A Generalization of Sampling Without Replacement From a Finite Universe

Horvitz, Daniel G.; Thompson, Donovan J.

doi:10.2307/2280784

Cited by 1,318 publications

(902 citation statements)

References 8 publications

Supporting

Mentioning

887

Contrasting

Unclassified

Order By: Relevance

“…Multivariate models were expansion weighted for the racestratified sampling design (non-proportional sampling fractions) and weighted for survey non-response using the HorvitzThompson approach. 27 Multiple imputation with 20 imputations was used for missing covariates, and an alpha level of 0.05 was set as the threshold for statistical significance. As sensitivity analyses, all models were repeated after excluding patients prescribed bupropion or duloxetine, both of which have Food and Drug Administration (FDA)-approved non-psychiatric indications, who lacked a chart diagnosis of a depressive or anxiety disorder within 1 year of the index prescription.…”

Section: Resultsmentioning

confidence: 99%

Associations Between Antidepressant Adherence and Shared Decision-Making, Patient–Provider Trust, and Communication Among Adults with Diabetes: Diabetes Study of Northern California (DISTANCE)

et al. 2014

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Associations Between Antidepressant Adherence and Shared Decision-Making, Patient–Provider Trust, and Communication Among Adults with Diabetes: Diabetes Study of Northern California (DISTANCE)

et al. 2014

View full text Add to dashboard Cite

“…We use equation (A1) in Theorem A2 provided in the Appendix to obtain the variance estimator for the estimatorβ. For comparison we also include the inverse probability weighted estimatorβ IPW of Binder (1992) and Lin (2000); see also Horvitz & Thompson (1952) and Qi et al (2005). For the definition of the inverse probability weighted estimator, see equation (13) in § 4·3.…”

Section: Applications 4·1 Length-biased Datamentioning

confidence: 99%

Pseudo-partial likelihood for proportional hazards models with biased-sampling data

Tsai¹

2009

Biometrika

View full text Add to dashboard Cite

SUMMARYWe obtain a pseudo-partial likelihood for proportional hazards models with biased-sampling data by embedding the biased-sampling data into left-truncated data. The log pseudo-partial likelihood of the biased-sampling data is the expectation of the log partial likelihood of the left-truncated data conditioned on the observed data. Asymptotic properties of the estimator that maximize the pseudo-partial likelihood are derived. Applications to length-biased data, biased samples with right censoring and proportional hazards models with missing covariates are discussed.

show abstract

“…Clinicians may want to estimate the average e ect of: (1) assigning all patients to treatment t versus treatment k; (2) treatment t versus treatment k for those assigned to treatment t; or (3) treatment t versus any other treatment, t, for those assigned to t. To answer the ÿrst question, we must assume that all patients can potentially be assigned to each treatment, and be willing to estimate potential outcomes under all treatments for each patient. Imbens [2] presents a weighted estimator similar to Horvitz-Thompson estimator [14] to answer the ÿrst question. The second question can be answered by comparing only the data from treatments t and k. This approach drastically reduces the sample size and does not make use of all the potential information.…”

Section: Causal Inference With Multi-valued Treatmentsmentioning

confidence: 99%

On the use of discrete choice models for causal inference

Tchernis¹,

Horvitz-Lennon²,

Normand³

2005

Statist. Med.

View full text Add to dashboard Cite

SUMMARYMethodology for causal inference based on propensity scores has been developed and popularized in the last two decades. However, the majority of the methodology has concentrated on binary treatments. Only recently have these methods been extended to settings with multi-valued treatments. We propose a number of discrete choice models for estimating the propensity scores. The models di er in terms of exibility with respect to potential correlation between treatments, and, in turn, the accuracy of the estimated propensity scores. We present the e ects of discrete choice models used on performance of the causal estimators through a Monte Carlo study. We also illustrate the use of discrete choice models to estimate the e ect of antipsychotic drug use on the risk of diabetes in a cohort of adults with schizophrenia.

show abstract

A Generalization of Sampling Without Replacement From a Finite Universe

Cited by 1,318 publications

References 8 publications

Associations Between Antidepressant Adherence and Shared Decision-Making, Patient–Provider Trust, and Communication Among Adults with Diabetes: Diabetes Study of Northern California (DISTANCE)

Associations Between Antidepressant Adherence and Shared Decision-Making, Patient–Provider Trust, and Communication Among Adults with Diabetes: Diabetes Study of Northern California (DISTANCE)

Pseudo-partial likelihood for proportional hazards models with biased-sampling data

On the use of discrete choice models for causal inference

Contact Info

Product

Resources

About