The purpose of this paper is to review both classic and modern methods for constructing prediction intervals. We focus, primarily, on model-based non-Bayesian methods for the prediction of a scalar random variable, but we also include Bayesian methods with objective prior distributions. Our review of non-Bayesian methods follows two lines: general methods based on (approximate) pivotal quantities and methods based on non-Bayesian predictive distributions. The connection between these two types of methods is described for distributions in the (log-)location-scale family. We also discuss extending the general prediction methods to data with complicated dependence structures as well as some nonparametric prediction methods (e.g., conformal prediction).

We propose well-calibrated null preference priors for use with one-sided hypothesis tests, such that resulting Bayesian and frequentist inferences agree. Null preference priors mean that they have nearly 100% of their prior belief in the null hypothesis, and well-calibrated priors mean that the resulting posterior beliefs in the alternative hypothesis are not overconfident. This formulation expands the class of problems giving Bayes-frequentist agreement to include problems involving discrete distributions such as binomial and negative binomial one- and two-sample exact (i.e., valid) tests. When applicable, these priors give posterior belief in the null hypothesis that is a valid p-value, and the null preference prior emphasizes that large p-values may simply represent insufficient data to overturn prior belief. This formulation gives a Bayesian interpretation of some common frequentist tests, as well as more intuitively explaining lesser known and less straightforward confidence intervals for two-sample tests.

In this article, I will discuss my experience as a statistician involved in COVID-19 research in multiple capacities in the last two years, especially in the early phase of the pandemic. I will reflect on the challenges and the lessons I have learned in pandemic research regarding data collection and access, epidemic modeling and data analysis, open science and real time dissemination of research findings, implementation science, media and public communication, and partnerships between academia, government, industry and civil society. I will also make several recommendations on navigating the next stage of the pandemic and preparing for future pandemics.

In modern science, computer models are often used to understand complex phenomena and a thriving statistical community has grown around analyzing them. This review aims to bring a spotlight to the growing prevalence of stochastic computer models—providing a catalogue of statistical methods for practitioners, an introductory view for statisticians (whether familiar with deterministic computer models or not), and an emphasis on open questions of relevance to practitioners and statisticians. Gaussian process surrogate models take center stage in this review, and these, along with several extensions needed for stochastic settings, are explained. The basic issues of designing a stochastic computer experiment and calibrating a stochastic computer model are prominent in the discussion. Instructive examples, with data and code, are used to describe the implementation of, and results from, various methods.

Multiple imputation (MI) is a method for repairing and analyzing data with missing values. MI replaces missing values with a sample of random values drawn from an imputation model. The most popular form of MI, which we call posterior draw multiple imputation (PDMI), draws the parameters of the imputation model from a Bayesian posterior distribution. An alternative, which we call maximum likelihood multiple imputation (MLMI), estimates the parameters of the imputation model using maximum likelihood (or equivalent). Compared to PDMI, MLMI is less computationally intensive, faster, and yields slightly more efficient point estimates. A past barrier to using MLMI was the difficulty of estimating the standard errors of MLMI point estimates. We derive, implement, and evaluate three consistent standard error formulas: (1) one combines variances within and between the imputed datasets, (2) one uses the score function, and (3) one uses the bootstrap to estimate variance components due to sampling and imputation. Formula (1) modifies for MLMI a formula that has long been used under PDMI, while formulas (2) and (3) can be used without modification under either PDMI or MLMI. We have implemented MLMI and the standard error estimators in the mlmi and bootImpute packages for R.

We congratulate Ruobin Gong and Xiao-Li Meng on their thought-provoking paper demonstrating the power of imprecise probabilities in statistics. In particular, Gong and Meng clarify important statistical paradoxes by discussing them in the framework of generalized uncertainty quantification and different conditioning rules used for updating. In this note, we characterize all three conditioning rules as envelopes of certain sets of conditional probabilities. This view also suggests some generalizations that can be seen as compromise rules. Similar to Gong and Meng, our derivations mainly focus on Choquet capacities of order 2, and so we also briefly discuss in general their role as statistical models. We conclude with some general remarks on the potential of imprecise probabilities to cope with the multidimensional nature of uncertainty.

Gong and Meng show that we can gain insights into classical paradoxes about conditional probability by acknowledging that apparently precise probabilities live within a larger world of imprecise probability. They also show that the notion of updating becomes problematic in this larger world. A closer look at the historical development of the notion of updating can give us further insights into its limitations.

We discuss how sampling design, units, the observation mechanism and other basic statistical notions figure into modern network data analysis. These considerations pose several new challenges that cannot be adequately addressed by merely extending or generalizing classical methods. Such challenges stem from fundamental differences between the domains in which network data emerge and those for which classical tools were developed. By revisiting these basic statistical considerations, we suggest a framework in which to develop theory and methods for network analysis in a way that accounts for both conceptual and practical challenges of network science. We then discuss how some well-known model classes fit within this framework.

In exciting recent work, Bertsimas, King and Mazumder (Ann. Statist. 44 (2016) 813–852) showed that the classical best subset selection problem in regression modeling can be formulated as a mixed integer optimization (MIO) problem. Using recent advances in MIO algorithms, they demonstrated that best subset selection can now be solved at much larger problem sizes than what was thought possible in the statistics community. They presented empirical comparisons of best subset with other popular variable selection procedures, in particular, the lasso and forward stepwise selection. Surprisingly (to us), their simulations suggested that best subset consistently outperformed both methods in terms of prediction accuracy. Here, we present an expanded set of simulations to shed more light on these comparisons. The summary is roughly as follows: •neither best subset nor the lasso uniformly dominate the other, with best subset generally performing better in very high signal-to-noise (SNR) ratio regimes, and the lasso better in low SNR regimes; •for a large proportion of the settings considered, best subset and forward stepwise perform similarly, but in certain cases in the high SNR regime, best subset performs better; •forward stepwise and best subsets tend to yield sparser models (when tuned on a validation set), especially in the high SNR regime; •the relaxed lasso (actually, a simplified version of the original relaxed estimator defined in Meinshausen (Comput. Statist. Data Anal. 52 (2007) 374–393)) is the overall winner, performing just about as well as the lasso in low SNR scenarios, and nearly as well as best subset in high SNR scenarios.