Results 11  20
of
28
Simultaneous Sensitivity Analysis for Observational Studies Using Full Matching or Matching with Multiple Controls
"... Summary: In a matched observational study, a sensitivity analysis asks how the conclusions of the study would change if the matching had failed to adjust for an unobserved covariate with particular attributes. A ‘simultaneous’sensitivity analysis characterizes the unobserved covariate u in terms of ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
(Show Context)
Summary: In a matched observational study, a sensitivity analysis asks how the conclusions of the study would change if the matching had failed to adjust for an unobserved covariate with particular attributes. A ‘simultaneous’sensitivity analysis characterizes the unobserved covariate u in terms of two sensitivity parameters which relate u to treatment and to response. In a previous paper, we proposed a simultaneous sensitivity analysis for matched pairs. current paper extends this to matching with multiple controls and to full matching, using the technique of asymptotic separability. The An example concerns the possibility that the military caused an increase in smoking by soldiers by various programs that subsidized cigarettes. 1
ORIGINAL ARTICLE
, 2006
"... 3D segmentation of medical images using a fast multistage hybrid algorithm ..."
Abstract
 Add to MetaCart
3D segmentation of medical images using a fast multistage hybrid algorithm
Error Free Milestones in Error Prone Measurements
, 2008
"... Abstract: A predictor variable or dose that is measured with substantial error may possess an errorfree milestone, such that it is known with negligible error whether the value of the variable is to the left or right of the milestone. Such a milestone provides a basis for estimating a linear relati ..."
Abstract
 Add to MetaCart
Abstract: A predictor variable or dose that is measured with substantial error may possess an errorfree milestone, such that it is known with negligible error whether the value of the variable is to the left or right of the milestone. Such a milestone provides a basis for estimating a linear relationship between the true but unknown value of the errorfree predictor and an outcome, because the milestone creates a strong and valid instrumental variable. The inferences are nonparametric and robust, and in the simplest cases, they are exact and distribution free. We also consider multiple milestones for a single predictor and milestones for several predictors whose partial slopes are estimated simultaneously. Examples are drawn from the Wisconsin Longitudinal Study, in which a BA degree acts as a milestone for sixteen years of education, and the binary indicator of military service acts as a milestone for years of service. Key words: Attenuation; errors in measurement; full matching; instrumental variables; nonbipartite matching; questionnaire design.
Estimation of Treatment Effect of Asthma Case Management Using Propensity Score Methods
"... Objective: To estimate the treatment effect from participating in an asthma intervention that was part of the National Asthma Control Program. Study Setting: Data on children who participated in asthma case management (N=270) and eligible children who did not participate in case management (N=2,742) ..."
Abstract
 Add to MetaCart
(Show Context)
Objective: To estimate the treatment effect from participating in an asthma intervention that was part of the National Asthma Control Program. Study Setting: Data on children who participated in asthma case management (N=270) and eligible children who did not participate in case management (N=2,742) were extracted from a claims database. Study Design: We created 81 measures of health care utilization and 40 measures of neighborhood characteristics that could be related to participation in the program. The participation model was selected using the crossvalidationbased Deletion Substitution and Addition (DSA) algorithm. We used optimal full matching for the vector of Mahalanobis ’ distances and propensity scores to estimate the difference between participants and nonparticipants in the probability of a range of asthma outcomes. Principal Findings: Compared to nonparticipants, participants were more likely to have vaccinations for pulmonary illness, use controller medications, and have a refill for rescue medication. There was no statistically significant difference in the number of nebulizer treatments or ED visits between the two groups. We find that the asthma program had no significant effect on overall asthma control. Conclusion: We are not able to discern whether the lack of an effect in overall control is due to the effectiveness of the program, heterogeneity of effects or barriers outside the program’s control. We
Valid PostSelection Inference
"... In the classical theory of statistical inference, data is assumed to be generated from a known model, and the properties of the parameters in the model are of interest. In applications, however, it is often the case that the model that generates the data is unknown, and as a consequence a model is o ..."
Abstract
 Add to MetaCart
In the classical theory of statistical inference, data is assumed to be generated from a known model, and the properties of the parameters in the model are of interest. In applications, however, it is often the case that the model that generates the data is unknown, and as a consequence a model is often chosen based on the data. In my dissertation research, we study how to achieve valid inference when the model or hypotheses are datadriven. We study three scenarios, which are summarized in the three chapters. In the first chapter, we study the common practice to perform datadriven variable selection and derive statistical inference from the resulting model. We find such inference enjoys none of the guarantees that classical statistical theory provides for tests and confidence intervals when the model has been chosen a priori. We propose to produce valid "postselection inference " by reducing the problem to one of simultaneous inference. Simultaneity is required for all linear functions that arise as coefficient estimates in all submodels. By purchasing "simultaneity insurance " for all possible submodels, the resulting postselection inference is rendered universally valid under all possible model selection procedures. This inference is therefore generally conservative for particular selection procedures, but it is always more precise than full Scheffé protection. Importantly it does not depend on the truth of the selected submodel, and hence it produces valid inference
Propensity Score Matching for Causal Inference with Relational Data
"... Propensity score matching (PSM) is a widely used method for performing causal inference with observational data. PSM requires fully specifying the set of confounding variables of treatment and outcome. In the case of relational data, this set may include nonintuitive relational variables, i.e., var ..."
Abstract
 Add to MetaCart
Propensity score matching (PSM) is a widely used method for performing causal inference with observational data. PSM requires fully specifying the set of confounding variables of treatment and outcome. In the case of relational data, this set may include nonintuitive relational variables, i.e., variables derived from the relational structure of the data. In this work, we provide an automated method to derive these relational variables based on the relational structure and a set of naive confounders. This automatic construction includes two unusual classes of variables: relational degree and entity identifiers. We provide experimental evidence that demonstrates the utility of these variables in accounting for certain latent confounders. Finally, through a set of synthetic experiments, we show that our method improves the performance of PSM for causal inference with relational data. 1
© Institute of Mathematical Statistics, 2009 ERRORFREE MILESTONES IN ERROR PRONE MEASUREMENTS
"... A predictor variable or dose that is measured with substantial error may possess an errorfree milestone, such that it is known with negligible error whether the value of the variable is to the left or right of the milestone. Such a milestone provides a basis for estimating a linear relationship bet ..."
Abstract
 Add to MetaCart
A predictor variable or dose that is measured with substantial error may possess an errorfree milestone, such that it is known with negligible error whether the value of the variable is to the left or right of the milestone. Such a milestone provides a basis for estimating a linear relationship between the true but unknown value of the errorfree predictor and an outcome, because the milestone creates a strong and valid instrumental variable. The inferences are nonparametric and robust, and in the simplest cases, they are exact and distribution free. We also consider multiple milestones for a single predictor and milestones for several predictors whose partial slopes are estimated simultaneously. Examples are drawn from the Wisconsin Longitudinal Study, in which a BA degree acts as a milestone for sixteen years of education, and the binary indicator of military service acts as a milestone for years of service.
For valuable comments we thank Michael Greenstone (the editor), two anonymous reviewers, Alberto
, 2012
"... This paper presents Genetic Matching, a method of multivariate matching, that uses an evolutionary search algorithm to determine the weight each covariate is given. Both propensity score matching and matching based on Mahalanobis distance are limiting cases of this method. The algorithm makes transp ..."
Abstract
 Add to MetaCart
(Show Context)
This paper presents Genetic Matching, a method of multivariate matching, that uses an evolutionary search algorithm to determine the weight each covariate is given. Both propensity score matching and matching based on Mahalanobis distance are limiting cases of this method. The algorithm makes transparent certain issues that all matching methods must confront. We present simulation studies that show that the algorithm improves covariate balance, and that it may reduce bias if the selection on observables assumption holds. We then present a reanalysis of a number of datasets in the LaLonde (1986) controversy.