When you run 32-bit SAS on Windows and disconnect from the Oracle database server, you might see the error: "ERROR: ORACLE disconnect error: ORA-03135: connection lost contact."

When the problem occurs, you are unable to perform any workflow actions in a SAS solution that uses SAS Workflow Services.

A sign-on to a grid-enabled environment fails while it is trying to communicate with the client host. The following errors then appear in the SAS log:

If your business key column is a name literal, like " business key "n, a syntax error occurs when that variable name does not follow standard SAS naming conventions.

An error occurs because of an incorrectly generated CREATE INDEX clause in an SQL query that is sent to DB2 when the DB2 schema value is SESSION . The error message says "The name '; index_name '; has the wrong number of qualifie

Trying to read a Google BigQuery table that contains a variable that is defined as an array of records might result in an error and cause SAS to shut down. This issue occurs when one of the variables contained in

When you issue a LIBNAME statement for a Google BigQuery database without including the SCHEMA= option, all tables in the project are shown when the libref is expanded. However, if you try to acces

If the following conditions are met in PROC QLIM: the SELECT option and DISCRETE option are specified in the same MODEL statement or ENDOGENOUS statement the same dependent variable with S

When you run the Copy Files task in SAS Enterprise Guide and there is no connection to a SAS server, it fails with the following error: "ERROR: Target folder does not exist or cannot be accessed."

The problem occurs on a content release on the SAS Risk Governance Framework.

The problem occurs on a content release on the SAS Risk Governance Framework.

You can create create a Databricks table by using PROC SQL, but you cannot insert data into the table. PROC APPEND cannot create a new table or append data to an existing table.

When you bulk load data into a Google BigQuery database, you might encounter this error: "Error while reading data, error message: CSV table encountered too many errors, giving up...Error detected while parsing row starting at position: 0...Data

In SAS  High-Performance Risk, a STRESS task might fail with a message like the following in the SAS log while the compute server is sending the ScenarioCF/Value data to the HPRisk Engine:

You might see the following error in SAS Workflow Studio when you try to open the CECL_Cycle_AFS workflow template that is shipped with SAS Solution for CECL:

Medical error is not included on death certificates or in rankings of cause of death. Martin Makary, professor of surgery at Johns Hopkins University School of Medicine, joins us to explain why we don't measure medical error, and why it is so important that we start. Read the full analysis: http://www.bmj.com/content/353/bmj.i2139

The action mechanisms revealed by the biochemical and structural analyses of replicative and translesion synthesis (TLS) DNA polymerases (Pols) are retained in their cellular roles. In this regard, DNA polymerase θ differs from other Pols in that whereas purified Polθ misincorporates an A opposite 1,N6-ethenodeoxyadenosine (ϵdA) using an abasic-like mode, Polθ performs predominantly error-free TLS in human cells. To test the hypothesis that Polθ adopts a different mechanism for replicating through ϵdA in human cells than in the purified Pol, here we analyze the effects of mutations in the two highly conserved tyrosine residues, Tyr-2387 and Tyr-2391, in the Polθ active site. Our findings that these residues are indispensable for TLS by the purified Pol but are not required in human cells, as well as other findings, provide strong evidence that the Polθ active site is reconfigured in human cells to stabilize ϵdA in the syn conformation for Hoogsteen base pairing with the correct nucleotide. The evidence that a DNA polymerase can configure its active site entirely differently in human cells than in the purified Pol establishes a new paradigm for DNA polymerase function.

The U.S. Food and Drug Administration announced March 24 that it is alerting health care professionals, patients and caregivers of EpiPen autoinjector errors related to device malfunctions and user administration.

Days before the Sept. 11, 2001, attacks, Osama bin Laden left his compound in Kandahar in Afghanistan and headed into the mountains. His driver, Salim Ahmed Hamdan, traveled with him. As U.S. and Northern Alliance forces stood poised to capture Kandahar a few months later, bin Laden told Hamdan t...

London : J. Churchill, 1849.

London : H. Renshaw, 1861.

Assaf Rabinowicz, Saharon Rosset.

Source: Electronic Journal of Statistics, Volume 14, Number 1, 272--301.

Abstract:
Common model selection criteria, such as $AIC$ and its variants, are based on in-sample prediction error estimators. However, in many applications involving predicting at interpolation and extrapolation points, in-sample error does not represent the relevant prediction error. In this paper new prediction error estimators, $tAI$ and $Loss(w_{t})$ are introduced. These estimators generalize previous error estimators, however are also applicable for assessing prediction error in cases involving interpolation and extrapolation. Based on these prediction error estimators, two model selection criteria with the same spirit as $AIC$ and Mallow’s $C_{p}$ are suggested. The advantages of our suggested methods are demonstrated in a simulation and a real data analysis of studies involving interpolation and extrapolation in linear mixed model and Gaussian process regression.

Xianzheng Huang, Haiming Zhou.

Source: Electronic Journal of Statistics, Volume 14, Number 1, 970--1023.

Abstract:
We consider estimating the density of a response conditioning on an error-prone covariate. Motivated by two existing kernel density estimators in the absence of covariate measurement error, we propose a method to correct the existing estimators for measurement error. Asymptotic properties of the resultant estimators under different types of measurement error distributions are derived. Moreover, we adjust bandwidths readily available from existing bandwidth selection methods developed for error-free data to obtain bandwidths for the new estimators. Extensive simulation studies are carried out to compare the proposed estimators with naive estimators that ignore measurement error, which also provide empirical evidence for the effectiveness of the proposed bandwidth selection methods. A real-life data example is used to illustrate implementation of these methods under practical scenarios. An R package, lpme, is developed for implementing all considered methods, which we demonstrate via an R code example in Appendix B.2.

Jun Zhang, Yujie Gai, Xia Cui, Gaorong Li.

Source: Brazilian Journal of Probability and Statistics, Volume 34, Number 2, 370--393.

Abstract:
This paper studies the measure of symmetry or asymmetry of a continuous variable under the multiplicative distortion measurement errors setting. The unobservable variable is distorted in a multiplicative fashion by an observed confounding variable. First, two direct plug-in estimation procedures are proposed, and the empirical likelihood based confidence intervals are constructed to measure the symmetry or asymmetry of the unobserved variable. Next, we propose four test statistics for testing whether the unobserved variable is symmetric or not. The asymptotic properties of the proposed estimators and test statistics are examined. We conduct Monte Carlo simulation experiments to examine the performance of the proposed estimators and test statistics. These methods are applied to analyze a real dataset for an illustration.

Victor Coscrato, Rafael Izbicki, Rafael B. Stern.

Source: Brazilian Journal of Probability and Statistics, Volume 34, Number 2, 230--250.

Abstract:
Despite its common practice, statistical hypothesis testing presents challenges in interpretation. For instance, in the standard frequentist framework there is no control of the type II error. As a result, the non-rejection of the null hypothesis $(H_{0})$ cannot reasonably be interpreted as its acceptance. We propose that this dilemma can be overcome by using agnostic hypothesis tests, since they can control the type I and II errors simultaneously. In order to make this idea operational, we show how to obtain agnostic hypothesis in typical models. For instance, we show how to build (unbiased) uniformly most powerful agnostic tests and how to obtain agnostic tests from standard p-values. Also, we present conditions such that the above tests can be made logically coherent. Finally, we present examples of consistent agnostic hypothesis tests.

Monte Carlo simulation is useful to compute or estimate expected functionals of random elements if those random samples are possible to be generated from the true distribution. However, when the distribution has some unknown parameters, the samples must be generated from an estimated distribution with the parameters replaced by some estimators, which causes a statistical error in Monte Carlo estimation. This paper considers such a statistical error and investigates the asymptotic distributions of Monte Carlo-based estimators when the random elements are not only the real valued, but also functional valued random variables. We also investigate expected functionals for semimartingales in details. The consideration indicates that the Monte Carlo estimation can get worse when a semimartingale has a jump part with unremovable unknown parameters.

We focus on estimating emph{a priori} generalization error of two-layer ReLU neural networks (NNs) trained by mean squared error, which only depends on initial parameters and the target function, through the following research line. We first estimate emph{a priori} generalization error of finite-width two-layer ReLU NN with constraint of minimal norm solution, which is proved by cite{zhang2019type} to be an equivalent solution of a linearized (w.r.t. parameter) finite-width two-layer NN. As the width goes to infinity, the linearized NN converges to the NN in Neural Tangent Kernel (NTK) regime citep{jacot2018neural}. Thus, we can derive the emph{a priori} generalization error of two-layer ReLU NN in NTK regime. The distance between NN in a NTK regime and a finite-width NN with gradient training is estimated by cite{arora2019exact}. Based on the results in cite{arora2019exact}, our work proves an emph{a priori} generalization error bound of two-layer ReLU NNs. This estimate uses the intrinsic implicit bias of the minimum norm solution without requiring extra regularity in the loss function. This emph{a priori} estimate also implies that NN does not suffer from curse of dimensionality, and a small generalization error can be achieved without requiring exponentially large number of neurons. In addition the research line proposed in this paper can also be used to study other properties of the finite-width network, such as the posterior generalization error.

Qiyang Han, Jon A. Wellner.

Source: The Annals of Statistics, Volume 47, Number 4, 2286--2319.

Abstract:
We study the performance of the least squares estimator (LSE) in a general nonparametric regression model, when the errors are independent of the covariates but may only have a $p$th moment ($pgeq1$). In such a heavy-tailed regression setting, we show that if the model satisfies a standard “entropy condition” with exponent $alphain(0,2)$, then the $L_{2}$ loss of the LSE converges at a rate [mathcal{O}_{mathbf{P}}igl(n^{-frac{1}{2+alpha}}vee n^{-frac{1}{2}+frac{1}{2p}}igr).] Such a rate cannot be improved under the entropy condition alone. This rate quantifies both some positive and negative aspects of the LSE in a heavy-tailed regression setting. On the positive side, as long as the errors have $pgeq1+2/alpha$ moments, the $L_{2}$ loss of the LSE converges at the same rate as if the errors are Gaussian. On the negative side, if $p<1+2/alpha$, there are (many) hard models at any entropy level $alpha$ for which the $L_{2}$ loss of the LSE converges at a strictly slower rate than other robust estimators. The validity of the above rate relies crucially on the independence of the covariates and the errors. In fact, the $L_{2}$ loss of the LSE can converge arbitrarily slowly when the independence fails. The key technical ingredient is a new multiplier inequality that gives sharp bounds for the “multiplier empirical process” associated with the LSE. We further give an application to the sparse linear regression model with heavy-tailed covariates and errors to demonstrate the scope of this new inequality.

Yating Liu, Gilles Pagès.

Source: Bernoulli, Volume 26, Number 2, 1171--1204.

Abstract:
We establish conditions to characterize probability measures by their $L^{p}$-quantization error functions in both $mathbb{R}^{d}$ and Hilbert settings. This characterization is two-fold: static (identity of two distributions) and dynamic (convergence for the $L^{p}$-Wasserstein distance). We first propose a criterion on the quantization level $N$, valid for any norm on $mathbb{R}^{d}$ and any order $p$ based on a geometrical approach involving the Voronoï diagram. Then, we prove that in the $L^{2}$-case on a (separable) Hilbert space, the condition on the level $N$ can be reduced to $N=2$, which is optimal. More quantization based characterization cases in dimension 1 and a discussion of the completeness of a distance defined by the quantization error function can be found at the end of this paper.

Keisuke Yano, Kengo Kato.

Source: Bernoulli, Volume 26, Number 1, 616--641.

Abstract:
In this paper, we study frequentist coverage errors of Bayesian credible sets for an approximately linear regression model with (moderately) high dimensional regressors, where the dimension of the regressors may increase with but is smaller than the sample size. Specifically, we consider quasi-Bayesian inference on the slope vector under the quasi-likelihood with Gaussian error distribution. Under this setup, we derive finite sample bounds on frequentist coverage errors of Bayesian credible rectangles. Derivation of those bounds builds on a novel Berry–Esseen type bound on quasi-posterior distributions and recent results on high-dimensional CLT on hyperrectangles. We use this general result to quantify coverage errors of Castillo–Nickl and $L^{infty}$-credible bands for Gaussian white noise models, linear inverse problems, and (possibly non-Gaussian) nonparametric regression models. In particular, we show that Bayesian credible bands for those nonparametric models have coverage errors decaying polynomially fast in the sample size, implying advantages of Bayesian credible bands over confidence bands based on extreme value theory.

Michael V. Boutsikas, Eutichia Vaggelatou

Source: Bernoulli, Volume 16, Number 2, 301--330.

Abstract:
Let X 1 , X 2 , …, X n be a sequence of independent or locally dependent random variables taking values in ℤ + . In this paper, we derive sharp bounds, via a new probabilistic method, for the total variation distance between the distribution of the sum ∑ i =1 n X i and an appropriate Poisson or compound Poisson distribution. These bounds include a factor which depends on the smoothness of the approximating Poisson or compound Poisson distribution. This “smoothness factor” is of order O( σ −2 ), according to a heuristic argument, where σ 2 denotes the variance of the approximating distribution. In this way, we offer sharp error estimates for a large range of values of the parameters. Finally, specific examples concerning appearances of rare runs in sequences of Bernoulli trials are presented by way of illustration.