Prediction Intervals for Artificial Neural Networks

DOI10.2307/2965723zbMath1090.62559MaRDI QIDQ4366256

A. Adam Ding, J. T. Gene Hwang

Publication date: 1997

Full work available at URL: https://doi.org/10.2307/2965723

zbMATH Keywords

Model selection; Asymptotic properties; Identifiability; Electric load forecasting; Jackknife estimate of coverage probability; Statistical nonlinear regression

Mathematics Subject Classification ID

62P99: Applications of statistics

62M45: Neural nets and related approaches to inference from stochastic processes

Related Items

Improving Reliability Estimation for Individual Numeric Predictions: A Machine Learning Approach, Forecasting Macroeconomic Variables Using Neural Network Models and Three Automated Model Selection Techniques, Extremely randomized neural networks for constructing prediction intervals, Epicasting: an ensemble wavelet neural network for forecasting epidemics, Designing neural networks for modeling biological data: a statistical perspective, Comparison of the performance of multi-layer perceptron and linear regression for epidemiological data, Statistical aspects of multilayer perceptrons under data limitations, Efficient Monte Carlo computation of Fisher information matrix using prior information, Boosting GARCH and neural networks for the prediction of heteroskedastic time series, Forecasting nonlinear time series with neural network sieve bootstrap, Robust prediction interval estimation for Gaussian processes by cross-validation method, Gradient conjugate priors and multi-layer neural networks, A note on the identifiability of the conditional expectation for the mixtures of neural networks, Modeling time-varying parameters using artificial neural networks: a GARCH illustration, Testing for parameter stability in nonlinear autoregressive models, Unnamed Item, MODELING MULTIPLE REGIMES IN FINANCIAL VOLATILITY WITH A FLEXIBLE COEFFICIENT GARCH(1,1) MODEL