Managing a Destructive, Episodic Crop Disease: A National Survey of Wheat and Barley Growers' Experience With Fusarium Head Blight.

The main techniques for minimizing Fusarium head blight (FHB, or scab) and deoxynivalenol in wheat and barley are well established and generally available: planting of moderately FHB-resistant cultivars, risk monitoring, and timely use of the most effective fungicides. Yet the adoption of these techniques remains uneven across the FHB-prone portions of the U.S. cereal production area. A national survey was undertaken by the U.S. Wheat and Barley Scab Initiative in 17 states where six market classes of wheat and barley are grown. In 2014, 5,107 usable responses were obtained. The highest percentages reporting losses attributable to FHB in the previous 5 years were in North Dakota, Maryland, Kentucky, and states bordering the Great Lakes but across all states, ≥75% of respondents reported no FHB-related losses in the previous 5 years. Adoption of cultivar resistance was uneven by state and market class and was low except among hard red spring wheat growers. In 13 states, a majority of respondents had not applied an FHB-targeted fungicide in the previous 5 years. Although the primary FHB information source varied by state, crop consultants were considered to be an important source or their primary source of information on risk or management of FHB by the largest percentage of respondents. Use of an FHB risk forecasting website was about twice as high in North Dakota as the 17-state average of 6%. The most frequently cited barriers to adopting FHB management practices were weather or logistics preventing timely fungicide application, difficulty in determining flowering timing for fungicide applications, and the impracticality of FHB-reducing rotations. The results highlight the challenges of managing an episodically damaging crop disease and point to specific areas for improvement.

Assessing Variability of Complex Descriptive Statistics in Monte Carlo Studies using Resampling Methods.

Good statistical practice dictates that summaries in Monte Carlo studies should always be accompanied by standard errors. Those standard errors are easy to provide for summaries that are sample means over the replications of the Monte Carlo output: for example, bias estimates, power estimates for tests, and mean squared error estimates. But often more complex summaries are of interest: medians (often displayed in boxplots), sample variances, ratios of sample variances, and non-normality measures like skewness and kurtosis. In principle standard errors for most of these latter summaries may be derived from the Delta Method, but that extra step is often a barrier for standard errors to be provided. Here we highlight the simplicity of using the jackknife and bootstrap to compute these standard errors, even when the summaries are somewhat complicated.

Estimation of treatment effect for the sequential parallel design.

The sequential parallel clinical trial is a novel clinical trial design being used in psychiatric diseases that are known to have potentially high placebo response rates. The design consists of an initial parallel trial of placebo versus drug augmented by a second parallel trial of placebo versus drug in the placebo non-responders from the initial trial. Statistical research on the design has focused on hypothesis tests. However, an equally important output from any clinical trial is the estimate of treatment effect and variability around that estimate. In the sequential parallel trial, the most important treatment effect is the effect in the overall population. This effect can be estimated by considering only the first phase of the trial, but this ignores useful information from the second phase of the trial. We develop estimates of treatment effect that incorporate data from both phases of the trial. Our simulations and a real data example suggest that there can be substantial gains in precision by incorporating data from both phases. The potential gains appear to be greatest in moderate-sized trials, which would typically be the case in phase II trials.

FSR Methods for Second-Order Regression Models.

Most variable selection techniques focus on first-order linear regression models. Often, interaction and quadratic terms are also of interest, but the number of candidate predictors grows very fast with the number of original predictors, making variable selection more difficult. Forward selection algorithms are thus developed that enforce natural hierarchies in second-order models to control the entry rate of uninformative effects and to equalize the false selection rates from first-order and second-order terms. Method performance is compared through Monte Carlo simulation and illustrated with data from a Cox regression and from a response surface experiment.

Coming Together: How Medical Students, Academic Administrators, and Hospital Administrators Approached Student Volunteering During the COVID-19 Pandemic.

The COVID-19 pandemic caused dramatic interruptions and shifts to medical education, but students at schools nationwide responded by volunteering to support their physician educators on the frontlines. Relationships between student leaders, school administrators, and hospital administrators were key to the successful creation and organization of volunteer responses. This perspective piece from medical students, as well as hospital and medical school leadership, explores the evolving relationships in the creation of Rutgers New Jersey Medical School's Student COVID Team. By reflecting on choices made by each group in parallel points in time, the piece highlights where interests and actions aligned and diverged.

Fast FSR variable selection with applications to clinical trials.

A new version of the false selection rate variable selection method of Wu, Boos, and Stefanski (2007, Journal of the American Statistical Association 102, 235-243) is developed that requires no simulation. This version allows the tuning parameter in forward selection to be estimated simply by hand calculation from a summary table of output even for situations where the number of explanatory variables is larger than the sample size. Because of the computational simplicity, the method can be used in permutation tests and inside bagging loops for improved prediction. Illustration is provided in clinical trials for linear regression, logistic regression, and Cox proportional hazards regression.

Maximum likelihood estimation of time to first event in the presence of data gaps and multiple events.

We propose a novel likelihood method for analyzing time-to-event data when multiple events and multiple missing data intervals are possible prior to the first observed event for a given subject. This research is motivated by data obtained from a heart monitor used to track the recovery process of subjects experiencing an acute myocardial infarction. The time to first recovery, T1, is defined as the time when the ST-segment deviation first falls below 50% of the previous peak level. Estimation of T1 is complicated by data gaps during monitoring and the possibility that subjects can experience more than one recovery. If gaps occur prior to the first observed event, T, the first observed recovery may not be the subject's first recovery. We propose a parametric gap likelihood function conditional on the gap locations to estimate T1 Standard failure time methods that do not fully utilize the data are compared to the gap likelihood method by analyzing data from an actual study and by simulation. The proposed gap likelihood method is shown to be more efficient and less biased than interval censoring and more efficient than right censoring if data gaps occur early in the monitoring process or are short in duration.

P-Value Precision and Reproducibility.

P-values are useful statistical measures of evidence against a null hypothesis. In contrast to other statistical estimates, however, their sample-to-sample variability is usually not considered or estimated, and therefore not fully appreciated. Via a systematic study of log-scale p-value standard errors, bootstrap prediction bounds, and reproducibility probabilities for future replicate p-values, we show that p-values exhibit surprisingly large variability in typical data situations. In addition to providing context to discussions about the failure of statistical results to replicate, our findings shed light on the relative value of exact p-values vis-a-vis approximate p-values, and indicate that the use of *, **, and *** to denote levels .05, .01, and .001 of statistical significance in subject-matter journals is about the right level of precision for reporting p-values when judged by widely accepted rules for rounding statistical estimates.

New confidence bounds for QT studies.

The proposed guidelines for the assessment of the effect of new pharmaceutical agents on the QT interval (beginning of QRS complex to end of T wave on the electrocardiogram) are based on the maximum of a series over time of simple one-sided 95 per cent upper confidence bounds. This procedure is typically very conservative as a procedure for obtaining a 95 per cent bound for the maximum of the population parameters. This paper proposes new bounds for the maximum, both analytical and bootstrap-based, that are lower but still achieve correct coverage in the context of crossover and parallel designs for the most realistic portions of the parameter space.

The distribution of genetic parameter estimates and confidence intervals from small disconnected diallels.

The distributions of genetic variance components and their ratios (heritability and type-B genetic correlation) from 105 pairs of six-parent disconnected half-diallels of a breeding population of loblolly pine (Pinus taeda L.) were examined. A series of simulations based on these estimates were carried out to study the coverage accuracy of confidence intervals based on the usual t-method and several other alternative methods. Genetic variance estimates fluctuated greatly from one experiment to another. Both general combining ability variance (sigma(2) (g)) and specific combining ability variance (sigma(2) (s)) had a large positive skewness. For sigma(2) (g) and sigma(2) (s), a skewness-adjusted t-method proposed by Boos and Hughes-Oliver (Am Stat 54:121-128, 2000) provided better upper endpoint confidence intervals than t-intervals, whereas they were similar for the lower endpoint. Bootstrap BCa-intervals (Efron and Tibshirani, An introduction to the bootstrap. Chapman & Hall, London 436 p, 1993) and Hall's transformation methods (Zhou and Gao, Am Stat 54:100-104, 2000) had poor coverages. Coverage accuracy of Fieller's interval endpoint(J R Stat Soc Ser B 16:175-185, 1954) and t-interval endpoint were similar for both h(2) and r(B) for sample sizes n

Score tests for dose effect in the presence of non-responders.

When only a certain proportion of subjects respond to treatment ('responders') or may never experience an event of interest (thus 'cured'), mixture models often lead to increased understanding of the treatment or disease process. This paper focuses on hypothesis testing in a dose-response framework and shows that increased power is possible by using a mixture model where both the logit of the response rate and the response mean are linear functions of the dose level. Three score tests are developed for testing an overall effect and permutation methods are used to control the type I error. Extensive simulations establish the power properties of the tests and show that our proposed score test has the best performance. The approach is illustrated by a multi-country clinical trial of rapid acting Intramuscular Olanzapine.