Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality
Generalized linear models are often assumed to fit propensity scores, which are used to compute inverse probability weighted (IPW) estimators. To derive the asymptotic properties of IPW estimators, the propensity score is supposed to be bounded away from zero. This condition is known in the literatu...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | JOUR |
| Materias: | |
| Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_02776715_v37_n24_p3503_Molina |
| Aporte de: |
| id |
todo:paper_02776715_v37_n24_p3503_Molina |
|---|---|
| record_format |
dspace |
| spelling |
todo:paper_02776715_v37_n24_p3503_Molina2023-10-03T15:16:13Z Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality Molina, J. Sued, M. Valdora, M. average treatment effect inverse probability weighting missing data observational studies positivity article observational study probability propensity score theoretical study Generalized linear models are often assumed to fit propensity scores, which are used to compute inverse probability weighted (IPW) estimators. To derive the asymptotic properties of IPW estimators, the propensity score is supposed to be bounded away from zero. This condition is known in the literature as strict positivity (or positivity assumption), and, in practice, when it does not hold, IPW estimators are very unstable and have a large variability. Although strict positivity is often assumed, it is not upheld when some of the covariates are unbounded. In real data sets, a data-generating process that violates the positivity assumption may lead to wrong inference because of the inaccuracy in the estimations. In this work, we attempt to conciliate between the strict positivity condition and the theory of generalized linear models by incorporating an extra parameter, which results in an explicit lower bound for the propensity score. An additional parameter is added to fulfil the overlap assumption in the causal framework. Copyright © 2018 John Wiley & Sons, Ltd. JOUR info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_02776715_v37_n24_p3503_Molina |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
average treatment effect inverse probability weighting missing data observational studies positivity article observational study probability propensity score theoretical study |
| spellingShingle |
average treatment effect inverse probability weighting missing data observational studies positivity article observational study probability propensity score theoretical study Molina, J. Sued, M. Valdora, M. Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality |
| topic_facet |
average treatment effect inverse probability weighting missing data observational studies positivity article observational study probability propensity score theoretical study |
| description |
Generalized linear models are often assumed to fit propensity scores, which are used to compute inverse probability weighted (IPW) estimators. To derive the asymptotic properties of IPW estimators, the propensity score is supposed to be bounded away from zero. This condition is known in the literature as strict positivity (or positivity assumption), and, in practice, when it does not hold, IPW estimators are very unstable and have a large variability. Although strict positivity is often assumed, it is not upheld when some of the covariates are unbounded. In real data sets, a data-generating process that violates the positivity assumption may lead to wrong inference because of the inaccuracy in the estimations. In this work, we attempt to conciliate between the strict positivity condition and the theory of generalized linear models by incorporating an extra parameter, which results in an explicit lower bound for the propensity score. An additional parameter is added to fulfil the overlap assumption in the causal framework. Copyright © 2018 John Wiley & Sons, Ltd. |
| format |
JOUR |
| author |
Molina, J. Sued, M. Valdora, M. |
| author_facet |
Molina, J. Sued, M. Valdora, M. |
| author_sort |
Molina, J. |
| title |
Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality |
| title_short |
Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality |
| title_full |
Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality |
| title_fullStr |
Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality |
| title_full_unstemmed |
Models for the propensity score that contemplate the positivity assumption and their application to missing data and causality |
| title_sort |
models for the propensity score that contemplate the positivity assumption and their application to missing data and causality |
| url |
http://hdl.handle.net/20.500.12110/paper_02776715_v37_n24_p3503_Molina |
| work_keys_str_mv |
AT molinaj modelsforthepropensityscorethatcontemplatethepositivityassumptionandtheirapplicationtomissingdataandcausality AT suedm modelsforthepropensityscorethatcontemplatethepositivityassumptionandtheirapplicationtomissingdataandcausality AT valdoram modelsforthepropensityscorethatcontemplatethepositivityassumptionandtheirapplicationtomissingdataandcausality |
| _version_ |
1807315201427505152 |