Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment Data
Quantile regression (QR) is a valuable tool for data analysis and multiple imputation (MI) of missing values – especially when standard parametric modelling assumptions are violated. Yet, Monte Carlo simulations that systematically evaluate QR-based MI in a variety of different practically relevant...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PsychOpen GOLD/ Leibniz Institute for Psychology
2021-09-01
|
| Series: | Methodology |
| Subjects: | |
| Online Access: | https://meth.psychopen.eu/index.php/meth/article/view/2317 |
| _version_ | 1828074578736316416 |
|---|---|
| author | Kristian Kleinke Markus Fritsch Mark Stemmler Jost Reinecke Friedrich Lösel |
| author_facet | Kristian Kleinke Markus Fritsch Mark Stemmler Jost Reinecke Friedrich Lösel |
| author_sort | Kristian Kleinke |
| collection | DOAJ |
| description | Quantile regression (QR) is a valuable tool for data analysis and multiple imputation (MI) of missing values – especially when standard parametric modelling assumptions are violated. Yet, Monte Carlo simulations that systematically evaluate QR-based MI in a variety of different practically relevant settings are still scarce. In this paper, we evaluate the method regarding the imputation of ordinal data and compare the results with other standard and robust imputation methods. We then apply QR-based MI to an empirical dataset, where we seek to identify risk factors for corporal punishment of children by their fathers. We compare the modelling results with previously published findings based on complete cases. Our Monte Carlo results highlight the advantages of QR-based MI over fully parametric imputation models: QR-based MI yields unbiased statistical inferences across large parts of the conditional distribution, when parametric modelling assumptions, such as normal and homoscedastic error terms, are violated. Regarding risk factors for corporal punishment, our MI results support previously published findings based on complete cases. Our empirical results indicate that the identified “missing at random” processes in the investigated dataset are negligible. |
| first_indexed | 2024-04-11T01:44:43Z |
| format | Article |
| id | doaj.art-9ec1fcbdade44c10871026f9d3db8dff |
| institution | Directory Open Access Journal |
| issn | 1614-2241 |
| language | English |
| last_indexed | 2024-04-11T01:44:43Z |
| publishDate | 2021-09-01 |
| publisher | PsychOpen GOLD/ Leibniz Institute for Psychology |
| record_format | Article |
| series | Methodology |
| spelling | doaj.art-9ec1fcbdade44c10871026f9d3db8dff2023-01-03T07:57:25ZengPsychOpen GOLD/ Leibniz Institute for PsychologyMethodology1614-22412021-09-0117320523010.5964/meth.2317meth.2317Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment DataKristian Kleinke0Markus Fritsch1Mark Stemmler2Jost Reinecke3Friedrich Lösel4Department of Eductation Studies and Psychology, University of Siegen, Siegen, GermanySchool of Business, Economics and Information Systems, University of Passau, Passau, GermanyInstitute of Psychology, University of Erlangen-Nurnberg, Erlangen, GermanyFaculty of Sociology, University of Bielefeld, Bielefeld, GermanyInstitute of Psychology, University of Erlangen-Nurnberg, Erlangen, GermanyQuantile regression (QR) is a valuable tool for data analysis and multiple imputation (MI) of missing values – especially when standard parametric modelling assumptions are violated. Yet, Monte Carlo simulations that systematically evaluate QR-based MI in a variety of different practically relevant settings are still scarce. In this paper, we evaluate the method regarding the imputation of ordinal data and compare the results with other standard and robust imputation methods. We then apply QR-based MI to an empirical dataset, where we seek to identify risk factors for corporal punishment of children by their fathers. We compare the modelling results with previously published findings based on complete cases. Our Monte Carlo results highlight the advantages of QR-based MI over fully parametric imputation models: QR-based MI yields unbiased statistical inferences across large parts of the conditional distribution, when parametric modelling assumptions, such as normal and homoscedastic error terms, are violated. Regarding risk factors for corporal punishment, our MI results support previously published findings based on complete cases. Our empirical results indicate that the identified “missing at random” processes in the investigated dataset are negligible.https://meth.psychopen.eu/index.php/meth/article/view/2317missing valuesmultiple imputationquantile regressionrandom forestcorporal punishmentparenting behavior |
| spellingShingle | Kristian Kleinke Markus Fritsch Mark Stemmler Jost Reinecke Friedrich Lösel Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment Data Methodology missing values multiple imputation quantile regression random forest corporal punishment parenting behavior |
| title | Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment Data |
| title_full | Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment Data |
| title_fullStr | Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment Data |
| title_full_unstemmed | Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment Data |
| title_short | Quantile Regression-Based Multiple Imputation of Missing Values — An Evaluation and Application to Corporal Punishment Data |
| title_sort | quantile regression based multiple imputation of missing values an evaluation and application to corporal punishment data |
| topic | missing values multiple imputation quantile regression random forest corporal punishment parenting behavior |
| url | https://meth.psychopen.eu/index.php/meth/article/view/2317 |
| work_keys_str_mv | AT kristiankleinke quantileregressionbasedmultipleimputationofmissingvaluesanevaluationandapplicationtocorporalpunishmentdata AT markusfritsch quantileregressionbasedmultipleimputationofmissingvaluesanevaluationandapplicationtocorporalpunishmentdata AT markstemmler quantileregressionbasedmultipleimputationofmissingvaluesanevaluationandapplicationtocorporalpunishmentdata AT jostreinecke quantileregressionbasedmultipleimputationofmissingvaluesanevaluationandapplicationtocorporalpunishmentdata AT friedrichlosel quantileregressionbasedmultipleimputationofmissingvaluesanevaluationandapplicationtocorporalpunishmentdata |