1 / 20

Survey Design with a Focus on Model Validity

Survey Design with a Focus on Model Validity. 11th National Transportation Planning Applications Conference May 6-10, 2007, Daytona Beach, Florida. Stacey Bricka | NuStats | 512-306-9065 | sbricka@nustats.com Kermit Wies | CMAP | 312-386-8820 | kwies@cmap.illinois.gov. Overview of Presentation.

teenie
Download Presentation

Survey Design with a Focus on Model Validity

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. Survey Design with aFocus on Model Validity 11th National Transportation Planning Applications ConferenceMay 6-10, 2007, Daytona Beach, Florida Stacey Bricka | NuStats | 512-306-9065 | sbricka@nustats.com Kermit Wies | CMAP | 312-386-8820 | kwies@cmap.illinois.gov

  2. Overview of Presentation • Study Environment • Design Approach • Findings

  3. McHenry Lake Kane DuPage Cook Kendall Will Grundy Study Environment • Geography • 8 Counties • 4,000 square miles • Population • 2,940,007 households • Diversity • Residents • Languages • Travel Modes • Political Environment • Changing Technology • Telephone Service • Travel Demand Modeling

  4. Inventory Objectives • Document demographic and travel behavior characteristics of the region • Support update of the regional travel demand model • Serve as inputs for the development of a new regional travel demand model  Model Validity

  5. Design Phase Objectives 1. Confirm inventory contents 2. Validate budget assumptions • Establish “typical” conditions • Identify unique conditions, remedies, and associated costs • Evaluate most effective survey administration options 3. Vet recommendations

  6. Design Approach Community Outreach Passive Recruitment Traditional Pilot White Papers Peer Review Final Study Design

  7. Passive Recruitment • Objectives • Low-Cost Recruitment Mode • Contact Non-Telephone HH • Action • Address-based Sample • Mailed 1000 Letters with Brochure and Mail/Web Recruitment Survey • 50% received $2 incentive

  8. Passive Recruitment • Results • 53 HH returned surveys (6%) • 37% were non-telephone households • 83% received an incentive • No statistical differences from phone recruits • 38 non-participating HH debriefed • Only 28% recalled packet • 39% said would have participated if we called them

  9. Passive Recruitment • Full Study • Advance Mailings Included in Full Study • Mail to Active and Passive Sample • Capture of Cell-Only HH • Lower-cost Recruitment • Mailed 10,000 letters to Date • 225 passive recruits (~10% of all recruits) • 4% non-landline HH • 1-person/1-worker HH • Higher reported use of Auto

  10. Community Outreach • Objective • Identify and ameliorate participation issues • Action • Held 4 community group meetings

  11. Community Outreach • Results • Identified Design Improvements • Identified Activities to Increase Participation • Full Study • Design – Reflected Community Group Input • Lower Participation among Target Groups • Phase 1: Advance Mailings, Incentives, Tailored Interviewing, Multiplicity Sampling • Phase 2: Community Groups • Phase 3: In-Person Interviewing

  12. Traditional Pilot • Objectives • Establish “typical” conditions • Evaluate respondent reaction • Action • Three Pilot Test Areas • Three Diary Types • Two Survey Lengths • Incentives Test

  13. Traditional Pilot

  14. White Papers • Objectives • Recommend Final Study Design • Recommend Inventory Elements • Action • Identified Primary Data Elements for Pilot • Analyzed Pilot Data and Secondary Data • Presented & Discussed Recommendations

  15. White Papers • Results • Inventory Contents • Sampling • Efficient Data Collection • Maximizing Participation www.nustats.com/chicago

  16. White Papers • Full Study • Identified data elements • Support Model Update • Develop New Model • Sampling based on density and transit access • Phone/Mail/Web Options

  17. Peer Review Panel • Objectives • Vet Design Recommendations • National and Local “Experts” • Action • Presented Pilot Results and White Papers • Obtained Local Stakeholder Input • Full Day Discussion of Each Design Element

  18. Final Project Design • 11,600 HH • Mix of 1-day and 2-day HH • Year-long Data Collection Effort • 300 HH 7-day GPS Component • 1,000 SP Follow-up Surveys

  19. Findings • In-depth Design Phase Was Worth It • If Budget Constrained, Secondary Data Helpful • Peer Review Panel Input Was Invaluable • Mix of Local and National • Focus on Model Validity • Driving Question for Evaluation • Identify Data Elements for Current and Future Model Updates

  20. THANK YOU! Questions or Comments?

More Related