Re-designing the German job vacancy survey ─ assessing the impact of high non- response rates Hans Kiesl, Susanne Rässler Institute for Employment Research (IAB), Germany International Conference on Establishment Surveys III Montreal • June 18-21, 2007
15
Embed
Re-designing the German job vacancy survey ─ assessing the impact of high non-response rates
Re-designing the German job vacancy survey ─ assessing the impact of high non-response rates Hans Kiesl, Susanne Rässler Institute for Employment Research (IAB), Germany. International Conference on Establishment Surveys III Montreal • June 18-21, 2007. Background. - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Re-designing the German job vacancy survey ─ assessing the impact of high non-response rates
Hans Kiesl, Susanne Rässler
Institute for Employment Research (IAB), Germany
International Conference on Establishment Surveys IIIMontreal • June 18-21, 2007
2
Background
Information on job vacancies in Germany
Business units might report job vacancies to the Federal Employment Agency
Federal Employment Agency publishes monthly statistics on number of registered job vacancies (by industry class and NACE-sector)
IAB conducts a yearly (4th quarter) mail sample survey among business units to estimate number of job vacancies (registered or not) and to get additional information (e.g. about recruiting strategies)
Mail questionnaire (8 pages in length)
In the future: quarterly survey (CATI interviews in quarters 1-3)
After 2004 survey, CATI subsample of non-respondents to find out main reasons for non-response
sample of 1700 business units
26% no/wrong telephone number
16% not willing to respond
58% respondents; their reasons for non-response in job vac. survey:
75%: no time; too much work (88% for largest units)
27%: no job vacancies (41% for smallest units)
25%: no relevant topic (44% for smallest units)
17%: take part in surveys only if mandatory
9%: never take part in surveys
6
Impact of length of questionnaire (1)
During the 4th quarter of 2006 (at the same time of the regular survey with 8 pages) a separate survey was conducted (1 page, basic infos, e.g. number of job vacancies).
Questions:
Has length of questionnaire significant impact on response rates? (Prediction: yes)
If so, do different response rates lead to different estimates of number of job vacancies? (Prediction: yes)