1 / 28

PRESENTATION INFORMATION

PRESENTATION INFORMATION. DIVISION: STATISTICS SOUTH AFRICA, SOCIAL STATISTICS PROJECT: NATIONAL HOUSEHOLD TRAVEL SURVEY PRESENTER: DION PIETERSEN, STATS SA STATUS: FINAL TITLE: PHASES OF CONDUCTING A NATIONAL TRAVEL SURVEY. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY

marlon
Download Presentation

PRESENTATION INFORMATION

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. PRESENTATION INFORMATION DIVISION: STATISTICS SOUTH AFRICA, SOCIAL STATISTICS PROJECT: NATIONAL HOUSEHOLD TRAVEL SURVEY PRESENTER: DION PIETERSEN, STATS SA STATUS: FINAL TITLE: PHASES OF CONDUCTING A NATIONAL TRAVEL SURVEY

  2. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY • Design of the questionnaire • Testing and observational studies • Sampling • Field operations • Processing • Challenges • Comments and suggestions

  3. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY • DESIGN OF THE QUESTIONNAIRE • Stakeholders consulted: • National Department of Transport • TRC Africa Consortium • Statistics South Africa • External users – National Treasury • International consultants – Peter Jones • Advisory Committee

  4. STRUCTURE OF THE QUESTIONNAIRE • COVER – COVERING INFO ON PSU AND SAMPLED DWELLING UNITS • FLAP – STRUCTURE OF THE SAMPLED HOUSEHOLD SECTIONS ON: • DEMOGRAPHIC INFORMATION – AGE , GENDER, RACE • LEVELS OF EDUCATION • ACCESS TO FACILITIES • EMPLOYMENT AND UNEMPLOYMENT • MODES OF TRANSPORT • SCREENING QUESTIONS FOR WORKERS • INDIVIDUAL TRANSPORT QUESTIONS FOR WORKERS

  5. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY • TESTING AND OBSERVATIONAL STUDIES • Intensive Behind the Glass Testing of the questionnaire • 12 sessions • Pilot Survey 1 • Gauteng 2003 • Pilot Survey 2 • Mpumalanga 2003

  6. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY • SAMPLING FOR THE NTS • Step 1 • Overlap the 342 Travel Analysis Zone (TAZ) boundaries with the Census 2001 EA frame • Step 2 • Determine the number of EAs to be allocated to each of the TAZ’s. Need to use the number of dwelling units in the EAs as a measure of size. The power allocation method was used to determine the number of PSUs to be allocated per TAZ. • Step 3: • Creation of PSUs. • The PSU number consists of 12 digits, this was done by Geography. The first 8 digits represent the EA number and the last 4 digits represent the number of the PSU. • For example: • 124700120001 = Western Cape, PSU number 01

  7. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY SAMPLING FOR THE NTS, continued Step 4: Pooling EAs – Additional EAs were pooled to form PSUs if the selection criterion which a minimum of 80 dwelling units in an EA, where EA type and Area type must be the same as the original EA. If the original EA drawn was found to have too few dwelling units then the modified method of Kish’s pooling of EAs was to be used. Step 5: Determining the methodology for selecting dwelling units in the selected PSU. Once the 09 books had been copied, these were verified in the field during publicity PPS systematic sampling of EAs was used in all cases and equal probability systematic sampling was used to select the dwelling units that would be enumerated in each drawn EA. This allowed for approximate self-weighting of the selected dwelling units within each of the TAZ’s. Step 6: One person (aged 15 years and older) in each household at each of the selected dwellings was selected for enumeration in Section 7 (attitudes to transport services) in the questionnaire. Kish’s grid for selection of individuals in the household aged 15 years and older was used to determine who will be required to complete the attitudes to transport services.

  8. THE SAMPLE ALLOCATION TO EACH PROVINCE BY EA TYPE

  9. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY FIELD OPERATIONS The following personnel / Staff nationwide were used: 9 Provincial Survey Manager 30 Regional Survey Managers 95 Assistant Regional Survey Managers 9 Survey Clerks 1026 Fieldworkers 295 Supervisors 35 Data Capturers

  10. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY FIELD OPERATIONS – STAFF EMPLOYED

  11. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY FIELD OPERATIONS – VEHICLES USED

  12. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY FIELD OPERATIONS – MATERIAL ALLOCATIONS PER FIELD TEAM • Materials Per Team • Interviewer’s manuals • Supervisor’s manuals • Administrative Manuals • Questionnaires • List of PSUs allocated to Team • Copies of numbered 09 listings of the PSUs allocated to the Team • Maps of the selected EAs • ID cards • Introduction letter • Posters • Pencils/ pens • Erasers • Sharpeners • Log Book

  13. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY FIELD OPERATIONS – TRAINING • TRAINING WAS CASCADED TO 3 LEVELS – • NATIONAL TRAINING (TRAINING OF THE TRAINERS – CORE TEAM) • WHICH WAS ATTENDED BY THE CORE PROVINCIAL STAFF • 2. PROVINCIAL TRAINING • WHICH WAS COORDINATED BY THE CORE PROVINCIAL TEAM • 3. REGIONAL TRAINING (TRAINING OF THE FIELDWORKERS) • WHICH WAS COORDINATED BY THE ASSISTANT REGIONAL MANAGERS • MAP TRAINING PLAYED A CRUCIAL ROLE IN ALL LEVELS OF TRAINING

  14. PLANNING OF THE NATIONAL HOUSEHOLD TRAVEL SURVEY FIELD OPERATIONS – DATA COLLECTION • Initial data for the project was collected from 25 May to the 20 June 2003 • On 2nd September 2003, a delegation from the NDOT met with Stats SA to • discuss the status of response rates per Travel Analysis Zone. At this meeting a • joint decision was taken by Stats SA and the NDOT with regards to the TAZ’s: • 1. Travel Analysis Zones that were considered small, i.e. having 9 and/or fewer PSU’s • would require a TAZ response rate of not less than 90 % • 2. Travel Analysis Zones that were considered large, i.e. having 10 and/or more PSU’s • would require a TAZ response rate of not less than 85 % • With consultation with sampling experts at Stats SA, it was agreed that fieldwork take place in • 4 TAZ's that did not meet the above criteria: • Western Cape: 9002, • Mpumalanga: 5007 and 5015 • Limpopo: 7001 • In total 56 PSUs would be enumerated • Fieldwork: 20 November – 3 December 2003

  15. Reconciliation response rates

  16. CONSOLIDATED RESPONSE RATE

  17. PROCESSING OF THE NATIONAL TRAVEL SURVEY 2003 • Development of programs. • Capturing • Scanning • Editing • Receiving of boxes from the field. • Field ops checks all material arriving from the provinces • Boxes are handed over to processing. 4. Checking of enumerated sample. • Quality checking of questionnaires. • Coding of questionnaires.

  18. PROCESSING OF THE NATIONAL TRAVEL SURVEY 2003, continued • Cutting of questionnaires. • Scanning. • Capturing. • Editing of data. • Reducing of Scanned data.

  19. MIS and Project Coordination Documents issued and completed using Project Management • Contract with National Department of Transport • Business Plan and Detailed Budget • Project Organisation Chart • Project stakeholder list • Project registration form with the Office of Programme Coordination and MIS • Project kick-off meeting • Project brief/overview • Project scope of work statement • Project Work breakdown structure (WBS) • Project risk log • Project risk management form • Project key stage and sub-project responsibility chart

  20. Future recommendations: • If a project of this magnitude is to be undertake by the NDOT in conjunction with Stats SA the following points should be considered: • More time should be spent on the planning. • The manual needs clearer concepts and definitions that give more examples. • There should be training given to fieldworkers on how to sketch a map and what is needed on this map, if the Census 2001 09 Books are to be used . • A workshop held over a few days that involves the Provincial Survey Managers and other staff involved in the project should be organised. • The reporting forms for the monitors/quality assurers must be simpler so they can fill in all details in the field. • RSMs should have separated forms as they used the monitors reporting forms and completed them once the project had ended and forwarded them to Head office. • Trainer training as well as provincial training should be held most of the time in the field. Only concepts definitions and the questionnaire should be done in a training venue. • More evaluation exercises should be done during training after different modules such as concepts and definitions and then how to answer different sections within the questionnaire.

  21. PSU maps must be supplied by provincial training as a complete set instead of having a few coming at a time. • Provinces should be given more time to check the questionnaires after field operations. • QAs should remain in the provinces a week later to do control checks with the listings. • It is very important that collaboration with various divisions in Statistics South Africa work together on this project. The collaboration with geography almost did not work well at all. • The following persons should be involved in the project from first inception through to the end: Quality and Methodology staff, Prof. Stoker and Geography staff, external experts could assist in giving an objective point of view. • ASD Finance in all provinces must sign all documentation relating to finance including the operational plans • A form monitoring mileage of vehicles must be improved on.

More Related