How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders?
Abstract Using a rich and unique combined administrative-survey dataset, this paper explores how sensitive propensity score (PS) matching estimates of Active Labor Market Policies (ALMPs) based on the selection-on-observables assumption are to typically unobserved covariates. Using a sample of Germa...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-08-01
|
| Series: | Journal for Labour Market Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12651-023-00352-9 |
| _version_ | 1827724116364361728 |
|---|---|
| author | Stefan Tübbicke |
| author_facet | Stefan Tübbicke |
| author_sort | Stefan Tübbicke |
| collection | DOAJ |
| description | Abstract Using a rich and unique combined administrative-survey dataset, this paper explores how sensitive propensity score (PS) matching estimates of Active Labor Market Policies (ALMPs) based on the selection-on-observables assumption are to typically unobserved covariates. Using a sample of German unemployed welfare recipients, the analysis shows that typically unobserved factors such job search behavior, concessions willing to make for a job as well as (mental) health are in fact relevant confounders. However, results also show that matching on the PS using only typically observed covariates reduces imbalance in terms of typically unobserved covariates by about 46 percent in this setting. In line with this finding, the inclusion of typically unobserved covariates yields very similar estimates to estimates based on a standard specification. Hence, a standard matching approach based on rich and high quality administrative data appears to be sufficient to obtain estimates that are rather robust to unobserved confounding. |
| first_indexed | 2024-03-10T22:10:29Z |
| format | Article |
| id | doaj.art-8ff8cfc6a4194ad589540971e9ed83ea |
| institution | Directory Open Access Journal |
| issn | 2510-5027 |
| language | English |
| last_indexed | 2024-03-10T22:10:29Z |
| publishDate | 2023-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal for Labour Market Research |
| spelling | doaj.art-8ff8cfc6a4194ad589540971e9ed83ea2023-11-19T12:38:39ZengSpringerOpenJournal for Labour Market Research2510-50272023-08-0157111610.1186/s12651-023-00352-9How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders?Stefan Tübbicke0Institute for Employment Research (IAB)Abstract Using a rich and unique combined administrative-survey dataset, this paper explores how sensitive propensity score (PS) matching estimates of Active Labor Market Policies (ALMPs) based on the selection-on-observables assumption are to typically unobserved covariates. Using a sample of German unemployed welfare recipients, the analysis shows that typically unobserved factors such job search behavior, concessions willing to make for a job as well as (mental) health are in fact relevant confounders. However, results also show that matching on the PS using only typically observed covariates reduces imbalance in terms of typically unobserved covariates by about 46 percent in this setting. In line with this finding, the inclusion of typically unobserved covariates yields very similar estimates to estimates based on a standard specification. Hence, a standard matching approach based on rich and high quality administrative data appears to be sufficient to obtain estimates that are rather robust to unobserved confounding.https://doi.org/10.1186/s12651-023-00352-9Propensity score matchingObservational studiesSelection biasActive labor market policyEvaluation |
| spellingShingle | Stefan Tübbicke How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders? Journal for Labour Market Research Propensity score matching Observational studies Selection bias Active labor market policy Evaluation |
| title | How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders? |
| title_full | How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders? |
| title_fullStr | How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders? |
| title_full_unstemmed | How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders? |
| title_short | How sensitive are matching estimates of active labor market policy effects to typically unobserved confounders? |
| title_sort | how sensitive are matching estimates of active labor market policy effects to typically unobserved confounders |
| topic | Propensity score matching Observational studies Selection bias Active labor market policy Evaluation |
| url | https://doi.org/10.1186/s12651-023-00352-9 |
| work_keys_str_mv | AT stefantubbicke howsensitivearematchingestimatesofactivelabormarketpolicyeffectstotypicallyunobservedconfounders |