On detecting the optimal structure of a neural network under strong statistical features in errors

DOI10.1111/J.1467-9892.2010.00693.XMaRDI QIDQ4979103zbMATH OpenOpenAlexFDO

Authors Nikos S. Thomaidis, George D. Dounias

Publication date 16 June 2014

Published in Journal of Time Series Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1111/j.1467-9892.2010.00693.x

zbMATH Keywords

artificial neural networksheteroskedasticitysimulationGARCH modelswild bootstrapLagrange multiplier testsneglected nonlinearity tests

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Applications of statistics to biology and medical sciences; meta analysis (62P10) Sequential statistical analysis (62L10) Non-Markovian processes: hypothesis testing (62M07) Neural nets and related approaches to inference from stochastic processes (62M45)

Recommendations

• scientific article; zbMATH DE number 1368813
• Neural networks and statistical inference: seeking robust and efficient learning
• scientific article; zbMATH DE number 67623
• The strong consistency of error probability estimates in nn discrimination
• An improved determination approach to the structure and parameters of dynamic structure-based neural networks
• Probabilistic robustness estimates for feed-forward neural networks
• A statistical model of neural network learning via the Cramer-Rao lower bound

Cites work

• scientific article; zbMATH DE number 4090638 (Why is no real title available?)
• scientific article; zbMATH DE number 1168350 (Why is no real title available?)
• Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation
• Bootstrap and wild bootstrap for high dimensional linear models
• Bootstrap procedures under some non-i.i.d. models
• Bootstrapping autoregressions with conditional heteroskedasticity of unknown form
• Conditional Heteroskedasticity in Asset Returns: A New Approach
• Controlling the finite sample significance levels of heteroskedasticity-robust tests of several linear restrictions on regression coefficients
• Diagnostic Checking in a Flexible Nonlinear Time Series Model
• Generalized autoregressive conditional heteroscedasticity
• Hypothesis Testing When a Nuisance Parameter is Present Only Under the Alternative
• Jackknife, bootstrap and other resampling methods in regression analysis
• Multilayer feedforward networks are universal approximators
• On the application of robust, regression-based diagnostics to models of conditional means and conditional variances
• Testing for neglected nonlinearity in time series models. A comparison of neural network methods and alternative tests
• The wild bootstrap and heteroskedasticity-robust tests for serial correlation in dynamic regression models
• The wild bootstrap, tamed at last

Cited in

(2)

• Effectiveness of neural networks to regression with structural changes
• A goodness-of-fit test based on neural network sieve estimators

This page was built for publication: On detecting the optimal structure of a neural network under strong statistical features in errors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4979103)