1 / 14

Knut Kalgraff Skjåk Kirstine Kolsrud

Experiences with mixed mode mail & web-enquêtes in probability samples with known individuals. Knut Kalgraff Skjåk Kirstine Kolsrud. Norwegian Social Science Data Services. 2nd WEBDATANET Meeting, Amsterdam, 30 November 2011. Presented by Knut Kalgraff Skjåk. Background.

sutton
Télécharger la présentation

Knut Kalgraff Skjåk Kirstine Kolsrud

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. Experiences with mixed mode mail & web-enquêtes in probability samples with known individuals Knut Kalgraff Skjåk Kirstine Kolsrud Norwegian Social Science Data Services 2nd WEBDATANET Meeting, Amsterdam, 30 November 2011 Presented by Knut Kalgraff Skjåk

  2. Background International Social Survey Programme (ISSP) • Annual social survey • NSD, Norwegian member and responsible for ISSP Norway since 1989 • The ISSP surveys • Topics of central importance for cross national social science (Role of Government, Social Inequality, Religion, Family and Gender Roles, Work orientation, Environment etc) • 11 topics fielded to date, repeated at intervals • 60 topic items + 40 background variables • Mode of administration: self-administration and face to face • National representative random samples aged 18 and older.

  3. Background National setting • Sample frame: National Population Register (named individuals) • Restricted number of reminders • Restricted budgets • Mode: self-administration • Information, deliveries and social exchange by post

  4. Unit nonresponse in ISSP Norway 2000-2009Total and selected age/gender groups

  5. Other biasNonresponse among younger men, 2011, by place of living Oslo Next three largest cities Rest of the country Representing men 18-24 years in Oslo

  6. Why introduce websurvey? • Mixed mode design, freedom of choice, reduce unit nonresponse and increase data quality • More attractive for certain groups • No “mailbox effect” • Administrative advantages • Low cost • Collected electronically, no transfer costs • Data file created on the spot • Administrative records continuously updated • Paradata • Quality • Control of skip patterns • More detailed response to open ended question (Schaefer & Dillman 1989) • Less item non-response ?

  7. Implementation of experiment 2011 • Gross sample 3 600 persons aged 18-79 • 2 modes of self-administration, Web and PaP • Aims • decrease in unit nonresponse • maximised share of Web-respondents, (reduce bias) • Contact design • Split ballot (1 800 + 1 800) • Group 1. “This is a Websurvey” • Group 2. “This is a mixed mode survey”

  8. Timeline

  9. Results Response rates1 by response mode, and 1st response mode offered

  10. Item nonresponse 1 – topic module

  11. Item nonresponse 2 – verbatim recorded answers Occupation of respondent: Web: 8,2 % missing Paper: 11,5 % missing

  12. What is next? • Keep mixed mode with Web and PaP • Target groups for tailored contact design? • Possibilities for obtaining e-mail addresses • By phone? • Reminders by phone? • Split ballot with a clean post-enquête sample • Sample design: stratify by gender, age groups and region • Analyses of mode effects

More Related