Narrow search
Showing 1 - 9 of 9
Cover Image
Non-parametric inference for the effect of a treatment on survival times with application in the health and social sciences
Luna, Xavier de; Johansson, Per - 2009
control group which are made comparable through matching on observed covariates. The inference is performed by conditioning on …
Persistent link: https://www.econbiz.de/10010269367
Cover Image
Dynamic Treatment Assignment : The Consequences for Evaluations Using Observational Data
Fredriksson, Peter; Johansson, Per - 2004
This paper discusses the evaluation problem using observational data when the timing of treatment is an outcome of a … suggest easy-to-use nonparametric survival function matching estimators. These estimators can be used to estimate the time …
Persistent link: https://www.econbiz.de/10010261825
Cover Image
Non-Parametric Inference for the Effect of a Treatment on Survival Times with Application in the Health and Social Sciences
de Luna, Xavier; Johansson, Per - Institute for the Study of Labor (IZA) - 2009
control group which are made comparable through matching on observed covariates. The inference is performed by conditioning on …
Persistent link: https://www.econbiz.de/10005233824
Cover Image
On Nonparametric Identification of Treatment Effects in Duration Models
Johansson, Per; Lee, Myoung-jae - 2016
We show that the main nonparametric identification finding of Abbring and Van den Berg (2003b, Econometrica) for the effect of a timing-chosen treatment on an event duration of interest does not hold. The main problem is that the identification is based on the competing-risks identification...
Persistent link: https://www.econbiz.de/10011559675
Cover Image
Bootstrap inference for K-nearest neighbour matching estimators
de Luna, Xavier; Johansson, Per; Sjöstedt-de Luna, Sara - 2010
-nearest neighbour (KNN) matching estimators of average causal effects. This is an interesting result showing that bootstrap should not … valid inference for KNN matching estimators. We resample estimated individual causal effects (EICE), i.e. the difference in … the matching covariate, we obtain a bootstrap scheme valid also with heterogeneous causal effects where mild assumptions …
Persistent link: https://www.econbiz.de/10010278782
Cover Image
Proxy Variables and Nonparametric Identification of Causal Effects
de Luna, Xavier; Fowler, Philip; Johansson, Per - 2016
Proxy variables are often used in linear regression models with the aim of removing potential confounding bias. In this paper we formalise proxy variables within the potential outcome framework, giving conditions under which it can be shown that causal effects are nonparametrically identified....
Persistent link: https://www.econbiz.de/10011524988
Cover Image
Dynamic Treatment Assignment - The Consequences for Evaluations Using Observational Data
Fredriksson, Peter; Johansson, Per - Institute for the Study of Labor (IZA) - 2004
This paper discusses the evaluation problem using observational data when the timing of treatment is an outcome of a … suggest easy-to-use nonparametric survival function matching estimators. These estimators can be used to estimate the time …
Persistent link: https://www.econbiz.de/10005822709
Cover Image
Bootstrap Inference for K-Nearest Neighbour Matching Estimators
de Luna, Xavier; Johansson, Per; Sjöstedt-de Luna, Sara - Institute for the Study of Labor (IZA) - 2010
-nearest neighbour (KNN) matching estimators of average causal effects. This is an interesting result showing that bootstrap should not … valid inference for KNN matching estimators. We resample "estimated individual causal effects" (EICE), i.e. the difference … respect to the matching covariate, we obtain a bootstrap scheme valid also with heterogeneous causal effects where mild …
Persistent link: https://www.econbiz.de/10008765225
Cover Image
Testing for nonparametric identification of causal effects in the presence of a quasi-instrument
DeLuna, Xavier; Johansson, Per - 2012
The identification of average causal effects of a treatment in observational studies is typically based either on the unconfoundedness assumption or on the availability of an instrument. When available, instruments may also be used to test for the unconfoundedness assumption (exogeneity of the...
Persistent link: https://www.econbiz.de/10010284025