-
作者：Sen, A.; Sen, B.
作者单位：University of Minnesota System; University of Minnesota Twin Cities; Columbia University
摘要：We consider a linear regression model and propose an omnibus test to simultaneously check the assumption of independence between the error and predictor variables and the goodness-of-fit of the parametric model. Our approach is based on testing for independence between the predictor and the residual obtained from the parametric fit by using the Hilbert-Schmidt independence criterion (Gretton et al., 2008). The proposed method requires no user-defined regularization, is simple to compute based ...
-
作者：Ding, Peng; Vanderweele, Tyler J.
作者单位：Harvard University; Harvard University; Harvard T.H. Chan School of Public Health
摘要：A central question in causal inference with observational studies is the sensitivity of conclusions to unmeasured confounding. The classical Cornfield condition allows us to assess whether an unmeasured binary confounder can explain away the observed relative risk of the exposure on the outcome. It states that for an unmeasured confounder to explain away an observed relative risk, the association between the unmeasured confounder and the exposure and the association between the unmeasured conf...
-
作者：Laber, Eric B.; Linn, Kristin A.; Stefanski, Leonard A.
作者单位：North Carolina State University
摘要：Evidence-based rules for optimal treatment allocation are key components in the quest for efficient, effective health-care delivery. Q-learning, an approximate dynamic programming algorithm, is a popular method for estimating optimal sequential decision rules from data. Q-learning requires the modelling of nonsmooth, nonmonotone transformations of the data, complicating the search for adequately expressive, yet parsimonious, statistical models. The default Q-learning working model is multiple ...
-
作者：Durante, Daniele; Dunson, David B.
作者单位：University of Padua; Duke University
摘要：Symmetric binary matrices representing relations are collected in many areas. Our focus is on dynamically evolving binary relational matrices, with interest being on inference on the relationship structure and prediction. We propose a nonparametric Bayesian dynamic model, which reduces dimensionality in characterizing the binary matrix through a lower-dimensional latent space representation, with the latent coordinates evolving in continuous time via Gaussian processes. By using a logistic map...
-
作者：Schott, James R.
作者单位：State University System of Florida; University of Central Florida
摘要：We develop likelihood methods for the Kronecker envelope model in the principal components analysis of matrix observations that have a multivariate normal distribution. Maximum likelihood estimates are derived and the associated likelihood ratio statistic for a test of this Knonecker envelope model is obtained. The asymptotic null distribution of the likelihood ratio statistic is derived as some nuisance parameters approach infinity, and a saddlepoint approximation for this limiting distributi...
-
作者：Gou, Jiangtao; Tamhane, Ajit C.; Xi, Dong; Rom, Dror
作者单位：Northwestern University; Northwestern University; Novartis; Novartis USA
摘要：In this paper we derive a new p-value based multiple testing procedure that improves upon the Hommel procedure by gaining power as well as having a simpler step-up structure similar to the Hochberg procedure. The key to this improvement is that the Hommel procedure can be improved by a consonant procedure. Exact critical constants of this new procedure can be numerically determined. The zeroth-order approximations to the exact critical constants, albeit slightly conservative, are simple to use...
-
作者：Hidaka, S.
作者单位：Japan Advanced Institute of Science & Technology (JAIST)
摘要：We consider the problem of estimating the number of types in a corpus using the number of types observed in a sample of tokens from that corpus. We derive exact and asymptotic distributions for the number of observed types, conditioned on the number of tokens and the latent type distribution. We use the asymptotic distributions to derive an estimator of the latent number of types and validate this estimator numerically.
-
作者：Biswas, Munmun; Mukhopadhyay, Minerva; Ghosh, Anil K.
作者单位：Indian Statistical Institute; Indian Statistical Institute Kolkata; Indian Statistical Institute; Indian Statistical Institute Kolkata
摘要：We propose a multivariate generalization of the univariate two-sample run test based on the shortest Hamiltonian path. The proposed test is distribution-free in finite samples. While most existing two-sample tests perform poorly or are even inapplicable to high-dimensional data, our test can be conveniently used in high-dimension, low-sample-size situations. We investigate its power when the sample size remains fixed and the dimension of the data grows to infinity. Simulated and real datasets ...
-
作者：Maruyama, Yuzo; Strawderman, William E.
作者单位：University of Tokyo; Rutgers University System; Rutgers University New Brunswick
摘要：This paper studies Bayesian variable selection in linear models with general spherically symmetric error distributions. We construct the posterior odds based on a separable prior, which arises as a class of mixtures of Gaussian densities. The posterior odds for comparing among nonnull models are shown to be independent of the error distribution, if this is spherically symmetric. Because of this invariance, we refer to our method as a robust Bayesian variable selection method. We demonstrate th...
-
作者：Barnett, Ian J.; Lin, Xihong
作者单位：Harvard University
摘要：The higher criticism test is effective for testing a joint null hypothesis against a sparse alternative, e.g., for testing the effect of a gene or genetic pathway that consists of d genetic markers. Accurate p-value calculations for the higher criticism test based on the asymptotic distribution require a very large d, which is not the case for the number of genetic variants in a gene or a pathway. In this paper we propose an analytical method for accurately computing the p-value of the higher ...
