PubMed Health⌕ Search

Biomedical subjects

D B Rubin

Publications and source records attributed to D B Rubin.

At least 19 recordsLinked to original sources
PubMed2002

The ethics of consulting for the tobacco industry.

This article describes how and why I became involved in consulting for the tobacco industry. I briefly discuss the four relatively distinct statistical topics that were the primary focus of my work, all of which have been central to my published academic research for over three decades: missing data; causal inference; adjustment for covariates in observational studies; and meta-analysis. To me, it is entirely appropriate to present the application of this academic work in a legal setting.

Consultants↗
PubMed2001

Multiple imputation for multivariate data with missing and below-threshold measurements: time-series concentrations of pollutants in the Arctic.

Many chemical and environmental data sets are complicated by the existence of fully missing values or censored values known to lie below detection thresholds. For example, week-long samples of airborne particulate matter were obtained at Alert, NWT, Canada, between 1980 and 1991, where some of the concentrations of 24 particulate constituents were coarsened in the sense of being either fully missing or below detection limits. To facilitate scientific analysis, it is appealing to create complete data by filling in missing values so that standard complete-data methods can be applied. We briefly review commonly used strategies for handling missing values and focus on the multiple-imputation approach, which generally leads to valid inferences when faced with missing data. Three statistical models are developed for multiply imputing the missing values of airborne particulate matter. We expect that these models are useful for creating multiple imputations in a variety of incomplete multivariate time series data sets.

Air Pollutants↗
PubMed2001

Addressing an idiosyncrasy in estimating survival curves using double sampling in the presence of self-selected right censoring.

We investigate the use of follow-up samples of individuals to estimate survival curves from studies that are subject to right censoring from two sources: (i) early termination of the study, namely, administrative censoring, or (ii) censoring due to lost data prior to administrative censoring, so-called dropout. We assume that, for the full cohort of individuals, administrative censoring times are independent of the subjects' inherent characteristics, including survival time. To address the loss to censoring due to dropout, which we allow to be possibly selective, we consider an intensive second phase of the study where a representative sample of the originally lost subjects is subsequently followed and their data recorded. As with double-sampling designs in survey methodology, the objective is to provide data on a representative subset of the dropouts. Despite assumed full response from the follow-up sample, we show that, in general in our setting, administrative censoring times are not independent of survival times within the two subgroups, nondropouts and sampled dropouts. As a result, the stratified Kaplan-Meier estimator is not appropriate for the cohort survival curve. Moreover, using the concept of potential outcomes, as opposed to observed outcomes, and thereby explicitly formulating the problem as a missing data problem, reveals and addresses these complications. We present an estimation method based on the likelihood of an easily observed subset of the data and study its properties analytically for large samples. We evaluate our method in a realistic situation by simulating data that match published margins on survival and dropout from an actual hip-replacement study. Limitations and extensions of our design and analytic method are discussed.

Arthroplasty, Replacement, Hip↗
PubMed2000

Assessing the effect of an influenza vaccine in an encouragement design.

Many randomized experiments suffer from noncompliance. Some of these experiments, so-called encouragement designs, can be expected to have especially large amounts of noncompliance, because encouragement to take the treatment rather than the treatment itself is randomly assigned to individuals. We present an extended framework for the analysis of data from such experiments with a binary treatment, binary encouragement, and background covariates. There are two key features of this framework: we use an instrumental variables approach to link intention-to-treat effects to treatment effects and we adopt a Bayesian approach for inference and sensitivity analysis. This framework is illustrated in a medical example concerning the effects of inoculation for influenza. In this example, the analyses suggest that positive estimates of the intention-to-treat effect need not be due to the treatment itself, but rather to the encouragement to take the treatment: the intention-to-treat effect for the subpopulation who would be inoculated whether or not encouraged is estimated to be approximately as large as the intention-to-treat effect for the subpopulation whose inoculation status would agree with their (randomized) encouragement status whether or not encouraged. Thus, our methods suggest that global intention-to-treat estimates, although often regarded as conservative, can be too coarse and even misleading when taken as summarizing the evidence in the data for the effects of treatments.

Journal Article↗
PubMed2000

Non-protein thiols flux to S-nitrosothiols in endothelial cells: an LPS redox signal.

Lipopolysaccharide (LPS) injures blood vessels by activating pathways in the endothelium that lead either to cell survival and proliferation or apoptosis. It has been suggested that these outcomes are determined when reactive oxygen and nitrogen intermediates oxidize low molecular weight non-protein thiols (NPSHs) such as glutathione (GSH) and cysteine (Cys), which serve as major intracellular reducing agents. The oxidoreduction of NPSHs could be an important redox signal if it were shown to occur rapidly following injury. Towards that end, cultured bovine aortic endothelial cells were stained with the thiol fluorescent probe, monobromobimane (MBB). Most of the acid extractable MBB-reactive adducts are GSH (approximately 90%) and Cys (approximately 90%). Within 1 min of LPS exposure, 50-70% of the MBB-reactive NPSHs are consumed without evidence for concomitant net generation of superoxide, hydrogen peroxide, singlet oxygen, or glutathione disulfide (GSSG). Although LPS induces an increased rate of thiol-disulfide exchange, the slight increase does not explain the magnitude of NPSH consumption. Within the first 10 min of recovery from LPS exposure, the MBB-reactive NPSH fluorescence returns at or slightly above baseline values. When HgCl2 was added to the acid extract, one mole of S-nitrosothiol oxidizing equivalent was found for every mole of MBB-reactive NPSH consumed. It is suspected that the rapid flux of MBB-reactive NPSHs and Hg2+-inducible oxidants reflects transition of GSH to GSNO (S-nitrosoglutathione) and could be an important redox signal in endothelial cells exposed to LPS.

Animals↗
PubMed2000

Contrasts and correlations in effect-size estimation.

This article describes procedures for presenting standardized measures of effect size when contrasts are used to ask focused questions of data. The simplest contrasts consist of comparisons of two samples (e.g., based on the independent t statistic). Useful effect-size indices in this situation are members of the g family (e.g., Hedges's g and Cohen's d) and the Pearson r. We review expressions for calculating these measures and for transforming them back and forth, and describe how to adjust formulas for obtaining g or d from t, or r from g, when the sample sizes are unequal. The real-life implications of d or g calculated from t become problematic when there are more than two groups, but the correlational approach is adaptable and interpretable, although more complex than in the case of two groups. We describe a family of four conceptually related correlation indices: the alerting correlation, the contrast correlation, the effect-size correlation, and the BESD (binomial effect-size display) correlation. These last three correlations are identical in the simple setting of only two groups, but differ when there are more than two groups.

Analysis of Variance↗
PubMed2000

Causal effects in clinical and epidemiological studies via potential outcomes: concepts and analytical approaches.

A central problem in public health studies is how to make inferences about the causal effects of treatments or agents. In this article we review an approach to making such inferences via potential outcomes. In this approach, the causal effect is defined as a comparison of results from two or more alternative treatments, with only one of the results actually observed. We discuss the application of this approach to a number of data collection designs and associated problems commonly encountered in clinical research and epidemiology. Topics considered include the fundamental role of the assignment mechanism, in particular the importance of randomization as an unconfounded method of assignment; randomization-based and model-based methods of statistical inference for causal effects; methods for handling noncompliance and missing data; and methods for limiting bias in the analysis of observational data, including propensity score matching and sensitivity analysis.

Analysis of Variance↗
PubMed1999

Intermittent degradation in performance in schizophrenia.

In a series of repeated trials, schizophrenic patients often fluctuate in performance. Our data suggest that it may be useful, not just to report an increased variance relative to nonschizophrenics, but to model these fluctuations concretely as transitions between a relatively normal and an abnormal cognitive state - an intermittent degradation in performance that may be related to transient abnormalities in CNS functioning. We define 'dialipsis' as a temporary substitution of a less efficient process of task performance. This phenomenon is mentioned in the literature, but the descriptions of dialipsis are heuristic rather than based on a statistical model. We present a mixture model in which the ordinary and degraded states are described by distinct ANOVA structures, each with its own task, subject and interaction effects, with transitions between them occurring at random times. We discuss ways of detecting dialipsis and comparing the mixture model statistically with alternative models.

Analysis of Variance↗
PubMed1998

More powerful randomization-based p-values in double-blind trials with non-compliance.

Standard randomization-based tests of sharp null hypotheses in randomized clinical trials, that is, intent-to-treat analyses, are valid without extraneous assumptions, but generally can be appropriately powerful only with alternative hypotheses that involve treatment assignment having an effect on outcome. In the context of clinical trials with non-compliance, other alternative hypotheses can be more natural. In particular, when a trial is double-blind, it is often reasonable for the alternative hypothesis to exclude any effect of treatment assignment on outcome for a unit unless the assignment affected which treatment that unit actually received. Bayesian analysis under this alternative 'exclusion' hypothesis leads to new estimates of the effect of receipt of treatment, and to a new randomization-based procedure that has frequentist validity yet can be substantially more powerful than the standard intent-to-treat procedure. The key idea is to obtain a p-value using a posterior predictive check distribution, which includes a model for non-compliance behaviour, although only under the standard sharp null hypothesis of no effect of assignment (or receipt) of treatment on outcome. It is important to note that these new procedures are distinctly different from 'as treated' and 'per protocol' analyses, which are not only badly biased in general, but generally have very low power.

Data Interpretation, Statistical↗
PubMed1998

Aminothiols protect endothelial cell proliferation against inhibition by lipopolysaccharide.

Lipopolysaccharide (LPS) is a primary agent of sepsis that damages the vascular endothelium. Endothelial cell proliferation is key to the repair of damaged endothelium, and drugs that counteract the antiproliferative impact of LPS on endothelial cells should be beneficial. Because LPS exerts much of its cytotoxicity by generating reactive oxygen and nitrogen intermediates, it would be helpful to know whether therapeutic antioxidant thiols maintain cell proliferation in injured endothelium. In this study, it was found that LPS inhibited bovine aortic endothelial cell proliferation by inducing apoptosis and by decreasing DNA synthesis. Because of its benefit to irradiated endothelial cells, we then treated the cells with a radio- and chemoprotective aminothiol, WR-1065 ([N-2-mecaptoethyl]-1-3-diaminopropane, the active form of Amifostine/Ethyol). WR-1065 attenuated the inhibition of DNA synthesis caused by LPS exposure. The disulfide of WR-1065, WR-33278, was tested and shown to both promote DNA synthesis and inhibit apoptosis. The effectiveness of the disulfide suggests that the reduction of cytotoxicity does not necessarily result from the scavenging of free radicals. These findings demonstrate a novel role for aminothiols in promoting DNA synthesis and lowering apoptosis in endothelium injured with LPS.

Animals↗
PubMed1998

Aminothiol WR-1065 protects endothelial cell morphology against alterations induced by lipopolysaccharide.

In septic patients, lipopolysaccharide (LPS) damages the vascular endothelium, which manifests as tissue edema and impaired healing. This pathology occurs when LPS distorts endothelial cell morphology partly by generating free radicals. A radioprotector that scavenges free radicals, the aminothiol WR-1065 ([N-2-mercaptoethyl]-1-3-diaminopropane) was found in a prior study to normalize the morphology of irradiated endothelial cells (Mooteri SN, Podolski JL, Drab EA, et al: Radiat Res 145:217-224, 1996). The aim of this study was to determine whether WR-1065 also normalized endothelial cell morphology following exposure to LPS. For this aim, portions of bovine aortic endothelial cell cultures were denuded and exposed to LPS at 1 ng/mL. After 30 min, the apical membrane expressed increased integrin receptor to fibronectin, alpha5beta1. After 5 h, the morphology of the cells at the leading edge was distorted, and cell-cell contact was lessened. Also, filamentous actin-containing stress fibers were dissipated; however, filamentous actin content per cell was unchanged. Treatment with 2 mM WR-1065 for 2 h prior to LPS exposure attenuated the increased expression of alpha5beta1 and promoted cell-cell contact in the migrating endothelial cells. WR-1065 also promoted the retention of stress fibers and actin cytoskeletal shape in cells treated with LPS. Thus, LPS distorted endothelial cell morphology after increasing apical membrane expression of alpha5beta1 and dissipating stress fibers, effects prevented by WR-1065.

Actins↗
PubMed1997

Estimating causal effects from large data sets using propensity scores.

The aim of many analyses of large databases is to draw causal inferences about the effects of actions, treatments, or interventions. Examples include the effects of various options available to a physician for treating a particular patient, the relative efficacies of various health care providers, and the consequences of implementing a new national health care policy. A complication of using large databases to achieve such aims is that their data are almost always observational rather than experimental. That is, the data in most large data sets are not based on the results of carefully conducted randomized clinical trials, but rather represent data collected through the observation of systems as they operate in normal practice without any interventions implemented by randomized assignment rules. Such data are relatively inexpensive to obtain, however, and often do represent the spectrum of medical practice better than the settings of randomized experiments. Consequently, it is sensible to try to estimate the effects of treatments from such large data sets, even if only to help design a new randomized experiment or shed light on the generalizability of results from existing randomized experiments. However, standard methods of analysis using available statistical software (such as linear or logistic regression) can be deceptive for these objectives because they provide no warnings about their propriety. Propensity score methods are more reliable tools for addressing such objectives because the assumptions needed to make their answers appropriate are more assessable and transparent to the investigator.

Breast Neoplasms↗
PubMed1997

Modeling schizophrenic behavior using general mixture components.

This article proposes a novel and general mixture component model, the features of which include a hierarchical structure with random effects, mixture components characterized by ANOVA-like linear regressions, and mixing mechanisms governed by logistic regressions. The model was developed as a consequence of attending to long-standing psychological theory about schizophrenic behavior. Scientifically revealing results are obtained by fitting the model to a data set concerning nonschizophrenic and schizophrenic eye-tracking behavior under different conditions. Included are descriptions of the algorithms for model fitting, specifically the ECM/SECM algorithms for large sample modal inference, and the Gibbs sampler for simulating the posterior distribution. For guidance on model comparison and selection, we use posterior predictive check distributions to obtain posterior predictive p-values for likelihood ratio statistics, which do not have asymptotic chi 2 reference distributions. These posterior predictive p-values suggest that all the mixture components in our model are necessary. The final model is selected using a combination of scientific parsimony, the posterior predictive p-values, and the posterior distributions of relevant parameters.

Algorithms↗
PubMed1996

[Delayed effects of prenatal exposure to phenobarbital on intelligence--Phenemal].

Two double-blind studies were conducted on two independent samples of adult men prenatally exposed to phenobarbital and matched control samples using two different measures of general intelligence (WAIS and a draft board test (BPP)). The two studies included 33 and 81 exposed adult men respectively, and the two control groups included 52 and 101 unexposed men matched on a wide spectrum of maternal variables recorded pre- and perinatally. Based on data from control subjects, regression models were built relating intelligence scores to relevant pre-exposure matching variables. Models generated predicted scores for each exposed subject. Men exposed prenatally to phenobarbital had significantly lower verbal intelligence scores than predicted. Lower socioeconomic status and being the offspring of an unwanted pregnancy increased the magnitude of the negative effects. Exposure which includes the last trimester was the most detrimental. Physicians are urged to use increased caution in prescribing such medications during pregnancy or to premature neonates.

Adult↗
PubMed1996

Tumor angiogenesis in pheochromocytomas and paragangliomas.

BACKGROUND: Angiogenesis correlates with growth and likely metastases in several tumors. To determine whether it has a similar role in pheochromocytomas, immunohistochemical staining of factor VIII was done on the tumor tissue of 42 patients. METHODS: Formalin-fixed, paraffin-embedded tissue was obtained from 29 women and 13 men with 24 primary adrenal and 18 extraadrenal pheochromocytomas. Patients were divided into two groups. Group 1 included 32 patients with benign pheochromocytomas, and group 2 included 10 patients with malignant tumors evidenced by capsular or vascular invasion (six), liver metastases (three), or periaortic lymph node metastases (one). Blood vessels highlighted by factor VIII staining of endothelial cells with labeled streptavidin-biotin were counted under light microscopy. Mean vessel count within a 10 mm2 micrometer disk was calculated under x100, x200, and x400 magnification fields. RESULTS: There were no significant differences in patient age or clinical symptoms between the groups. The mean tumor size in group 2 of 8.8 +/- 5.3 cm was larger than the mean of 4.8 +/- 2.8 cm in group 1 (p < 0.005). The mean counts of vessels in the x100, x200, and x400 magnification fields were 102 +/- 48, 40 +/- 18, and 19 +/- 9 in group 1, and 203 +/- 77, 73 +/- 28, and 37 +/- 15 in group 2. The number of blood vessels in group 2 was significantly higher than in group 1 (p < 0.001) in each studied field. CONCLUSIONS: In this study the number of tumor blood vessels correlated with the invasive behavior of pheochromocytomas. Tumor angiogenesis may be useful in determining the likelihood of malignant behavior in pheochromocytomas.

Adolescent↗
PubMed1996

Markov chain Monte Carlo methods in biostatistics.

Appropriate models in biostatistics are often quite complicated. Such models are typically most easily fit using Bayesian methods, which can often be implemented using simulation techniques. Markov chain Monte Carlo (MCMC) methods are an important set of tools for such simulations. We give an overview and references of this rapidly emerging technology along with a relatively simple example. MCMC techniques can be viewed as extensions of iterative maximization techniques, but with random jumps rather than maximizations at each step. Special care is needed when implementing iterative maximization procedures rather than closed-form methods, and even more care is needed with iterative simulation procedures: it is substantially more difficult to monitor convergence to a distribution than to a point. The most reliable implementations of MCMC build upon results from simpler models fit using combinations of maximization algorithms and noniterative simulations, so that the user has a rough idea of the location and scale of the posterior distribution of the quantities of interest under the more complicated model. These concerns with implementation, however, should not deter the biostatistician from using MCMC methods, but rather help to ensure wise use of these powerful techniques.

Algorithms↗
PubMed1996

WR-1065 and radioprotection of vascular endothelial cells. I. Cell proliferation, DNA synthesis and damage.

Normal tissue toxicity limits radiation therapy and could depend on the extent of damage to the vascular endothelium Aminothiols such as WR-1065 [N-(2-mercaptoethyl)-1,3-diaminopropane] provide radioprotection for normal tissues, but little is known about how the aminothiols specifically affect the endothelium. Bovine aortic endothelial cells in culture were exposed to WR-1065 for 2 h before irradiation (137Cs gamma rays, 1 Gy/min). Alone, WR-1065 demonstrated an antiproliferative effect that was related to dose (0.5-4 mM) and was evident by lowered counts of adherent cells 48 h after exposure. WR-1065 was clearly radioprotective when assessed by colony formation and incorporation of [3H]thymidine. However, when the number of adherent cells was evaluated, radioprotection appeared to be slight and evident only in logarithmically growing cells. WR-1065 at 2 mM suppressed single-strand DNA breaks after 3 Gy by 22% and double-strand breaks after 9 Gy by 47%. Also in the irradiated cells, WR-1065 more than doubled the rate of progression of cells from G1 to S phase. WR-1065 pretreatment elevated cellular glutathione (GSH) content more than twofold. Although pretreatment with buthionine sulfoximine inhibited the elevation of GSH, the radioprotective impact of WR-1065 on total DNA strand breaks and colony formation was unaffected. These results suggest that WR-1065 may enable tissue recovery from irradiation by promoting the replication of endothelial cells, possibly by mechanisms independent of GSH.

Animals↗