The Bayesian measure of sample information about the parameter, known as Lindley's measure, is widely used in various problems such as developing prior distributions, models for the likelihood functions and optimal designs. The predictive information is defined similarly and used for model selection and optimal designs, though to a lesser extent. The parameter and predictive information measures are proper utility functions and have been also used in combination. Yet the relationship between the two measures and the effects of conditional dependence between the observable quantities on the Bayesian information measures remain unexplored. We address both issues. The relationship between the two information measures is explored through the information provided by the sample about the parameter and prediction jointly. The role of dependence is explored along with the interplay between the information measures, prior and sampling design. For the conditionally independent sequence of observable quantities, decompositions of the joint information characterize Lindley's measure as the sample information about the parameter and prediction jointly and the predictive information as part of it. For the conditionally dependent case, the joint information about parameter and prediction exceeds Lindley's measure by an amount due to the dependence. More specific results are shown for the normal linear models and a broad subfamily of the exponential family. Conditionally independent samples provide relatively little information for prediction, and the gap between the parameter and predictive information measures grows rapidly with the sample size.
Volkswagen Group of America Innovation Center California（大众汽车美国创新中心加州）；BayzAI
The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles. Bayesian Attention Networks are defined by introducing an attention factor per a training sample loss as a function of two sample inputs, from training sample and prediction sample. By using a sharpened Jensen's inequality we show that the attention factor is completely defined by a correlation function of the two samples w.r.t. the model weights. Due to the attention factor the solution for a prediction sample is mostly defined by a few training samples that are correlated with the p…
Bayesian sample size calculations for external validation studies of risk prediction models
Faculty of Pharmaceutical Sciences, The University of British Columbia（不列颠哥伦比亚大学药学院）；Department of Statistics, The University of British Columbia（不列颠哥伦比亚大学统计系）；British Columbia Centre For Disease Control（不列颠哥伦比亚疾病控制中心）；CAPHRI Care and Public Health Research Institute, Maastricht University（马斯特里赫特大学CAPHRI健康与公共护理研究所）；Department of Development and Regeneration, KU Leuven（荷语鲁汶大学发展与再生系）；Department of Applied Health Sciences, School of Health Sciences, College of Medicine and Health, University of Birmingham（伯明翰大学健康科学学院应用健康科学系）；National Institute for Health and Care Research (NIHR) Birmingham Biomedical Research Centre（英国国家卫生保健研究卓越创新中心伯明翰生物医学研究中心）
In this paper, we develop Bayesian predictive inferential procedures for prediction of repair times of a series system, applying a minimal repair strategy, using the information contained in an independent observed hybrid censored sample of the lifetimes of the components of the system, assuming the underlying distribution of the lifetimes to be Rayleigh distribution. An illustrative real data example and a simulation study are presented for the purpose of illustration and comparison of the proposed predictors.
In this paper, we treat estimation and prediction problems where negative multinomial variables are observed and in particular consider unbalanced settings. First, the problem of estimating multiple negative multinomial parameter vectors under the standardized squared error loss is treated and a new empirical Bayes estimator which dominates the UMVU estimator under suitable conditions is derived. Second, we consider estimation of the joint predictive density of several multinomial tables under the Kullback-Leibler divergence and obtain a sufficient condition under which the Bayesian predictive…
The prediction of cancer prognosis and metastatic potential immediately after the initial diagnoses is a major challenge in current clinical research. The relevance of such a signature is clear, as it will free many patients from the agony and toxic side-effects associated with the adjuvant chemotherapy automatically and sometimes carelessly subscribed to them. Motivated by this issue, Ein-Dor (2006) and Zuk (2007) presented a Bayesian model which leads to the following conclusion: Thousands of samples are needed to generate a robust gene list for predicting outcome. This conclusion is based o…
Employing a large dataset (at most, the order of n = 10^6), this study attempts enhance the literature on the comparison between regression and machine learning (ML)-based rent price prediction models by adding new empirical evidence and considering the spatial dependence of the observations. The regression-based approach incorporates the nearest neighbor Gaussian processes (NNGP) model, enabling the application of kriging to large datasets. In contrast, the ML-based approach utilizes typical models: extreme gradient boosting (XGBoost), random forest (RF), and deep neural network (DNN). The ou…
Kyoto University（京都大学）；Preferred Networks, Inc.（Preferred Networks公司）；University of Tsukuba（筑波大学）
Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: "how do we explain the predictions of graph convolutional networks?" A possible approach to answer this question is to visualize evidence substructures responsible for the predictions. For chemical property prediction tasks, the sample size of the training data is often small and/or a label imbalance problem occurs, where a few samples belong to a single class and the majority of samples belong to the other classes. This can lead to uncertainty r…
Background: Due to the finite size of the development sample, predicted probabilities from a risk prediction model are inevitably uncertain. We apply Value of Information methodology to evaluate the decision-theoretic implications of prediction uncertainty. Methods: Adopting a Bayesian perspective, we extend the definition of the Expected Value of Perfect Information (EVPI) from decision analysis to net benefit calculations in risk prediction. In the context of model development, EVPI is the expected gain in net benefit by using the correct predictions as opposed to predictions from a proposed…
A decomposition of Fisher's information to inform sample size for developing or updating fair and precise clinical prediction models -- Part 3: continuous outcomes
The mean absolute deviation about the mean is an alternative to the standard deviation for measuring dispersion in a sample or in a population. For stationary, ergodic time series with a finite first moment, an asymptotic expansion for the sample mean absolute deviation is proposed. The expansion yields the asymptotic distribution of the sample mean absolute deviation under a wide range of settings, allowing for serial dependence or an infinite second moment.
Functional Data Analysis represents a field of growing interest in statistics. Despite several studies have been proposed leading to fundamental results, the problem of obtaining valid and efficient prediction sets has not been thoroughly covered. Indeed, the great majority of methods currently in the literature rely on strong distributional assumptions (e.g, Gaussianity), dimension reduction techniques and/or asymptotic arguments. In this work, we propose a new nonparametric approach in the field of Conformal Prediction based on a new family of nonconformity measures inducing conformal predic…
We consider the problem of testing the equality of conditional distributions of a response variable given a vector of covariates between two populations. Such a hypothesis testing problem can be motivated from various machine learning and statistical inference scenarios, including transfer learning and causal predictive inference. We develop a nonparametric test procedure inspired from the conformal prediction framework. The construction of our test statistic combines recent developments in conformal prediction with a novel choice of conformity score, resulting in a weighted rank-sum test stat…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；ETH Zurich（苏黎世联邦理工学院）；Tsinghua University（清华大学）；HOCH Health Ostschweiz, Kantonsspital St. Gallen（瑞士东部健康组织，圣加仑州立医院）
We propose several prediction intervals procedures for the individual treatment effect with either finite-sample or asymptotic coverage guarantee in a non-parametric regression setting, where non-linear regression functions, heteroskedasticity and non-Gaussianity are allowed. The construct the prediction intervals we use the conformal method of Vovk et al. (2005). In extensive simulations, we compare the coverage probability and interval length of our prediction interval procedures. We demonstrate that complex learning algorithms, such as neural networks, can lead to narrower prediction interv…
The paper considers the problem of out-of-sample risk estimation under the high dimensional settings where standard techniques such as $K$-fold cross validation suffer from large biases. Motivated by the low bias of the leave-one-out cross validation (LO) method, we propose a computationally efficient closed-form approximate leave-one-out formula (ALO) for a large class of regularized estimators. Given the regularized estimate, calculating ALO requires minor computational overhead. With minor assumptions about the data generating process, we obtain a finite-sample upper bound for $|\text{LO} -…
With a growing interest in using non-representative samples to train prediction models for numerous outcomes it is necessary to account for the sampling design that gives rise to the data in order to assess the generalized predictive utility of a proposed prediction rule. After learning a prediction rule based on a non-uniform sample, it is of interest to estimate the rule's error rate when applied to unobserved members of the population. Efron (1986) proposed a general class of covariance penalty inflated prediction error estimators that assume the available training data are representative o…
This paper considers the estimation and prediction of a high-dimensional linear regression in the setting of transfer learning, using samples from the target model as well as auxiliary samples from different but possibly related regression models. When the set of "informative" auxiliary samples is known, an estimator and a predictor are proposed and their optimality is established. The optimal rates of convergence for prediction and estimation are faster than the corresponding rates without using the auxiliary samples. This implies that knowledge from the informative auxiliary samples can be t…
Poznan University of Technology（波兹南理工大学）；Polish Academy of Sciences（波兰科学院）；MNM Bioscience（MNM生物科学公司）
Machine learning applications, especially in the fields of me\-di\-cine and social sciences, are slowly being subjected to increasing scrutiny. Similarly to sample size planning performed in clinical and social studies, lawmakers and funding agencies may expect statistical uncertainty estimations in machine learning applications that impact society. In this paper, we present an easy-to-use python package and web application for estimating prediction confidence intervals. The package offers eight different procedures to determine and justify the sample size and confidence of predictions from ho…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Columbia University（哥伦比亚大学）
This paper proposes probabilistic conformal prediction (PCP), a predictive inference algorithm that estimates a target variable by a discontinuous predictive set. Given inputs, PCP construct the predictive set based on random samples from an estimated generative model. It is efficient and compatible with either explicit or implicit conditional generative models. Theoretically, we show that PCP guarantees correct marginal coverage with finite samples. Empirically, we study PCP on a variety of simulated and real datasets. Compared to existing methods for conformal inference, PCP provides sharper…
In regression with random design, we study the problem of selecting a model that performs well for out-of-sample prediction. We do not assume that any of the candidate models under consideration are correct. Our analysis is based on explicit finite-sample results. Our main findings differ from those of other analyses that are based on traditional large-sample limit approximations because we consider a situation where the sample size is small relative to the complexity of the data-generating process, in the sense that the number of parameters in a `good' model is of the same order as sample siz…
We propose a new inference framework called localized conformal prediction. It generalizes the framework of conformal prediction by offering a single-test-sample adaptive construction that emphasizes a local region around this test sample, and can be combined with different conformal score constructions. The proposed framework enjoys an assumption-free finite sample marginal coverage guarantee, and it also offers additional local coverage guarantees under suitable assumptions. We demonstrate how to change from conformal prediction to localized conformal prediction using several conformal score…
We propose a new method called localized conformal prediction, where we can perform conformal inference using only a local region around a new test sample to construct its confidence interval. Localized conformal inference is a natural extension to conformal inference. It generalizes the method of conformal prediction to the case where we can break the data exchangeability, so as to give the test sample a special role. To our knowledge, this is the first work that introduces such a localization to the framework of conformal prediction. We prove that our proposal can also have assumption-free a…
We present a brief overview of the methods for making statistical inference (testing statistical hypotheses, construction of confidence and/or prediction intervals and regions) about linear functions of the fixed effects and/or about the fixed and random effects simultaneously, in conventional simple linear mixed model. The presented approach is based on solutions from the Henderson's mixed model equations.
Missing data are common in data analyses in biomedical fields, and imputation methods based on random forests (RF) have become widely accepted, as the RF algorithm can achieve high accuracy without the need for specification of data distributions or relationships. However, the predictions from RF do not contain information about prediction uncertainty, which was unacceptable for multiple imputation. Available RF-based multiple imputation methods tried to do proper multiple imputation either by sampling directly from observations under predicting nodes without accounting for the prediction erro…
Conformal prediction methods construct prediction regions for iid data that are valid in finite samples. We provide two parametric conformal prediction regions that are applicable for a wide class of continuous statistical models. This class of statistical models includes generalized linear models (GLMs) with continuous outcomes. Our parametric conformal prediction regions possesses finite sample validity, even when the model is misspecified, and are asymptotically of minimal length when the model is correctly specified. The first parametric conformal prediction region is constructed through b…
We consider the multi-class classification problem when the training data and the out-of-sample test data may have different distributions and propose a method called BCOPS (balanced and conformal optimized prediction sets). BCOPS constructs a prediction set $C(x)$ as a subset of class labels, possibly empty. It tries to optimize the out-of-sample performance, aiming to include the correct class as often as possible, but also detecting outliers $x$, for which the method returns no prediction (corresponding to $C(x)$ equal to the empty set). The proposed method combines supervised-learning algo…
We study distribution free, nonparametric prediction bands with a special focus on their finite sample behavior. First we investigate and develop different notions of finite sample coverage guarantees. Then we give a new prediction band estimator by combining the idea of "conformal prediction" (Vovk et al. 2009) with nonparametric conditional density estimation. The proposed estimator, called COPS (Conformal Optimized Prediction Set), always has finite sample guarantee in a stronger sense than the original conformal prediction estimator. Under regularity conditions the estimator converges to a…
A Critical Perspective on Finite Sample Conformal Prediction Theory in Medical Applications
Max Planck Institute for Intelligent Systems, Germany（德国马克斯·普朗克智能系统研究所）；Tübingen AI Center, Germany（图宾根人工智能中心）；ELLIS Institute Tübingen, Germany（图宾根ELLIS研究所）；Department of Digital Medicine, University of Bern, Switzerland（伯恩大学数字医学系）；Department of Diabetes, Endocrinology, Nutritional Medicine and Metabolism UDEM, Inselspital, Bern University Hospital, University of Bern, Switzerland（伯恩大学糖尿病、内分泌学、营养医学和代谢学系）；Diabetes Center Berne, Bern, Switzerland（伯恩糖尿病中心）；University of Tübingen, Germany（图宾根大学）；University of Lucerne, Switzerland（卢塞恩大学）
