Testing for the Unconfoundedness Assumption Using an Instrumental Assumption
The identification of average causal effects of a treatment in observational studies is typically based either on the unconfoundedness assumption (exogeneity of the treatment) or on the availability of an instrument. When available, instruments may also be used to test for the unconfoundedness assum...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2014-09-01
|
| Series: | Journal of Causal Inference |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/jci-2013-0011 |
| _version_ | 1831560326816989184 |
|---|---|
| author | de Luna Xavier Johansson Per |
| author_facet | de Luna Xavier Johansson Per |
| author_sort | de Luna Xavier |
| collection | DOAJ |
| description | The identification of average causal effects of a treatment in observational studies is typically based either on the unconfoundedness assumption (exogeneity of the treatment) or on the availability of an instrument. When available, instruments may also be used to test for the unconfoundedness assumption. In this paper, we present a set of assumptions on an instrumental variable which allows us to test for the unconfoundedness assumption, although they do not necessarily yield nonparametric identification of an average causal effect. We propose a test for the unconfoundedness assumption based on the instrumental assumptions introduced and give conditions under which the test has power. We perform a simulation study and apply the results to a case study where the interest lies in evaluating the effect of job practice on employment. |
| first_indexed | 2024-12-17T05:44:09Z |
| format | Article |
| id | doaj.art-df1c854d5e014b51a38b8d4998599417 |
| institution | Directory Open Access Journal |
| issn | 2193-3677 2193-3685 |
| language | English |
| last_indexed | 2024-12-17T05:44:09Z |
| publishDate | 2014-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Journal of Causal Inference |
| spelling | doaj.art-df1c854d5e014b51a38b8d49985994172022-12-21T22:01:22ZengDe GruyterJournal of Causal Inference2193-36772193-36852014-09-012218719910.1515/jci-2013-0011Testing for the Unconfoundedness Assumption Using an Instrumental Assumptionde Luna Xavier0Johansson PerDepartment of Statistics, Umeå School of Business and Economics, Umeå University, SE-90187 Umeå, SwedenThe identification of average causal effects of a treatment in observational studies is typically based either on the unconfoundedness assumption (exogeneity of the treatment) or on the availability of an instrument. When available, instruments may also be used to test for the unconfoundedness assumption. In this paper, we present a set of assumptions on an instrumental variable which allows us to test for the unconfoundedness assumption, although they do not necessarily yield nonparametric identification of an average causal effect. We propose a test for the unconfoundedness assumption based on the instrumental assumptions introduced and give conditions under which the test has power. We perform a simulation study and apply the results to a case study where the interest lies in evaluating the effect of job practice on employment.https://doi.org/10.1515/jci-2013-0011average treatment effectjob practicenonparametric identification |
| spellingShingle | de Luna Xavier Johansson Per Testing for the Unconfoundedness Assumption Using an Instrumental Assumption Journal of Causal Inference average treatment effect job practice nonparametric identification |
| title | Testing for the Unconfoundedness Assumption Using an Instrumental Assumption |
| title_full | Testing for the Unconfoundedness Assumption Using an Instrumental Assumption |
| title_fullStr | Testing for the Unconfoundedness Assumption Using an Instrumental Assumption |
| title_full_unstemmed | Testing for the Unconfoundedness Assumption Using an Instrumental Assumption |
| title_short | Testing for the Unconfoundedness Assumption Using an Instrumental Assumption |
| title_sort | testing for the unconfoundedness assumption using an instrumental assumption |
| topic | average treatment effect job practice nonparametric identification |
| url | https://doi.org/10.1515/jci-2013-0011 |
| work_keys_str_mv | AT delunaxavier testingfortheunconfoundednessassumptionusinganinstrumentalassumption AT johanssonper testingfortheunconfoundednessassumptionusinganinstrumentalassumption |