87,714 Hits in 4.0 sec

Permutation inference for the general linear model

Anderson M. Winkler, Gerard R. Ridgway, Matthew A. Webster, Stephen M. Smith, Thomas E. Nichols
2014 NeuroImage  
We present a generic framework for permutation inference for complex general linear models (GLMs) when the errors are exchangeable and/or have a symmetric distribution, and show that, even in the presence  ...  the best method for settings that are typical for imaging research scenarios.  ...  Conclusion We presented a generic framework that allows permutation inference using the general linear model with complex experimental designs, and which depends only on the weak requirements of exchangeable  ... 
doi:10.1016/j.neuroimage.2014.01.060 pmid:24530839 pmcid:PMC4010955 fatcat:37c2aeh5xjg4dkny7pd47q6nqa

New methods for multiple testing in permutation inference for the general linear model [article]

Tomas Mrkvicka, Mari Myllymaki, Mikko Kuronen, Naveen Naidu Narisetty
2020 arXiv   pre-print
Permutation methods are commonly used to test significance of regressors of interest in general linear models (GLMs) for functional (image) data sets, in particular for neuroimaging applications as they  ...  Permutation inference for GLMs typically consists of three parts: choosing a relevant test statistic, computing pointwise permutation tests and applying a multiple testing correction.  ...  Data availability We confirm that the used data of autism brain imaging from ABIDE are freely available at http://fcon I.html.  ... 
arXiv:1906.09004v3 fatcat:6zorcrtpw5gqdgg7ga3wpo5fei

glmperm: A Permutation of Regressor Residuals Test for Inference in Generalized Linear Models

Wiebke Werft, Axel Benner
2010 The R Journal  
We introduce a new R package called glmperm for inference in generalized linear models especially for small and moderate-sized data sets.  ...  The inference is based on the permutation of regressor residuals test introduced by Potter (2005) .  ...  Acknowledgements We would like to acknowledge the many valuable suggestions made by two anonymous referees. Bibliography  ... 
doi:10.32614/rj-2010-007 fatcat:lrdq3lf55jeglknni3cnkxlwre

A unified approach to estimation and prediction under simple random sampling

Edward J. Stanek III, Julio da Motta Singer, Viviana Beatriz Lencina
2004 Journal of Statistical Planning and Inference  
We consider a probability model where the design based approach to inference under simple random sampling of a finite population encompasses a simple random permutation superpopulation model.  ...  The model consists of an expanded set of random variables following a random permutation probability distribution that keeps track of both the units' labels and positions in the permutation.  ...  Loureiro for helpful comments that lead to improvements in the manuscript.  ... 
doi:10.1016/s0378-3758(03)00114-9 fatcat:m34lzvf2bbgqbgwb3aojtm2o4i

Generalized Linear Models for Aggregated Data [article]

Avradeep Bhowmik, Joydeep Ghosh, Oluwasanmi Koyejo
2016 arXiv   pre-print
We consider a limiting case of generalized linear modeling when the target variables are only known up to permutation, and explore how this relates to permutation testing; a standard technique for assessing  ...  Based on this relationship, we propose a simple algorithm to estimate the model parameters and individual level inferences via alternating imputation and standard generalized linear model fitting.  ...  We consider a limiting case of generalized linear modeling when the target variables are only known up to permutation, and explore how this relates to permutation testing; a standard technique for assessing  ... 
arXiv:1605.04466v1 fatcat:utch27hxyvhmbgd4oftrl74nwa

Towards Secure and Practical Machine Learning via Secret Sharing and Random Permutation [article]

Fei Zheng, Chaochao Chen, Xiaolin Zheng, Mingjie Zhu
2022 arXiv   pre-print
Since our method reduces the cost for element-wise function computation, it is more efficient than existing cryptographic methods.  ...  With the increasing demands for privacy protection, privacy-preserving machine learning has been drawing much attention in both academia and industry.  ...  Neural Network Inference and Training Based on A-SS and the compute-after-permutation techniques, we can implement both inference and training algorithms for general machine learning models such as fully  ... 
arXiv:2108.07463v3 fatcat:r7jbejughvcifjatvj62uh6icm

Statistically reinforced machine learning for nonlinear patterns and variable interactions

Masahiro Ryo, Matthias C. Rillig
2017 Ecosphere  
We demonstrate the behaviors of three techniques (conditional inference tree, model-based tree, and permutation-based random forest) by analyzing an artificially generated example dataset that contains  ...  Most statistical models assume linearity and few variable interactions, even though real-world ecological patterns often result from nonlinear and highly interactive processes.  ...  Zeileis et al. 2008) , couples the features of parametric statistical models such as generalized linear models and decision tree models.  ... 
doi:10.1002/ecs2.1976 fatcat:w77ryefvpfepjjm7tm42n6dotu

Neural Full-Rank Spatial Covariance Analysis for Blind Source Separation

Yoshiaki Bando, Kouhei Sekiguchi, Yoshiki Masuyama, Aditya Arie Nugraha, Mathieu Fontaine, Kazuyoshi Yoshii
2021 IEEE Signal Processing Letters  
Once the inference model is optimized, it can be used for estimating the latent features of sources included in unseen mixture signals.  ...  This paper describes a neural blind source separation (BSS) method based on amortized variational inference (AVI) of a non-linear generative model of mixture signals.  ...  A typical model utilizes the decoder of a variational autoencoder (VAE) [19] as a non-linear generative model of a source signal.  ... 
doi:10.1109/lsp.2021.3101699 fatcat:o37fcxqdg5f3phbnxhwbdvkhai

Accelerated estimation and permutation inference for ACE modeling

Xu Chen, Elia Formisano, Gabriëlla A. M. Blokland, Lachlan T. Strike, Katie L. McMahon, Greig I. Zubicaray, Paul M. Thompson, Margaret J. Wright, Anderson M. Winkler, Tian Ge, Thomas E. Nichols
2019 Human Brain Mapping  
Combined with permutation, we call this approach "Accelerated Permutation Inference for the ACE Model (APACE)" where ACE refers to the additive genetic (A) effects, and common (C), and unique (E) environmental  ...  There are a wealth of tools for fitting linear models at each location in the brain in neuroimaging analysis, and a wealth of genetic tools for estimating heritability for a small number of phenotypes.  ...  DATA ACCESSIBILITY We have developed a Matlab-based tool "Accelerated Permutation Inference for the ACE Model (APACE)", which provides different analysis approaches specialized for heritability inference  ... 
doi:10.1002/hbm.24611 pmid:31037793 pmcid:PMC6680147 fatcat:dyyqidmvk5dkfgxbl5weqnzwuu

A connection between pattern classification by machine learning and statistical inference with the General Linear Model

Juan-Manuel Gorriz, John Suckling, Javier Ramirez, Carmen Jimenez-Mesa, Fermin Segovia
2021 IEEE journal of biomedical and health informatics  
A connection between the general linear model (GLM) with frequentist statistical testing and machine learning (MLE) inference is derived and illustrated.  ...  Subsequently, we derive a more refined predictive statistical test: the linear Support Vector Machine (SVM), that maximizes the class margin of separation within a permutation analysis.  ...  In this paper we show a connection between the classical general linear model (GLM), including random effect models, with the MLE framework for the estimation of model/classifier parameters and subsequent  ... 
doi:10.1109/jbhi.2021.3101662 fatcat:iyjb7gf4jvcg3lpqlcevhab3t4

Privacy-preserving Cloud-based DNN Inference [article]

Shangyu Xie, Bingyu Liu, Yuan Hong
2021 arXiv   pre-print
well-addressed due to the complexity of DNN models and expensive cryptographic primitives.  ...  Finally, we conduct extensive experiments on two commonly-used datasets to validate both effectiveness and efficiency for the PROUD, which also outperforms the state-of-the-art techniques.  ...  Acknowledgments This work is partially supported by the NSF under Grant No. CNS-1745894. The authors would like to thank the anonymous reviewers for their constructive comments.  ... 
arXiv:2102.03915v2 fatcat:zr4vgfbsu5h6lmed4is53qkage

Seq2VAR: Multivariate Time Series Representation with Relational Neural Networks and Linear Autoregressive Model [chapter]

Edouard Pineau, Sébastien Razakarivony, Thomas Bonald
2020 Lecture Notes in Computer Science  
We propose to associate a relational neural network to a VAR generative model to form an encoder-decoder of MTS. The model is denoted Seq2VAR for Sequenceto-VAR.  ...  In this paper, we propose to use the inference capacity of neural networks to overpass this limit.  ...  Acknowledgments This work is supported by the company Safran through the CIFRE convention 2017/1317.  ... 
doi:10.1007/978-3-030-39098-3_10 fatcat:zxyqzc7ujbcptltumr3icl72ma

Opening the Black Box: Machine Learning Interpretability and Inference Tools with an Application to Economic Forecasting [chapter]

Marcus Buckmann, Andreas Joseph, Helena Robertson
2021 Data Science for Economics and Finance  
The latter is achieved by the Shapley regression framework, which allows for the evaluation and communication of machine learning models akin to that of linear models.  ...  AbstractWe present a comprehensive comparative case study for the use of machine learning models for macroeconomics forecasting.  ...  To the best of our knowledge, there exists only one general framework that performs statistical inference jointly on all variables used in a machine learning prediction model to test for their statistical  ... 
doi:10.1007/978-3-030-66891-4_3 fatcat:fdmig5pohbc2leii5qa46l5qwa

Overview and Main Advances in Permutation Tests for Linear Regression Models

Massimiliano Giacalone, Angela Alibrandi
2015 Journal of Mathematics and System Science  
The purpose of this study is to examine different kinds of permutation tests applied to linear models, focused our attention on the specific test statistic on which they are based.  ...  An alternative to the normal model is the permutation or randomization model.  ...  Overview and Main Advances in Permutation Tests for Linear Regression Models 57 The Permutation Test of the Dependent Variable The Exact Restricted Permutation Tests for Partial Regression Models  ... 
doi:10.17265/2159-5291/2015.02.001 fatcat:5whapw232bdvdkm2picnzls43q

Bivariate Causal Discovery and Its Applications to Gene Expression and Imaging Data Analysis

Rong Jiao, Nan Lin, Zixin Hu, David A. Bennett, Li Jin, Momiao Xiong
2018 Frontiers in Genetics  
We will introduce independence of cause and mechanism (ICM) as a basic principle for causal inference, algorithmic information theory and additive noise model (ANM) as major tools for bivariate causal  ...  To further evaluate their performance for causal inference, the ANM will be applied to the construction of gene regulatory networks.  ...  ACKNOWLEDGMENTS We sincerely thank two reviewers for their helpful comments to improve the presentation of the paper.  ... 
doi:10.3389/fgene.2018.00347 pmid:30233639 pmcid:PMC6127271 fatcat:qn2ujj6c6fgmfp5oy6witp42l4
« Previous Showing results 1 — 15 out of 87,714 results