A5054851001- Statistical Methods and Inference
- Quantum Chromodynamics and Particle Interactions
- High-Energy Particle Collisions Research
- Particle physics theoretical and experimental studies
- Advanced Statistical Methods and Models
- Statistical Methods and Bayesian Inference
- Additive Manufacturing and 3D Printing Technologies
- Granular flow and fluidized beds
- Lignin and Wood Chemistry
- Catalysis for Biomass Conversion
- Catalysis and Hydrodesulfurization Studies
- Fault Detection and Control Systems
- Bayesian Methods and Mixture Models
- Rheology and Fluid Dynamics Studies
- Fluid Dynamics and Heat Transfer
- Particle Dynamics in Fluid Flows
- Probabilistic and Robust Engineering Design
- Textile materials and evaluations
University of Colorado Boulder
2020-2024
University of Colorado System
2024
University of Delaware
2018-2020
Center for Innovation
2018
Bayesian model averaging is a practical method for dealing with uncertainty due to specification. Use of this technique requires the estimation probability weights. In work, we revisit derivation estimators these Kullback-Leibler divergence as starting point leads naturally number alternative information criteria suitable weight estimation. We explore three such criteria, known statistics literature before, in detail: analog Akaike criterion which call BAIC, predictive criterion, and...
Biorefinery and paper pulping lignins, referred hereto as technical contain condensed C–C interunit linkages. These robust linkages with higher bond dissociation energies are difficult to disrupt under hydrogenolysis conditions, which generally used for cleaving C–O bonds of native lignin in biomass or model linked compounds. Thus, selective cleavage release aromatic monomers high-value applications is a challenge. We report an effective catalytic system cleave such selectively mild...
Model averaging is a useful and robust method for dealing with model uncertainty in statistical analysis. Often, it to consider data subset selection at the same time, which criteria are used compare models across different subsets of data. Two have been proposed literature how should be weighted. We two closely unified treatment based on Kullback-Leibler divergence conclude that one them subtly flawed will tend yield larger uncertainties due loss information. Analytical numerical examples provided.
When a pair of wetted particles undergoes an oblique collision their liquid layers overlap and cause lubrication capillary forces. The relative motion in the direction normal to sphere surfaces contact region is then arrested, can either remain agglomerated, experience rapid rebound, or rotate slowly separate as result centrifugal Collision laws for wet are presented, conditions leading different outcomes determined.
Bayesian model averaging is a practical method for dealing with uncertainty due to specification. Use of this technique requires the estimation probability weights. In work, we revisit derivation estimators these Kullback-Leibler divergence as starting point leads naturally number alternative information criteria suitable weight estimation. We explore three such criteria, known statistics literature before, in detail: analogue Akaike criterion which call BAIC, predictive (BPIC), and...
Model averaging is a useful and robust method for dealing with model uncertainty in statistical analysis. Often, it to consider data subset selection at the same time, which criteria are used compare models across different subsets of data. Two have been proposed literature how should be weighted. We two closely unified treatment based on Kullback-Leibler divergence conclude that one them subtly flawed will tend yield larger uncertainties due loss information. Analytical numerical examples provided.