Related Experiment Video
Updated: Jun 11, 2026
09:17
Surrogate Model Development for Digital Experiments in Welding
Published on: March 28, 2025
Online Prediction Under Model Uncertainty via Dynamic Model Averaging: Application to a Cold Rolling Mill
Adrian E Raftery1, Miroslav Kárný, Pavel Ettler
1University of Washington, Seattle, WA 98195-4322, ( raftery@u.washington.edu ).
Summary
Dynamic Model Averaging (DMA) offers robust online prediction by dynamically selecting the best model, even when the optimal model changes over time. This approach minimizes the cost of model uncertainty, outperforming single models in complex scenarios.
Area of Science:
- Statistics
- Machine Learning
- Control Engineering
Background:
- Online prediction requires selecting the best model amidst uncertainty.
- Existing methods may struggle when the optimal model shifts over time.
Purpose of the Study:
- To develop a novel method, Dynamic Model Averaging (DMA), for online prediction under model uncertainty.
- To allow the optimal prediction model to adapt and change over time.
Main Methods:
- DMA combines state-space models for parameters with Markov chain models for the correct model.
- Both models are specified using forgetting factors for parsimony.
- DMA is a recursive implementation of Bayesian model averaging when models are static.
Main Results:
- DMA quickly converged to the best model when one was clearly superior, with minimal cost from model uncertainty.
- DMA effectively minimized the penalty for model uncertainty, even with a large number of models.
- DMA provided better predictions than the best single model during initial, difficult stages of a cold rolling mill process.
Conclusions:
- DMA is an effective method for online prediction with dynamic model uncertainty.
- The approach offers significant advantages in complex industrial applications like cold rolling mills.
- DMA demonstrates strong performance in recovering both constant and time-varying parameters and model specifications.
Related Concept Videos
01:03Prediction Intervals
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
The...
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
The...
01:24One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
On...
01:22Estimating Population Mean with Unknown Standard Deviation
In practice, we rarely know the population standard deviation. In the past, when the sample size was large, this did not present a problem to statisticians. They used the sample standard deviation s as an estimate for σ and proceeded as before to calculate a confidence interval with close enough results. However, statisticians ran into problems when the sample size was small. A small sample size caused inaccuracies in the confidence interval.
William S. Gosset (1876–1937) of the Guinness...
William S. Gosset (1876–1937) of the Guinness...
01:20Maxwell-Boltzmann Distribution: Problem Solving
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
01:16Estimating Population Mean with Known Standard Deviation
To construct a confidence interval for a single unknown population mean μ, where the population standard deviation is known, we need sample mean as an estimate for μ and we need the margin of error. Here, the margin of error (EBM) is called the error bound for a population mean (abbreviated EBM). The sample mean is the point estimate of the unknown population mean μ.
The confidence interval estimate will have the form as follows:
(point estimate - error bound, point estimate + error bound)
The...
The confidence interval estimate will have the form as follows:
(point estimate - error bound, point estimate + error bound)
The...
00:59Propagation of Uncertainty from Random Error
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...