Correction to 'A Bayesian bird's eye view of 'Replications of important results in social psychology'

[This corrects the article DOI: 10.1098/rsos.160426.].

Stan: A Probabilistic Programming Language

Stan is a probabilistic programming language for specifying statistical models. A Stan program imperatively defines a log probability function over parameters conditioned on specified data and constants. As of version 2.14.0, Stan provides full Bayesian inference for continuous-variable models through Markov chain Monte Carlo methods such as the No-U-Turn sampler, an adaptive form of Hamiltonian Monte Carlo sampling. Penalized maximum likelihood estimates are calculated using optimization methods such as the limited memory Broyden-Fletcher-Goldfarb-Shanno algorithm. Stan is also a platform for computing log densities and their gradients and Hessians, which can be used in alternative algorithms such as variational Bayes, expectation propagation, and marginal inference using approximate integration. To this end, Stan is set up so that the densities, gradients, and Hessians, along with intermediate quantities of the algorithm such as acceptance probabilities, are easily accessible. Stan can be called from the command line using the cmdstan package, through R using the rstan package, and through Python using the pystan package. All three interfaces support sampling and optimization-based inference with diagnostics and posterior analysis. rstan and pystan also provide access to log probabilities, gradients, Hessians, parameter transforms, and specialized plotting.

A Bayesian bird's eye view of 'Replications of important results in social psychology'

We applied three Bayesian methods to reanalyse the preregistered contributions to the Social Psychology special issue 'Replications of Important Results in Social Psychology' (Nosek & Lakens. 2014 Registered reports: a method to increase the credibility of published results. Soc. Psychol.45, 137-141. (doi:10.1027/1864-9335/a000192)). First, individual-experiment Bayesian parameter estimation revealed that for directed effect size measures, only three out of 44 central 95% credible intervals did not overlap with zero and fell in the expected direction. For undirected effect size measures, only four out of 59 credible intervals contained values greater than [Formula: see text] (10% of variance explained) and only 19 intervals contained values larger than [Formula: see text]. Second, a Bayesian random-effects meta-analysis for all 38 t-tests showed that only one out of the 38 hierarchically estimated credible intervals did not overlap with zero and fell in the expected direction. Third, a Bayes factor hypothesis test was used to quantify the evidence for the null hypothesis against a default one-sided alternative. Only seven out of 60 Bayes factors indicated non-anecdotal support in favour of the alternative hypothesis ([Formula: see text]), whereas 51 Bayes factors indicated at least some support for the null hypothesis. We hope that future analyses of replication success will embrace a more inclusive statistical approach by adopting a wider range of complementary techniques.

Significant role for microRNA-21 affecting toll-like receptor pathway in primary graft dysfunction after human lung transplantation

BACKGROUND

MicroRNAs (miRNAs) were recently identified as modulators of immune responses after human lung transplantation (LTx). This study was undertaken to assess the contribution of miRNAs to the pathogenesis of primary graft dysfunction (PGD) after LTx.

METHODS

Of the 39 recipients, 14 (35.9%) developed Grade 3 PGD (i.e., severe PGD) within the first 72 hours of LTx. The remaining 25 recipients (64.1%) had Grade 2 or less PGD, and served as the control group. miRNAs were isolated from cells purified by bronchoalveolar lavage (BAL). Bioinformatic prediction and validation by luciferase reporter assays were performed to identify targets regulated by miR-21. Transfection of human monocytic cell line (THP-1) was conducted to determine miR-21's cellular function.

RESULTS

Pilot miRNA profiling of donor BAL samples before implantation in PGD (n = 6) revealed significant upregulation in 44 miRNAs and downregulation in 80 miRNAs compared with control (n = 6). Validation using a separate cohort demonstrated significant underexpression of miR-21 in patients with severe PGD. Furthermore, underexpression of miR-21 levels was negatively correlated with clinical PGD grades (Grade 2 PGD vs Grade 0 PGD: p = 0.042; Grade 3 PGD vs Grade 0 PGD: p = 0.004). Molecular analysis demonstrated that miR-21 targeted key components in the toll-like receptor (TLR) signaling pathway, including TLR4, IRAK3 and CXCL10. Further, incubation of THP-1 cells with cell-free BAL from severe PGD resulted in transactivation of inflammatory cytokines interleukin-1β (IL-1β) and tumor necrosis factor-α (TNF-α). In contrast, increased expression of miR-21 resulted in marked suppression of IL-1-β and TNF-α production.

CONCLUSIONS

Underexpression of miR-21 may lead to the development of severe PGD by activating key components of the TLR pathway.

B Cell-Activating Transcription Factor Plays a Critical Role in the Pathogenesis of Anti-Major Histocompatibility Complex-Induced Obliterative Airway Disease

Antibodies (Abs) against major histocompatibility complex (MHC) results in T helper-17 (Th17)-mediated immunity against lung self-antigens (SAgs), K-α1 tubulin and collagen V and obliterative airway disease (OAD). Because B cell-activating transcription factor (BATF) controls Th17 and autoimmunity, we proposed that BATF may play a critical role in OAD. Anti-H2K(b) was administered intrabronchially into Batf (-/-) and C57BL/6 mice. Histopathology of the lungs on days 30 and 45 after Ab administration to Batf (-/-) mice resulted in decreased cellular infiltration, epithelial metaplasia, fibrosis, and obstruction. There was lack of Abs to SAgs, reduction of Sag-specific interleukin (IL)-17 T cells, IL-6, IL-23, IL-17, IL-1β, fibroblast growth factor-6, and CXCL12 and decreased Janus kinase 2, signal transducer and activator of transcription 3 (STAT3), and retinoid-related orphan receptor γT. Further, micro-RNA (miR)-301a, a regulator of Th17, was reduced in Batf (-/-) mice in contrast to upregulation of miR-301a and downregulation of protein inhibitor of activated STAT3 (PIAS3) in anti-MHC-induced OAD animals. We also demonstrate an increase in miR-301a in the bronchoalveolar lavage cells from lung transplant recipients with Abs to human leukocyte antigen. This was accompanied by reduction in PIAS3 mRNA. Therefore, we conclude that BATF plays a critical role in the immune responses to SAgs and pathogenesis of anti-MHC-induced rejection. Targeting BATF should be considered for preventing chronic rejection after human lung transplantation.

Incorporating the sampling design in weighting adjustments for panel attrition

We review weighting adjustment methods for panel attrition and suggest approaches for incorporating design variables, such as strata, clusters, and baseline sample weights. Design information can typically be included in attrition analysis using multilevel models or decision tree methods such as the chi-square automatic interaction detection algorithm. We use simulation to show that these weighting approaches can effectively reduce bias in the survey estimates that would occur from omitting the effect of design factors on attrition while keeping the resulted weights stable. We provide a step-by-step illustration on creating weighting adjustments for panel attrition in the Galveston Bay Recovery Study, a survey of residents in a community following a disaster, and provide suggestions to analysts in decision-making about weighting approaches.

Correlations and Multiple Comparisons in Functional Imaging: A Statistical Perspective (Commentary on Vul et al., 2009)

Vul, Harris, Winkielman, and Pashler (2009), this issue) claim in their article that the correlations reported in fMRI studies are commonly overstated because researchers tend to report only the highest correlations or only those correlations that exceed some threshold. Their article has in a short time given rise to a spirited debate about key statistical issues at the heart of most functional neuroimaging studies. The debate provides a useful opportunity to discuss core statistical issues in neuroimaging and ultimately provides a chance for the field to grow and move forward. This commentary approaches the debate from a fundamentally statistical perspective. We begin by summarizing several of the key points under discussion, followed by our own commentary on these issues from a statistical point of view. We conclude our discussion by contemplating whether it may be time to move beyond the correlation and multiple comparisons framework that is causing so much confusion and instead represent all relevant research questions as parameters in one coherent multilevel model.

Beyond Power Calculations

Statistical power analysis provides the conventional approach to assess error rates when designing a research study. However, power analysis is flawed in that a narrow emphasis on statistical significance is placed as the primary focus of study design. In noisy, small-sample settings, statistically significant results can often be misleading. To help researchers address this problem in the context of their own studies, we recommend design calculations in which (a) the probability of an estimate being in the wrong direction ( Type S [ sign] error) and (b) the factor by which the magnitude of an effect might be overestimated ( Type M [ magnitude] error or exaggeration ratio) are estimated. We illustrate with examples from recent published research and discuss the largest challenge in a design calculation: coming up with reasonable estimates of plausible effect sizes based on external information.