Correct Coverage Research Articles

Deciding What's True: The Rise of Political Fact-Checking in American Journalism

In a journalistic moment like ours, that is, rife with conspiracy theories, one-sided political coverage, and outright fake news—that is, real fake news, not the honest reporting that Donald Trump clumsily tries to dismiss as “fake news”—it may surprise some people to realize that the best, most professional mainstream media outlets are more committed than ever to telling the truth. In recent decades, those outlets have suffered attack from all sides: from the right for allegedly harboring a liberal bias; from the left for “he said, she said” stories that let falsehood share the stage with truth; and from high-minded critics of all types for dwelling on political strategy and image more than policy substance. In response, these organizations have developed and strengthened practices to ensure correct and informative coverage. Thus as the perils of superficiality and errancy have grown, so too have the strictures designed to safeguard accuracy. One of the most visible of these new practices is fact-checking—not the kind famously performed by sharp-penciled New Yorker staffers (“internal” fact-checking) but the kind made famous by FactCheck.org, PolitiFact, and the Washington Post's Fact Checker. Born during the presidency of George W. Bush, these entities, along with sporadic features in other news outlets, scrutinize the claims of public officials to judge their veracity. For audiences lost in today's vast, disorienting Medialand, these features provide a needed compass—thoughtful, well-reported accounts of where dubious-sounding factoids came from, how much truth or falsehood they contain, and the context necessary to assess them beyond the Pinocchio noses or rating on the Truth-o-Meter. In Deciding What's True: The Rise of Political Fact-Checking in American Journalism, Lucas Graves, an assistant professor of journalism and mass communication at the University of Wisconsin, provides a first-rate history and sociology of these new watchdogs, helping to make sense of their role in the contemporary media ecosystem. Well-researched, carefully argued, and lucidly written, Deciding What's True does an excellent job of sorting out the messy questions of truth and falsehood, fact and opinion, in contemporary politics and journalism.

Gaussian approximation for high dimensional time series

We consider the problem of approximating sums of high dimensional stationary time series by Gaussian vectors, using the framework of functional dependence measure. The validity of the Gaussian approximation depends on the sample size $n$, the dimension $p$, the moment condition and the dependence of the underlying processes. We also consider an estimator for long-run covariance matrices and study its convergence properties. Our results allow constructing simultaneous confidence intervals for mean vectors of high-dimensional time series with asymptotically correct coverage probabilities. As an application, we propose a Kolmogorov–Smirnov-type statistic for testing distributions of high-dimensional time series.

North Atlantic observations sharpen meridional overturning projections

Atlantic Meridional Overturning Circulation (AMOC) projections are uncertain due to both model errors, as well as internal climate variability. An AMOC slowdown projected by many climate models is likely to have considerable effects on many aspects of global and North Atlantic climate. Previous studies to make probabilistic AMOC projections have broken new ground. However, they do not drift-correct or cross-validate the projections, and do not fully account for internal variability. Furthermore, they consider a limited subset of models, and ignore the skill of models at representing the temporal North Atlantic dynamics. We improve on previous work by applying Bayesian Model Averaging to weight 13 Coupled Model Intercomparison Project phase 5 models by their skill at modeling the AMOC strength, and its temporal dynamics, as approximated by the northern North-Atlantic temperature-based AMOC Index. We make drift-corrected projections accounting for structural model errors, and for the internal variability. Cross-validation experiments give approximately correct empirical coverage probabilities, which validates our method. Our results present more evidence that AMOC likely already started slowing down. While weighting considerably moderates and sharpens our projections, our results are at low end of previously published estimates. We project mean AMOC changes between periods 1960–1999 and 2060–2099 of −4.0 Sv and −6.8 Sv for RCP4.5 and RCP8.5 emissions scenarios respectively. The corresponding average 90% credible intervals for our weighted experiments are [−7.2, −1.2] and [−10.5, −3.7] Sv respectively for the two scenarios.

A Simple Adjustment for Bandwidth Snooping

Kernel-based estimators such as local polynomial estimators in regression discontinuity designs are often evaluated at multiple bandwidths as a form of sensitivity analysis. However, if in the reported results, a researcher selects the bandwidth based on this analysis, the associated confidence intervals (CIs) may not have correct coverage, even if the estimator is unbiased. This article proposes a simple adjustment that gives correct coverage in such situations: replace the normal quantile with a critical value that depends only on the kernel and ratio of the maximum and minimum bandwidths the researcher has entertained. We tabulate these critical values and quantify the loss in coverage for conventional CIs. For a range of relevant cases, a conventional 95% CI has coverage between 70% and 90%, and our adjustment amounts to replacing the conventional critical value 1.96 with a number between 2.2 and 2.8. Our results also apply to other settings involving trimmed data, such as trimming to ensure overlap in treatment effect estimation. We illustrate our approach with three empirical applications.

Proper joint analysis of summary association statistics requires the adjustment of heterogeneity in SNP coverage pattern.

As meta-analysis results published by consortia of genome-wide association studies (GWASs) become increasingly available, many association summary statistics-based multi-locus tests have been developed to jointly evaluate multiple single-nucleotide polymorphisms (SNPs) to reveal novel genetic architectures of various complex traits. The validity of these approaches relies on the accurate estimate of z-score correlations at considered SNPs, which in turn requires knowledge on the set of SNPs assessed by each study participating in the meta-analysis. However, this exact SNP coverage information is usually unavailable from the meta-analysis results published by GWAS consortia. In the absence of the coverage information, researchers typically estimate the z-score correlations by making oversimplified coverage assumptions. We show through real studies that such a practice can generate highly inflated type I errors, and we demonstrate the proper way to incorporate correct coverage information into multi-locus analyses. We advocate that consortia should make SNP coverage information available when posting their meta-analysis results, and that investigators who develop analytic tools for joint analyses based on summary data should pay attention to the variation in SNP coverage and adjust for it appropriately.

A Bayesian posterior predictive framework for weighting ensemble regional climate models

Abstract. We present a novel Bayesian statistical approach to computing model weights in climate change projection ensembles in order to create probabilistic projections. The weight of each climate model is obtained by weighting the current day observed data under the posterior distribution admitted under competing climate models. We use a linear model to describe the model output and observations. The approach accounts for uncertainty in model bias, trend and internal variability, including error in the observations used. Our framework is general, requires very little problem-specific input, and works well with default priors. We carry out cross-validation checks that confirm that the method produces the correct coverage.

CARACTERÍSTICAS DOS PROCESSOS PRODUTIVOS DE REFEIÇÕES NA IMPLANTAÇÃO DO NutriSus EM MUNICÍPIOS DO RIO GRANDE DO NORTE

This is a descriptive, cross-sectional survey which aims to evaluate the characteristics of the productive processes of meals in the implementation of NutriSus in four municipalities of Rio Grande do Norte. For the data collection, interviews and visits were carried out to the daycare centers and to the Technical Manager of each participating municipality, to make the observation and the approach of questions to evaluate how NutriSus was implemented, as well as the recordings of the interviews and transcription of the obtained audios. These data made possible the knowledge about the strategies used in each city for the implementation of the Program, in order to know if it was necessary to carry out new menu planning, implementation or adjustments in some preparations, besides verifying how is the acceptability. To achieve the expected result of the Program, it is necessary to follow the recommended administration schedule: two months of supplementation with a three or four-month interval. In the visited municipalities, it was identified that the implementation of the strategy occurred only as a pilot project, happening in some months of 2014 or 2015, not completing the cycle, without progression in 2016 and with a limited number of children. This discontinuity was due to the insufficient number of sachets sent to the municipalities by the Ministerio da Saude (Ministry of Health). It is concluded that nationalized programs that involve the three governmental spheres in their moment of implementation, such as Nutrisus, require a consistent planning, with the participation of the involved actors, which encompasses the factors necessary for its correct execution and full coverage of the target population. DOI: 10.12957/demetra.2017.25374

Biological variation: Evaluation of methods for constructing confidence intervals for estimates of within-person biological variation for different distributions of the within-person effect

BackgroundPrecise estimates of the within-person biological variation, CVI, can be essential both for monitoring patients and for setting analytical performance specifications. The confidence interval, CI, may be used to evaluate the reliability of an estimate, as it is a good measure of the uncertainty of the estimated CVI. The aim of the present study is to evaluate and establish methods for constructing a CI with the correct coverage probability and non-cover probability when estimating CVI. MethodData based on 3 models for distributions for the within-person effect were simulated to assess the performance of 3 methods for constructing confidence intervals; the formula based method for the nested ANOVA, the percentile bootstrap and the bootstrap-t methods. ResultsThe performance of the evaluated methods for constructing a CI varied, both dependent on the size of the CVI and the type of distributions. The bootstrap-t CI have good and stable performance for the models evaluated, while the formula based are more distribution dependent. The percentile bootstrap performs poorly. ConclusionCI is an essential part of estimation of the within-person biological variation. Good coverage probability and non-cover probabilities for CI are achievable by using the bootstrap-t combined with CV-ANOVA. Supplemental R-code is provided online.

A note on multiple imputation under complex sampling

SUMMARY Multiple imputation is popular for handling item nonresponse in survey sampling. Current multiple imputation techniques with complex survey data assume that the sampling design is ignorable. In this paper, we propose a new multiple imputation procedure for parametric inference without this assumption. Instead of using the sample-data likelihood, we use the sampling distribution of the pseudo maximum likelihood estimator to derive the posterior distribution of the parameters. The asymptotic properties of the proposed method are investigated. A simulation study confirms that the new procedure provides unbiased point estimation and valid confidence intervals with correct coverage properties whether or not the sampling design is ignorable.

Nonparametric Inference for Time-Varying Coefficient Quantile Regression

The article considers nonparametric inference for quantile regression models with time-varying coefficients. The errors and covariates of the regression are assumed to belong to a general class of locally stationary processes and are allowed to be cross-dependent. Simultaneous confidence tubes (SCTs) and integrated squared difference tests (ISDTs) are proposed for simultaneous nonparametric inference of the latter models with asymptotically correct coverage probabilities and Type I error rates. Our methodologies are shown to possess certain asymptotically optimal properties. Furthermore, we propose an information criterion that performs consistent model selection for nonparametric quantile regression models of nonstationary time series. For implementation, a wild bootstrap procedure is proposed, which is shown to be robust to the dependent and nonstationary data structure. Our method is applied to studying the asymmetric and time-varying dynamic structures of the U.S. unemployment rate since the 1940s. Supplementary materials for this article are available online.

A Simple Adjustment for Bandwidth Snooping

Kernel-based estimators are often evaluated at multiple bandwidths as a form of sensitivity analysis. However, if in the reported results, a researcher selects the bandwidth based on this analysis, the associated confidence intervals may not have correct coverage, even if the estimator is unbiased. This paper proposes a simple adjustment that gives correct coverage in such situations: replace the Normal quantile with a critical value that depends only on the kernel and ratio of the maximum and minimum bandwidths the researcher has entertained. We tabulate these critical values and quantify the loss in coverage for conventional confidence intervals. For a range of relevant cases, a conventional 95% confidence interval has coverage between 70% and 90%, and our adjustment amounts to replacing the conventional critical value 1.96 with a number between 2.2 and 2.8. A Monte Carlo study confirms that our approach gives accurate coverage in finite samples. We illustrate our approach with two empirical applications.

Multivariate Stochastic Volatility-Double Jump Model: An Application for Oil Assets

We propose a new multivariate model to capture the presence of jumps in mean and conditional variance in the returns of oil prices and companies in this sector. The model is based on the presence of common factors associated with jumps in mean and variance, as it performs a decomposition of the conditional variance of each asset as the sum of the common factor plus a specific transitory factor in a multivariate stochastic volatility structure. The estimation is made through Bayesian methods using Markov Chain Monte Carlo. The model allows recovering the changes in prices and volatility patterns observed in this sector, relating the jumps with the events observed in the period 2000-2015. We apply the model to estimate risk management measures, hedging and portfolio allocation and performing a comparison with other multivariate models of conditional volatility. Based on the results, we may conclude that the proposed model has a better performance when used to calculate portfolio VaR, since it does not reject the hypothesis of correct nominal coverage with certain specifications presented in this work. Furthermore, we conclude that the model can be used to hedge oil price risks, through the optimal hedge ratio for a portfolio containing an oil company as-set (stock) and the oil price contract. When compared to the standard methodology based on GARCH models, our model performs well in this application.

Finite-Sample Optimal Estimation and Inference on Average Treatment Effects Under Unconfoundedness

We consider estimation and inference on average treatment effects under unconfoundedness conditional on the realizations of the treatment variable and covariates. We derive finite-sample optimal estimators and confidence intervals (CIs) under the assumption of normal errors when the conditional mean of the outcome variable is constrained only by nonparametric smoothness and/or shape restrictions. When the conditional mean is restricted to be Lipschitz with a large enough bound on the Lipschitz constant, we show that the optimal estimator reduces to a matching estimator with the number of matches set to one. In contrast to conventional CIs, our CIs use a larger critical value that explicitly takes into account the potential bias of the estimator. It is needed for correct coverage in finite samples and, in certain cases, asymptotically. We give conditions under which root-n inference is impossible, and we provide versions of our CIs that are feasible and asymptotically valid with unknown error distribution, including in this non-regular case. We apply our results in a numerical illustration and in an application to the National Supported Work Demonstration.

Flexible Correlation Structure for Accurate Prediction and Uncertainty Quantification in Bayesian Gaussian Process Emulation of a Computer Model

Gaussian processes are widely used in the analysis of data from a computer model. Ideally, the analysis will yield accurate predictions with correct coverage probabilities of credible intervals. In this paper, we first review several existing Bayesian implementations in the literature. We show that Bayesian approaches with squared-exponential correlation structure do not always quantify well the uncertainty in prediction. Thus, we propose new Bayesian approaches with power-exponential or Matern correlation structure, which have more flexibility. Through application examples and a simulation study, we show that the proposed Bayesian methods not only have superior prediction accuracy but are closer to having the correct coverage probability.

A new confidence interval in errors-in-variables model with known error variance

ABSTRACTThis paper considers constructing a new confidence interval for the slope parameter in the structural errors-in-variables model with known error variance associated with the regressors. Existing confidence intervals are so severely affected by Gleser–Hwang effect that they are subject to have poor empirical coverage probabilities and unsatisfactory lengths. Moreover, these problems get worse with decreasing reliability ratio which also result in more frequent absence of some existing intervals. To ease these issues, this paper presents a fiducial generalized confidence interval which maintains the correct asymptotic coverage. Simulation results show that this fiducial interval is slightly conservative while often having average length comparable or shorter than the other methods. Finally, we illustrate these confidence intervals with two real data examples, and in the second example some existing intervals do not exist.

A new confidence interval in measurement error model with the reliability ratio known

ABSTRACTFor the slope parameter of the measurement error model with the reliability ratio known, this article constructs a fiducial generalized confidence interval (FGCI) which is proved to have correct asymptotic coverage. Simulation results demonstrate that the FGCI often outperforms the existing intervals in terms of empirical coverage probability, average interval length, and false parameter coverage rate. Two examples are also provided to illustrate our approach.

Confidence intervals for the between-study variance in random-effects meta-analysis using generalised heterogeneity statistics: should we use unequal tails?

BackgroundConfidence intervals for the between study variance are useful in random-effects meta-analyses because they quantify the uncertainty in the corresponding point estimates. Methods for calculating these confidence intervals have been developed that are based on inverting hypothesis tests using generalised heterogeneity statistics. Whilst, under the random effects model, these new methods furnish confidence intervals with the correct coverage, the resulting intervals are usually very wide, making them uninformative.MethodsWe discuss a simple strategy for obtaining 95 % confidence intervals for the between-study variance with a markedly reduced width, whilst retaining the nominal coverage probability. Specifically, we consider the possibility of using methods based on generalised heterogeneity statistics with unequal tail probabilities, where the tail probability used to compute the upper bound is greater than 2.5 %. This idea is assessed using four real examples and a variety of simulation studies. Supporting analytical results are also obtained.ResultsOur results provide evidence that using unequal tail probabilities can result in shorter 95 % confidence intervals for the between-study variance. We also show some further results for a real example that illustrates how shorter confidence intervals for the between-study variance can be useful when performing sensitivity analyses for the average effect, which is usually the parameter of primary interest.ConclusionsWe conclude that using unequal tail probabilities when computing 95 % confidence intervals for the between-study variance, when using methods based on generalised heterogeneity statistics, can result in shorter confidence intervals. We suggest that those who find the case for using unequal tail probabilities convincing should use the ‘1–4 % split’, where greater tail probability is allocated to the upper confidence bound. The ‘width-optimal’ interval that we present deserves further investigation.Electronic supplementary materialThe online version of this article (doi:10.1186/s12874-016-0219-y) contains supplementary material, which is available to authorized users.

Fiducial inference in the classical errors-in-variables model

For the slope parameter of the classical errors-in-variables model, existing interval estimations with finite length will have confidence level equal to zero because of the Gleser–Hwang effect. Especially when the reliability ratio is low and the sample size is small, the Gleser–Hwang effect is so serious that it leads to the very liberal coverages and the unacceptable lengths of the existing confidence intervals. In this paper, we obtain two new fiducial intervals for the slope. One is based on a fiducial generalized pivotal quantity and we prove that this interval has the correct asymptotic coverage. The other fiducial interval is based on the method of the generalized fiducial distribution. We also construct these two fiducial intervals for the other parameters of interest of the classical errors-in-variables model and introduce these intervals to a hybrid model. Then, we compare these two fiducial intervals with the existing intervals in terms of empirical coverage and average length. Simulation results show that the two proposed fiducial intervals have better frequency performance. Finally, we provide a real data example to illustrate our approaches.

A Statistical Model to Analyze Clinician Expert Consensus on Glaucoma Progression using Spatially Correlated Visual Field Data.

PurposeWe developed a statistical model to improve the detection of glaucomatous visual field (VF) progression as defined by the consensus of expert clinicians.MethodsWe developed new methodology in the Bayesian setting to properly model the progression status of a patient (as determined by a group of expert clinicians) as a function of changes in spatially correlated sensitivities at each VF location jointly. We used a spatial probit regression model that jointly incorporates all highly correlated VF changes in a single framework while accounting for structural similarities between neighboring VF regions.ResultsOur method had improved model fit and predictive ability compared to competing models as indicated by the deviance information criterion (198.15 vs. 201.29–213.38), a posterior predictive model selection metric (130.08 vs. 142.08–155.59), area under the receiver operating characteristic curve (0.80 vs. 0.59–0.72; all P values < 0.018), and optimal sensitivity (0.92 vs. 0.28–0.82). Simulation study results suggest that estimation (reduction of mean squared errors) and inference (correct coverage of 95% credible intervals) for the model parameters are improved when spatial modeling is incorporated.ConclusionsWe developed a statistical model for the detection of VF progression defined by clinician expert consensus that accounts for spatially correlated changes in visual sensitivity over time, and showed that it outperformed competing models in a number of areas.Translational RelevanceThis model may easily be incorporated into routine clinical practice and be useful for detecting glaucomatous VF progression defined by clinician expert consensus.

Variance estimation when using inverse probability of treatment weighting (IPTW) with survival analysis

Propensity score methods are used to reduce the effects of observed confounding when using observational data to estimate the effects of treatments or exposures. A popular method of using the propensity score is inverse probability of treatment weighting (IPTW). When using this method, a weight is calculated for each subject that is equal to the inverse of the probability of receiving the treatment that was actually received. These weights are then incorporated into the analyses to minimize the effects of observed confounding. Previous research has found that these methods result in unbiased estimation when estimating the effect of treatment on survival outcomes. However, conventional methods of variance estimation were shown to result in biased estimates of standard error. In this study, we conducted an extensive set of Monte Carlo simulations to examine different methods of variance estimation when using a weighted Cox proportional hazards model to estimate the effect of treatment. We considered three variance estimation methods: (i) a naïve model‐based variance estimator; (ii) a robust sandwich‐type variance estimator; and (iii) a bootstrap variance estimator. We considered estimation of both the average treatment effect and the average treatment effect in the treated. We found that the use of a bootstrap estimator resulted in approximately correct estimates of standard errors and confidence intervals with the correct coverage rates. The other estimators resulted in biased estimates of standard errors and confidence intervals with incorrect coverage rates. Our simulations were informed by a case study examining the effect of statin prescribing on mortality. © 2016 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.