On inference validity of weighted U-statistics under data heterogeneity

  title={On inference validity of weighted U-statistics under data heterogeneity},
  author={Fang Han and Tianchen Qian},
  journal={arXiv: Statistics Theory},
Motivated by challenges on studying a new correlation measurement being popularized in evaluating online ranking algorithms' performance, this manuscript explores the validity of uncertainty assessment for weighted U-statistics. Without any commonly adopted assumption, we verify Efron's bootstrap and a new resampling procedure's inference validity. Specifically, in its full generality, our theory allows both kernels and weights asymmetric and data points not identically distributed, which are… Expand

Tables from this paper


Asymptotics of randomly weighted uu- and vv-statistics: Application to bootstrap
A new approach to conditioning is employed to derive a conditional central limit theorem (CLT) for weighted bootstrap u- and v-statistics, assuming the same conditions as the classical CLT for regular u-and- v-Statistics. Expand
Large Sample Confidence Regions Based on Subsamples under Minimal Assumptions
In this article, the construction of confidence regions by approximating the sampling distribution of some statistic is studied. The true sampling distribution is estimated by an appropriateExpand
Presently, conditions ensuring the validity of bootstrap methods for the sample mean of (possibly heterogeneous) near epoch dependent (NED) functions of mixing processes are unknown. Here weExpand
Central limit theorem and the bootstrap for U-statistics of strongly mixing data
A coupling technique introduced in 1983 is used to prove a new generalized covariance inequality similar to Yoshihara's and a CLT is proved for the circular block bootstrap version of U-statistics under absolute regularity and strong mixing. Expand
A new rank correlation coefficient for information retrieval
A new rank correlation coefficient, AP correlation (Τap), is proposed that is based on average precision and has a probabilistic interpretation and is shown to give more weight to the errors at high rankings and has nice mathematical properties which make it easy to interpret. Expand
Estimates of the Regression Coefficient Based on Kendall's Tau
Abstract The least squares estimator of a regression coefficient β is vulnerable to gross errors and the associated confidence interval is, in addition, sensitive to non-normality of the parentExpand
On weighted U-statistics for stationary processes
A weighted U-statistic based on a random sample X1;::: ;Xn has the form Un = P 1•i;jn wiijK(Xi;Xj) where K is fixed symmetric measurable function and the wi are symmetric weights. A large class ofExpand
The Jackknife and the Bootstrap for General Stationary Observations
We extend the jackknife and the bootstrap method of estimating standard errors to the case where the observations form a general stationary sequence. We do not attempt a reduction to i.i.d. values.Expand
The moving blocks bootstrap and robust inference for linear least squares and quantile regressions
Abstract This paper presents the moving blocks bootstrap (MBB) as a new inference procedure for linear regression estimation which is robust to heteroskedasticity and autocorrelation of unknownExpand
Bootstrap Methods: Another Look at the Jackknife
We discuss the following problem given a random sample X = (X 1, X 2,…, X n) from an unknown probability distribution F, estimate the sampling distribution of some prespecified random variable R(X,Expand