Learn More
This paper concerns the assessment of the effects of actions or policy interventions from a combination of: (i) nonexperimental data, and (ii) substantive assumptions. The assumptions are encoded in the form of a directed acyclic graph, also called "causal graph", in which some variables are presumed to be unobserved. The paper establishes a necessary and(More)
This paper concerns the assessment of the effects of actions or policies from a combination of: (i) nonexperimental data, and (ii) causal assumptions. The assumptions are encoded in the form of a directed acyclic graph, also called “causal graph”, in which some variables are presumed to be unobserved. The paper establishes new criteria for deciding whether(More)
BACKGROUND Proteinuria is a marker of cardiovascular and renal disease in patients with chronic kidney disease (CKD), and reduction in proteinuria has been associated with improved cardiovascular and renal outcomes. While active vitamin D and its analogs have been shown to have renal protective effects in animals, these hormones have not been shown to(More)
Selection bias is caused by preferential exclusion of units from the samples and represents a major obstacle to valid causal and statistical inferences; it cannot be removed by randomized experiments and can rarely be detected in either experimental or observational studies. In this paper, we provide complete graphical and algorithmic conditions for(More)
We study the problem of learning Bayesian network structures from data. We develop an algorithm for finding the k-best Bayesian network structures. We propose to compute the posterior probabilities of hypotheses of interest by Bayesian model averaging over the k-best Bayesian networks. We present empirical results on structural discovery over several real(More)
We propose a new method of discovering causal structures, based on the detection of local, spontaneous changes in the underlying data-generating model. We derive expressions for the Bayesian score that a causal structure should obtain from streams of data produced by locally changing distributions. Simulation experiments indicate that dynamic information(More)
BACKGROUND/AIMS Secondary hyperparathyroidism is a common complication of chronic kidney disease, resulting from inactivation of vitamin D receptor signaling and phosphate retention. Selective activation of vitamin D receptors with intravenous paricalcitol significantly reduced parathyroid hormone (PTH) levels with no significant hypercalcemia or(More)
This article considers the problem of estimating the average controlled direct effect (ACDE) of a treatment on an outcome, in the presence of unmeasured confounders between an intermediate variable and the outcome. Such confounders render the direct effect unidentifiable even in cases where the total effect is unconfounded (hence identifiable). Kaufman et(More)