Most work in causal inference considers deterministic interventions that set each unit's treatment to some fixed value. However, under positivity violations these interventions can lead to ...nonidentification, inefficiency, and effects with little practical relevance. Further, corresponding effects in longitudinal studies are highly sensitive to the curse of dimensionality, resulting in widespread use of unrealistic parametric models. We propose a novel solution to these problems: incremental interventions that shift propensity score values rather than set treatments to fixed values. Incremental interventions have several crucial advantages. First, they avoid positivity assumptions entirely. Second, they require no parametric assumptions and yet still admit a simple characterization of longitudinal effects, independent of the number of timepoints. For example, they allow longitudinal effects to be visualized with a single curve instead of lists of coefficients. After characterizing incremental interventions and giving identifying conditions for corresponding effects, we also develop general efficiency theory, propose efficient nonparametric estimators that can attain fast convergence rates even when incorporating flexible machine learning, and propose a bootstrap-based confidence band and simultaneous test of no treatment effect. Finally, we explore finite-sample performance via simulation, and apply the methods to study time-varying sociological effects of incarceration on entry into marriage. Supplementary materials for this article are available online.
In observational studies, identification of ATEs is generally achieved by assuming that the correct set of confounders has been measured and properly included in the relevant models. Because this ...assumption is both strong and untestable, a sensitivity analysis should be performed. Common approaches include modeling the bias directly or varying the propensity scores to probe the effects of a potential unmeasured confounder. In this article, we take a novel approach whereby the sensitivity parameter is the "proportion of unmeasured confounding": the proportion of units for whom the treatment is not as good as randomized even after conditioning on the observed covariates. We consider different assumptions on the probability of a unit being unconfounded. In each case, we derive sharp bounds on the average treatment effect as a function of the sensitivity parameter and propose nonparametric estimators that allow flexible covariate adjustment. We also introduce a one-number summary of a study's robustness to the number of confounded units. Finally, we explore finite-sample properties via simulation, and apply the methods to an observational database used to assess the effects of right heart catheterization.
Supplementary materials
for this article are available online.
Continuous treatments (e.g. doses) arise often in practice, but many available causal effect estimators are limited by either requiring parametric models for the effect curve, or by not allowing ...doubly robust covariate adjustment. We develop a novel kernel smoothing approach that requires only mild smoothness assumptions on the effect curve and still allows for misspecification of either the treatment density or outcome regression. We derive asymptotic properties and give a procedure for data-driven bandwidth selection. The methods are illustrated via simulation and in a study of the effect of nurse staffing on hospital readmissions penalties.
An introduction to g methods Naimi, Ashley I; Cole, Stephen R; Kennedy, Edward H
International journal of epidemiology,
04/2017, Letnik:
46, Številka:
2
Journal Article
Recenzirano
Odprti dostop
Robins' generalized methods (g methods) provide consistent estimates of contrasts (e.g. differences, ratios) of potential outcomes under a less restrictive set of identification conditions than do ...standard regression methods (e.g. linear, logistic, Cox regression). Uptake of g methods by epidemiologists has been hampered by limitations in understanding both conceptual and technical details. We present a simple worked example that illustrates basic concepts, while minimizing technical complications.
Abstract
Unlike parametric regression, machine learning (ML) methods do not generally require precise knowledge of the true data-generating mechanisms. As such, numerous authors have advocated for ML ...methods to estimate causal effects. Unfortunately, ML algorithms can perform worse than parametric regression. We demonstrate the performance of ML-based singly and doubly robust estimators. We used 100 Monte Carlo samples with sample sizes of 200, 1,200, and 5,000 to investigate bias and confidence-interval coverage under several scenarios. In a simple confounding scenario, confounders were related to the treatment and the outcome via parametric models. In a complex confounding scenario, the simple confounders were transformed to induce complicated nonlinear relationships. In the simple scenario, when ML algorithms were used, double-robust estimators were superior to singly robust estimators. In the complex scenario, single-robust estimators with ML algorithms were at least as biased as estimators using misspecified parametric models. Doubly robust estimators were less biased, but coverage was well below nominal. The use of sample splitting, inclusion of confounder interactions, reliance on a richly specified ML algorithm, and use of doubly robust estimators was the only explored approach that yielded negligible bias and nominal coverage. Our results suggest that ML-based singly robust methods should be avoided.
Many viral RNAs are modified by methylation of the N6 position of adenosine (m6A). m6A is thought to regulate RNA splicing, stability, translation, and secondary structure. Influenza A virus (IAV) ...expresses m6A-modified RNAs, but the effects of m6A on this segmented RNA virus remain unclear. We demonstrate that global inhibition of m6A addition inhibits IAV gene expression and replication. In contrast, overexpression of the cellular m6A “reader” protein YTHDF2 increases IAV gene expression and replication. To address whether m6A residues modulate IAV RNA function in cis, we mapped m6A residues on the IAV plus (mRNA) and minus (vRNA) strands and used synonymous mutations to ablate m6A on both strands of the hemagglutinin (HA) segment. These mutations inhibited HA mRNA and protein expression while leaving other IAV mRNAs and proteins unaffected, and they also resulted in reduced IAV pathogenicity in mice. Thus, m6A residues in IAV transcripts enhance viral gene expression.
Display omitted
•m6A sites on influenza A virus (IAV) mRNAs and vRNAs were mapped•High levels of m6A modification increase IAV RNA expression•IAV mutants lacking m6A sites on the HA segment are attenuated in culture•These same IAV HA m6A mutants show reduced pathogenicity in mice
Influenza A virus (IAV) transcripts bear numerous epitranscriptomic m6A modifications. Courtney et al. map these modifications on both the IAV mRNA and vRNA strands and demonstrate that m6A increases viral RNA expression in cis. Moreover, IAV mutants lacking HA sites on the viral HA segment show reduced pathogenicity in vivo.
The RNA modification N6-methyladenosine (m6A) post-transcriptionally regulates RNA function. The cellular machinery that controls m6A includes methyltransferases and demethylases that add or remove ...this modification, as well as m6A-binding YTHDF proteins that promote the translation or degradation of m6A-modified mRNA. We demonstrate that m6A modulates infection by hepatitis C virus (HCV). Depletion of m6A methyltransferases or an m6A demethylase, respectively, increases or decreases infectious HCV particle production. During HCV infection, YTHDF proteins relocalize to lipid droplets, sites of viral assembly, and their depletion increases infectious viral particles. We further mapped m6A sites across the HCV genome and determined that inactivating m6A in one viral genomic region increases viral titer without affecting RNA replication. Additional mapping of m6A on the RNA genomes of other Flaviviridae, including dengue, Zika, yellow fever, and West Nile virus, identifies conserved regions modified by m6A. Altogether, this work identifies m6A as a conserved regulatory mark across Flaviviridae genomes.
Display omitted
•The RNA genomes of HCV, ZIKV, DENV, YFV, and WNV contain m6A modification•The cellular m6A machinery regulates HCV infectious particle production•YTHDF proteins reduce HCV particle production and localize at viral assembly sites•m6A-abrogating mutations in HCV E1 increase infectious particle production
N6-methyladenosine (m6A) post-transcriptionally regulates RNA function. Gokhale et al. demonstrate that the RNA genomes of HCV, ZIKV, DENV, YFV, and WNV are modified by m6A. Depletion of cellular machinery that regulates m6A or introduction of m6A-abrogating mutations within HCV RNA increase viral particle production, suggesting that m6A negatively regulates HCV.
Estimators based on influence functions (IFs) have been shown to be effective in many settings, especially when combined with machine learning techniques. By focusing on estimating a specific target ...of interest (e.g., the average effect of a treatment), rather than on estimating the full underlying data generating distribution, IF-based estimators are often able to achieve asymptotically optimal mean-squared error. Still, many researchers find IF-based estimators to be opaque or overly technical, which makes their use less prevalent and their benefits less available. To help foster understanding and trust in IF-based estimators, we present tangible, visual illustrations of when and how IF-based estimators can outperform standard "plug-in" estimators. The figures we show are based on connections between IFs, gradients, linear approximations, and Newton-Raphson.
Summary
Instrumental variable (IV) methods allow us the opportunity to address unmeasured confounding in causal inference. However, most IV methods are only applicable to discrete or continuous ...outcomes with very few IV methods for censored survival outcomes. In this article, we propose nonparametric estimators for the local average treatment effect on survival probabilities under both covariate-dependent and outcome-dependent censoring. We provide an efficient influence function-based estimator and a simple estimation procedure when the IV is either binary or continuous. The proposed estimators possess double-robustness properties and can easily incorporate nonparametric estimation using machine learning tools. In simulation studies, we demonstrate the flexibility and double robustness of our proposed estimators under various plausible scenarios. We apply our method to the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial for estimating the causal effect of screening on survival probabilities and investigate the causal contrasts between the two interventions under different censoring assumptions.