Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste
There is an inherent tension between traditional norms and survey protocols for quantitative data collected in the developing world. Unexpected interactions between the interviewer and respondent can lead to interviewer effects in the data, particularly in the case of subjective or sensitive questio...
| Main Author: | |
|---|---|
| Format: | Working Paper |
| Language: | en_US |
| Published: |
World Bank Group, Washington, DC
2015
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10986/21647 |
| id |
okr-10986-21647 |
|---|---|
| recordtype |
oai_dc |
| spelling |
okr-10986-216472021-04-23T14:04:03Z Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste Himelein, Kristen living standards methods communities rights court access to justice interviews market research science politics time research working papers woman family description income participation age gender survey methodology quantitative data data collection pornography information services household social science effects youth incentives health sanction samples muslim women size project projects market corruption surveys economics measures gender characteristics regression analysis head of the family justice women’s rights sex theory techniques genders evaluation training development economics households tests sampling data quality feminist survey data law estimates organizations statistical analysis community indicators marriage women research methodology standards residence female modeling weighting service districts improvement design There is an inherent tension between traditional norms and survey protocols for quantitative data collected in the developing world. Unexpected interactions between the interviewer and respondent can lead to interviewer effects in the data, particularly in the case of subjective or sensitive questions. This paper makes use of a unique data set available from Timor-Leste containing subjective and objective questions to study these effects. In addition to their age and gender, data were collected from the interviewers regarding their opinions on the subjective questions prior to fieldwork. Fixed effects and mixed effects logit models are used to examine the main effects and interactions between interviewer and respondent characteristics. More objective measures serve as a pseudo control group. The paper finds interviewer effects in the both subjective and objective data, but the magnitude is considerably stronger for subjective questions. The paper also finds that female respondents are more susceptible to influence based on the interviewer's beliefs. Despite methodological shortcomings, the study highlights the need to consider more fully the impact of traditional cultural norms when conducting quantitative surveys in the developing world on topics that are outside the standard objective questions. 2015-03-30T20:50:42Z 2015-03-30T20:50:42Z 2015-03 Working Paper http://hdl.handle.net/10986/21647 en_US Policy Research Working Paper;No. 7208 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo World Bank World Bank Group, Washington, DC Publications & Research Publications & Research :: Policy Research Working Paper East Asia and Pacific Timor-Leste |
| repository_type |
Digital Repository |
| institution_category |
Foreign Institution |
| institution |
Digital Repositories |
| building |
World Bank Open Knowledge Repository |
| collection |
World Bank |
| language |
en_US |
| topic |
living standards methods communities rights court access to justice interviews market research science politics time research working papers woman family description income participation age gender survey methodology quantitative data data collection pornography information services household social science effects youth incentives health sanction samples muslim women size project projects market corruption surveys economics measures gender characteristics regression analysis head of the family justice women’s rights sex theory techniques genders evaluation training development economics households tests sampling data quality feminist survey data law estimates organizations statistical analysis community indicators marriage women research methodology standards residence female modeling weighting service districts improvement design |
| spellingShingle |
living standards methods communities rights court access to justice interviews market research science politics time research working papers woman family description income participation age gender survey methodology quantitative data data collection pornography information services household social science effects youth incentives health sanction samples muslim women size project projects market corruption surveys economics measures gender characteristics regression analysis head of the family justice women’s rights sex theory techniques genders evaluation training development economics households tests sampling data quality feminist survey data law estimates organizations statistical analysis community indicators marriage women research methodology standards residence female modeling weighting service districts improvement design Himelein, Kristen Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste |
| geographic_facet |
East Asia and Pacific Timor-Leste |
| relation |
Policy Research Working Paper;No. 7208 |
| description |
There is an inherent tension between traditional norms and survey protocols for quantitative data collected in the developing world. Unexpected interactions between the interviewer and respondent can lead to interviewer effects in the data, particularly in the case of subjective or sensitive questions. This paper makes use of a unique data set available from Timor-Leste containing subjective and objective questions to study these effects. In addition to their age and gender, data were collected from the interviewers regarding their opinions on the subjective questions prior to fieldwork. Fixed effects and mixed effects logit models are used to examine the main effects and interactions between interviewer and respondent characteristics. More objective measures serve as a pseudo control group. The paper finds interviewer effects in the both subjective and objective data, but the magnitude is considerably stronger for subjective questions. The paper also finds that female respondents are more susceptible to influence based on the interviewer's beliefs. Despite methodological shortcomings, the study highlights the need to consider more fully the impact of traditional cultural norms when conducting quantitative surveys in the developing world on topics that are outside the standard objective questions. |
| format |
Working Paper |
| author |
Himelein, Kristen |
| author_facet |
Himelein, Kristen |
| author_sort |
Himelein, Kristen |
| title |
Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste |
| title_short |
Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste |
| title_full |
Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste |
| title_fullStr |
Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste |
| title_full_unstemmed |
Interviewer Effects in Subjective Survey Questions : Evidence from Timor-Leste |
| title_sort |
interviewer effects in subjective survey questions : evidence from timor-leste |
| publisher |
World Bank Group, Washington, DC |
| publishDate |
2015 |
| url |
http://hdl.handle.net/10986/21647 |
| _version_ |
1764448869247090688 |