When estimating causal effects, unmeasured confounding and model misspecification are both potential sources of bias. We propose a method to simultaneously address both issues in the form of a semi-parametric sensitivity analysis. In particular, our approach incorporates Bayesian Additive Regression Trees into a two-parameter sensitivity analysis strategy that assesses sensitivity of posterior distributions of treatment effects to choices of sensitivity parameters. This results in an easily interpretable framework for testing for the impact of an unmeasured confounder that also limits the number of modeling assumptions. We evaluate our approach in a large-scale simulation setting and with high blood pressure data taken from the Third National Health and Nutrition Examination Survey. The model is implemented as open-source software, integrated into the treatSens package for the R statistical programming language. © 2016 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.

Iterative imputation, in which variables are imputed one at a time conditional on all the others, is a popular technique that can be convenient and flexible, as it replaces a potentially difficult multivariate modelling problem with relatively simple univariate regressions. In this paper, we begin to characterize the stationary distributions of iterative imputations and their statistical properties, accounting for the conditional models being iteratively estimated from data rather than being prespecified. When the families of conditional models are compatible, we provide sufficient conditions under which the imputation distribution converges in total variation to the posterior distribution of a Bayesian model. When the conditional models are incompatible but valid, we show that the combined imputation estimator is consistent.

We consider the relative performance of two common approaches to multiple imputation (MI): joint multivariate normal (MVN) MI, in which the data are modeled as a sample from a joint MVN distribution; and conditional MI, in which each variable is modeled conditionally on all the others. In order to use the multivariate normal distribution, implementations of joint MVN MI typically assume that categories of discrete variables are probabilistically constructed from continuous values. We use simulations to examine the implications of these assumptions. For each approach, we assess (1) the accuracy of the imputed values; and (2) the accuracy of coefficients and fitted values from a model fit to completed data sets. These simulations consider continuous, binary, ordinal, and unordered-categorical variables. One set of simulations uses multivariate normal data, and one set uses data from the 2008 American National Election Studies. We implement a less restrictive approach than is typical when evaluating methods using simulations in the missing data literature: in each case, missing values are generated by carefully following the conditions necessary for missingness to be “missing at random” (MAR). We find that in these situations conditional MI is more accurate than joint MVN MI whenever the data include categorical variables.

In the analysis of causal effects in non-experimental studies, conditioning on observable covariates is one way to try to reduce unobserved confounder bias. However, a developing literature has shown that conditioning on certain covariates may increase bias, and the mechanisms underlying this phenomenon have not been fully explored. We add to the literature on bias-increasing covariates by first introducing a way to decompose omitted variable bias into three constituent parts: bias due to an unobserved confounder, bias due toexcludingobserved covariates, and bias due to amplification. This leads to two important findings. Although instruments have been the primary focus of the bias amplification literature to date, we identify the fact that the popular approach of adding group fixed effects can lead to bias amplification as well. This is an important finding because many practitioners think that fixed effects are a convenient way to account for any and all group-level confounding and are at worst harmless. The second finding introduces the concept of biasunmaskingand shows how it can be even more insidious than bias amplification in some cases. After introducing these new results analytically, we use constructed observational placebo studies to illustrate bias amplification and bias unmasking with real data. Finally, we propose a way to add bias decomposition information to graphical displays for sensitivity analysis to help practitioners think through the potential for bias amplification and bias unmasking in actual applications.

In studies of discrimination, researchers often seek to estimate a causal effect of race or gender on outcomes. For example, in the criminal justice context, one might ask whether arrested individuals would have been subsequently charged or convicted had they been a different race. It has long been known that such counterfactual questions face measurement challenges related to omitted-variable bias, and conceptual challenges related to the definition of causal estimands for largely immutable characteristics. Another concern, which has been the subject of recent debates, is post-treatment bias: many studies of discrimination condition on apparently intermediate outcomes, like being arrested, that themselves may be the product of discrimination, potentially corrupting statistical estimates. There is, however, reason to be optimistic. By carefully defining the estimand—and by considering the precise timing of events—we show that a primary causal quantity of interest in discrimination studies can be estimated under an ignorability condition that may hold approximately in some observational settings. We illustrate these ideas by analyzing both simulated data and the charging decisions of a prosecutor’s office in a large county in the United States.

Purpose: Research comparing different biofeedback types could lead to individualized treatments for those with residual speech errors. This study examines within-treatment response to ultrasound and visual-acoustic biofeedback, as well as generalization to untrained words, for errors affecting the American English rhotic /ɹ/. We investigated whether some children demonstrated greater improvement in /ɹ/ during ultrasound or visual-acoustic biofeedback. Each participant received both biofeedback types. Individual predictors of treatment response (i.e., age, auditory-perceptual skill, oral somatosensory skill, and growth mindset) were also explored. Method: Seven children ages 9–16 years with residual rhotic errors participated in 10 treatment visits. Each visit consisted of two conditions: 45 min of ultrasound biofeedback and 45 min of visual-acoustic biofeedback. The order of biofeedback conditions was randomized within a single-case experimental design. Acquisition of /ɹ/ was evaluated through acoustic measurements (normalized F3–F2 difference) of selected nonbiofeedback productions during practice. Generalization of /ɹ/ was evaluated through acoustic measurements and perceptual ratings of pretreatment/posttreatment probes. Results: Five participants demonstrated acquisition of practiced words during the combined treatment package. Three participants demonstrated a clinically significant degree of generalization to untreated words on posttreatment probes. Randomization tests indicated one participant demonstrated a significant advantage for visual-acoustic over ultrasound biofeedback. Participants' auditory-perceptual acuity on an /ɹ/−/w/ identification task was identified as a possible correlate of generalization following treatment. Conclusions: Most participants did not demonstrate a statistically significant difference in acoustic productions between the ultrasound and visual-acoustic conditions, but one participant showed greater improvement in /ɹ/ during visual-acoustic biofeedback. Supplemental Material: https://doi.org/10.23641/asha.14881101