Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental Study
Panel surveys provide particularly rich data for implementing adaptive or responsive survey designs. Paradata and survey data as well as interviewer observations from all previous waves can be utilized to predict fieldwork outcomes in an ongoing wave. This manuscript contributes to the literature o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
European Survey Research Association
2023-10-01
|
| Series: | Survey Research Methods |
| Subjects: | |
| Online Access: | https://ojs.ub.uni-konstanz.de/srm/article/view/7988 |
| _version_ | 1797660685597933568 |
|---|---|
| author | Jonas Beste Corinna Frodermann Mark Trappmann Stefanie Unger |
| author_facet | Jonas Beste Corinna Frodermann Mark Trappmann Stefanie Unger |
| author_sort | Jonas Beste |
| collection | DOAJ |
| description |
Panel surveys provide particularly rich data for implementing adaptive or responsive survey designs. Paradata and survey data as well as interviewer observations from all previous waves can be utilized to predict fieldwork outcomes in an ongoing wave. This manuscript contributes to the literature on how to best make use of these data in an adaptive design framework applying machine learning algorithms. In a first step, different models were trained based on past panel waves. In a second step, we assess which model best predicts fieldwork outcomes of the following wave. Finally, we apply the superior model to predict response propensities and base case prioritizations of households at risk of attrition on these predictions. An experimental design allows us to evaluate the effect of these prioritizations on response rates and on nonresponse bias. Increasing prepaid respondent incentives from 10 to 20 euros substantially decreases attrition of low propensity cases in personal as well as telephone interviews and thereby helps reduce nonresponse bias in important target variables of the panel survey.
|
| first_indexed | 2024-03-11T18:34:29Z |
| format | Article |
| id | doaj.art-f9d934f9af1c416cb87bd4a9397a4f32 |
| institution | Directory Open Access Journal |
| issn | 1864-3361 |
| language | English |
| last_indexed | 2024-03-11T18:34:29Z |
| publishDate | 2023-10-01 |
| publisher | European Survey Research Association |
| record_format | Article |
| series | Survey Research Methods |
| spelling | doaj.art-f9d934f9af1c416cb87bd4a9397a4f322023-10-13T07:33:48ZengEuropean Survey Research AssociationSurvey Research Methods1864-33612023-10-0117310.18148/srm/2023.v17i3.7988Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental StudyJonas BesteCorinna FrodermannMark Trappmann0Stefanie UngerInstitute for Employment Research (IAB) Otto-Friedrich-Universität Bamberg Panel surveys provide particularly rich data for implementing adaptive or responsive survey designs. Paradata and survey data as well as interviewer observations from all previous waves can be utilized to predict fieldwork outcomes in an ongoing wave. This manuscript contributes to the literature on how to best make use of these data in an adaptive design framework applying machine learning algorithms. In a first step, different models were trained based on past panel waves. In a second step, we assess which model best predicts fieldwork outcomes of the following wave. Finally, we apply the superior model to predict response propensities and base case prioritizations of households at risk of attrition on these predictions. An experimental design allows us to evaluate the effect of these prioritizations on response rates and on nonresponse bias. Increasing prepaid respondent incentives from 10 to 20 euros substantially decreases attrition of low propensity cases in personal as well as telephone interviews and thereby helps reduce nonresponse bias in important target variables of the panel survey. https://ojs.ub.uni-konstanz.de/srm/article/view/7988panel surveyadaptive designcase prioritizationmachine learning |
| spellingShingle | Jonas Beste Corinna Frodermann Mark Trappmann Stefanie Unger Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental Study Survey Research Methods panel survey adaptive design case prioritization machine learning |
| title | Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental Study |
| title_full | Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental Study |
| title_fullStr | Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental Study |
| title_full_unstemmed | Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental Study |
| title_short | Case Prioritization in a Panel Survey Based on Predicting Hard to Survey Households by Machine Learning Algorithms: An Experimental Study |
| title_sort | case prioritization in a panel survey based on predicting hard to survey households by machine learning algorithms an experimental study |
| topic | panel survey adaptive design case prioritization machine learning |
| url | https://ojs.ub.uni-konstanz.de/srm/article/view/7988 |
| work_keys_str_mv | AT jonasbeste caseprioritizationinapanelsurveybasedonpredictinghardtosurveyhouseholdsbymachinelearningalgorithmsanexperimentalstudy AT corinnafrodermann caseprioritizationinapanelsurveybasedonpredictinghardtosurveyhouseholdsbymachinelearningalgorithmsanexperimentalstudy AT marktrappmann caseprioritizationinapanelsurveybasedonpredictinghardtosurveyhouseholdsbymachinelearningalgorithmsanexperimentalstudy AT stefanieunger caseprioritizationinapanelsurveybasedonpredictinghardtosurveyhouseholdsbymachinelearningalgorithmsanexperimentalstudy |