2009
DOI: 10.1111/j.1475-5890.2009.00100.x
|View full text |Cite
|
Sign up to set email alerts
|

Item Non‐Response to Financial Questions in Household Surveys: An Experimental Study of Interviewer and Mode Effects*

Abstract: We analyse the determinants of non-response to questions on financial items such as income and asset holdings in household surveys. Our data come from a controlled field experiment. As part of the SAVE study -a representative survey conducted in Germany in 2001 -questions on household income and financial assets were administered using different modes (personal interview versus drop-off questionnaire). The data also allow us to investigate the influence of interviewer characteristics on nonresponse. Our result… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
10
1

Year Published

2012
2012
2022
2022

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 25 publications
(11 citation statements)
references
References 22 publications
(20 reference statements)
0
10
1
Order By: Relevance
“…9 To be precise: the interview is conducted with the individual who knows best about the household's finances. 10 As in all surveys that deal with sensitive topics such as household finances, item non-response to sensitive questions is not ignorable (see Essig and Winter (2003) and Schunk (2006) for discussion and documentation). To prevent biased inference based on an analysis of complete cases only, an iterative multiple imputation procedure has been applied to the SAVE data (Schunk, 2008).…”
mentioning
confidence: 99%
“…9 To be precise: the interview is conducted with the individual who knows best about the household's finances. 10 As in all surveys that deal with sensitive topics such as household finances, item non-response to sensitive questions is not ignorable (see Essig and Winter (2003) and Schunk (2006) for discussion and documentation). To prevent biased inference based on an analysis of complete cases only, an iterative multiple imputation procedure has been applied to the SAVE data (Schunk, 2008).…”
mentioning
confidence: 99%
“…1 1 See, e.g., Essig and Winter (2009), Kalwij (2010) We consider correlations that can be useful in the assignment of interviewers to respondents. Of particular interest are our data on interviewing style.…”
Section: Introductionmentioning
confidence: 99%
“…Overall, the dataset consists of 1,538 individuals apart from the estimations that include the two income variables HH income and Individual income. These variables are typically prone to missing values; however the share of missing values is -compared to other surveys -relatively small within this dataset (see Essig and Winter 2009). Apart from the variables age and age squared, all other independent variables are binary.…”
mentioning
confidence: 97%