of zero is possible--e.g., number of workers in the household, number of children in the household, number of infants in the household, number of cars available to the household, etc. In like manner, the count that is the response will be the coded value in all cases. 4. Coding the number of person trips reported: In all personal travel surveys that seek to ascertain trip-making behavior of individuals, the person record should contain a count of the number of trips reported by the individual. A count of 0 is to be used only to indicate the response that the person did not travel on the diary day. If no travel information was provided, then the value coded should be -99. 5. Coding binary variables: The principal binary variables in personal travel surveys are yes/no responses and responses to gender. For questions to which the response is either "yes" or "no," the response of "yes" is coded as 1 and the response of "no" is coded as 2. For response to the gender question, "male" is 1 and "female" is 2.