Download presentation
Presentation is loading. Please wait.
Published bySharon McCoy Modified over 6 years ago
1
Attrition and Selection of alteri Respondents in the pairfam panel
Ulrich Krieger, SHARE MEA University of Mannheim Mannheim Research Institute for the Economics of Aging
2
Outline Motivation The pairfam Panel
Overview of cooperation and response in partner survey Model of cooperation in wave 2 2
3
Motivation Attempt to include alteri respondents in surveys like partners, parents or siblings raises questions on the selection process of these additional survey members. Reviewers continue to criticize the selectivity. The processes need to be better understood. Weighting Limitations of research Recent analysis with the Netherlands Kindship Panel Study show no bias in models using data of children (Kalmijn & Liefbroer 2011). But how to model the error in the sample? 3
4
The pairfam Panel First two waves of the German family panel study pairfam. Design: Register based sample of resident population. Three age cohorts: 14-17, 24-27, 34-37 CAPI study administered by Infratest Partner survey All respondents in a partnership are asked for consent to approach their partners for an interview. within or outside of the household PAPI questionnaire handed out, left behind with main respondent or mailed to partner. collected by the interviewer or returned by mail 4
5
The Role of the Interviewer
Interviewers are encouraged to administer the partner survey the way preferred by respondents to occupy the partner with the partner survey during the main respondents CAPI questionnaire. to collect the questionnaire in person Request the partners to participate in person whenever possible 5
6
the pairfam panel - wave two
Anchor: monotonous design, only respondents re- approached. Partners: Same design as in wave one. Consent request to Anchor, then partners are contacted. Partners can be the same as in wave one if the relationship did hold. Partners who refused to answer in wave one are contacted again. 6
7
Cooperation and Response - Wave one
% Anchor 12402 with partners 7234 100 consent to partner interview 5281 73 returned partner quest. 3743 52 lost for W2 due to anchor NR 877 12 7
8
Cooperation and Response - Wave one
% Anchor interview 9069 with partners 5408 100 same partner as in W1 4273 95 Consent to partner interview 3882 73 Consent in both waves 3009 56 returned partner questionnaire 2688 50 returned partner quest. in both waves 2081 38 8
9
Both processes are probably not independent of each other
Two error sources: Selection of main respondent and Nonresponse of Partner Both processes are probably not independent of each other Unsure about how to model the Data Here: logistic Regression on wave 2 cooperation, concentrating on main respondents keeping the same partner over the 2 waves. 9
10
Descriptive Statistic
Variables mean sd min max W2 Part. cooperation .58 1 W1 Part. cooperation .64 W2 Main Resp: Consent .20 W2 Survey handed out .38 Part. fulltime empl. .55 Part. parttime empl. .09 Part. self empl. .06 Part. Years of educ. 12.92 3.08 7 20 Partner female? .42 Partner born in Germany? .85 Main: Satisf. Relationship 7.99 2.15 10 W2 Main: Satisf. Relationship 6.80 2.50 N: 3748 10
11
Log. Regression on W2 Partner Coop (only ‘stable’ Rel.)
Variables OR (se) W1 Part cooperation 11.26*** (1.28) W2 Main Resp: Consent (0.13) W2 Survey handed out 4.85*** (0.46) Part. fulltime empl. (0.11) Part. parttime empl. 1.42* (0.25) Part. self empl. 0.64* (0.13) Part. Years of educ. 1.07*** (0.02) Partner female? (0.12) Partner born in Germany? 1.40** (0.17) Main: Satisf. Relationship 1.06** (0.02) W2 Main: Satisf. Relationship 0.94** (0.02) N:3748, Pseudo-R²:0.32, BIC: 3538
12
Conclusion Cooperation and Consent in Wave 1 do influence cooperation in wave 2 How to better describe the selection process? Here I focused on stable relationships. How to include all relationships, new partners? 12
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.