Can we make quantitative predictions for relative yield with incomplete knowledge of model parameters?

The interest of this work is to describe a framework to propagate uncertainties in piezoelectric energy harvesters (PEHs). The uncertainties are related to the random error associated to the mathematical model adopted, incomplete knowledge of the model parameters and the randomness nature of the excitation. The framework presented could be employed to conduct Prior and Posterior Robust Stochastic predictions. The prior analysis assumes a known Probability Density Function (PDF) for the uncertain variables while the posterior analysis calculates this PDF by adopting a Bayesian updating technique. The framework is particularized to evaluate the behavior of the Frequency Response Functions (FRFs) in PEHs while its implementation is illustrated by the use of a unimorph PEH. Results reveal the importance to include the model parameters uncertainties in the estimation of the FRFs. In that sense, the present framework constitutes a powerful tool in the robust design and prediction of PEH’s performance.

Download Full-text

TOWARDS QUANTITATIVE FORECASTING OF SPECIES YIELDS WITH INCOMPLETE INFORMATION ON MODEL PARAMETERS

10.1101/2021.03.25.437089 ◽

2021 ◽

Author(s):

Hugo Fort

Keyword(s):

Incomplete Information ◽

Relative Abundance ◽

Environmental Science ◽

Interspecific Interactions ◽

Model Parameters ◽

Generalized Equations ◽

Ecological Communities ◽

Incomplete Knowledge ◽

The Absolute ◽

Common Situation

Predicting both the absolute and the relative abundance of species in a spatial patch is of paramount interest in areas like, agriculture, ecology and environmental science. The linear Lotka-Volterra generalized equations (LLVGE) serve for describing the dynamics of communities of species connected by negative as well as positive interspecific interactions. Here we particularize these LLVGE to the case of single trophic ecological communities, like mixtures of plants, with S >2 species. Thus, by estimating the LLVGE parameters from the yields in monoculture and biculture experiments, the LLVGE are able to produce decently accurate predictions for species yields. However, a common situation we face is that we don't know all the parameters appearing in the LLVGE. Indeed, for large values of S, only a fraction of the experiments necessary for estimating the model parameters is commonly carried out. We then analyze which quantitative predictions are possible with an incomplete knowledge of the parameters.

Download Full-text

Reasonable choices for material constants in seismic modeling

Geophysics ◽

10.1190/1.1443488 ◽

1993 ◽

Vol 58 (7) ◽

pp. 978-986

Author(s):

Joseph H. Rosenbaum

Keyword(s):

Transverse Isotropy ◽

Earth Model ◽

Model Parameters ◽

Seismic Modeling ◽

Medium Theory ◽

Long Wavelength ◽

Incomplete Knowledge ◽

The Earth ◽

Default Options ◽

Minimal Information

In exploration geophysics, the seismic response is often modeled with the assumption that the earth consists of homogeneous formations that may exhibit transverse isotropy and moderate, “constant Q” attenuation. The geophysicist usually has only incomplete knowledge of the formation characteristics and must make educated guesses at the unknown elastic and absorption parameters. An extension of the long‐wavelength‐equivalent‐medium theory to the anelastic case has been used to derive default options and stability criteria, which require minimal information from the geophysicist, appear reasonable for many earth materials and reduce to a proper description in the case of isotropy. A very simple earth model is used to demonstrate that parasitic modes are excited and the computations can become unstable when the assumed anelastic model parameters violate some stability condition or are inconsistent.

Download Full-text

Quantitative predictions from competition theory with an incomplete knowledge of model parameters tested against experiments across diverse taxa

Ecological Modelling ◽

10.1016/j.ecolmodel.2017.11.002 ◽

2018 ◽

Vol 368 ◽

pp. 104-110 ◽

Cited By ~ 8

Author(s):

Hugo Fort

Keyword(s):

Model Parameters ◽

Incomplete Knowledge ◽

Competition Theory

Download Full-text

Instrumental and Ideological Union Commitment: Longitudinal Assessment of Construct Validity

European Journal of Psychological Assessment ◽

10.1027//1015-5759.17.2.98 ◽

2001 ◽

Vol 17 (2) ◽

pp. 98-111 ◽

Cited By ~ 1

Author(s):

Anders Sjöberg ◽

Magnus Sverke

Keyword(s):

Construct Validity ◽

Temporal Stability ◽

Strong Support ◽

Internal Consistency Reliability ◽

Measurement Model ◽

Two Dimensions ◽

Model Parameters ◽

Longitudinal Assessment ◽

Union Commitment ◽

Union Participation

Summary: Previous research has identified instrumentality and ideology as important aspects of member attachment to labor unions. The present study evaluated the construct validity of a scale designed to reflect the two dimensions of instrumental and ideological union commitment using a sample of 1170 Swedish blue-collar union members. Longitudinal data were used to test seven propositions referring to the dimensionality, internal consistency reliability, and temporal stability of the scale as well as postulated group differences in union participation to which the scale should be sensitive. Support for the hypothesized factor structure of the scale and for adequate reliabilities of the dimensions was obtained and was also replicated 18 months later. Tests for equality of measurement model parameters and test-retest correlations indicated support for the temporal stability of the scale. In addition, the results were consistent with most of the predicted differences between groups characterized by different patterns of change/stability in union participation status. The study provides strong support for the construct validity of the scale and indicates that it can be used in future theory testing on instrumental and ideological union commitment.

Download Full-text

Representation of bolted joints in a structure using finite element modelling and model updating

JOURNAL OF MECHANICAL ENGINEERING AND SCIENCES ◽

10.15282/jmes.14.3.2020.15.0560 ◽

2020 ◽

Vol 14 (3) ◽

pp. 7141-7151 ◽

Cited By ~ 1

Author(s):

R. Omar ◽

M. N. Abdul Rani ◽

M. A. Yunus

Keyword(s):

Finite Element ◽

Dynamic Behaviour ◽

Model Updating ◽

Complex Structure ◽

Bolted Joints ◽

Model Parameters ◽

Fe Model ◽

Bolted Joint ◽

Fe Modelling ◽

Joint Structure

Efficient and accurate finite element (FE) modelling of bolted joints is essential for increasing confidence in the investigation of structural vibrations. However, modelling of bolted joints for the investigation is often found to be very challenging. This paper proposes an appropriate FE representation of bolted joints for the prediction of the dynamic behaviour of a bolted joint structure. Two different FE models of the bolted joint structure with two different FE element connectors, which are CBEAM and CBUSH, representing the bolted joints are developed. Modal updating is used to correlate the two FE models with the experimental model. The dynamic behaviour of the two FE models is compared with experimental modal analysis to evaluate and determine the most appropriate FE model of the bolted joint structure. The comparison reveals that the CBUSH element connectors based FE model has a greater capability in representing the bolted joints with 86 percent accuracy and greater efficiency in updating the model parameters. The proposed modelling technique will be useful in the modelling of a complex structure with a large number of bolted joints.

Download Full-text

A Note on Confidence Intervals and Model Specification

Marketing ZFP ◽

10.15358/0344-1369-2019-4-33 ◽

2019 ◽

Vol 41 (4) ◽

pp. 33-42

Author(s):

Thomas Otter

Keyword(s):

Confidence Intervals ◽

Generalized Linear Model ◽

Statistical Information ◽

Regression Coefficients ◽

Model Specification ◽

Model Parameters ◽

Exploratory Research ◽

Empirical Calibration ◽

Credible Intervals ◽

Model Structures

Empirical research in marketing often is, at least in parts, exploratory. The goal of exploratory research, by definition, extends beyond the empirical calibration of parameters in well established models and includes the empirical assessment of different model specifications. In this context researchers often rely on the statistical information about parameters in a given model to learn about likely model structures. An example is the search for the 'true' set of covariates in a regression model based on confidence intervals of regression coefficients. The purpose of this paper is to illustrate and compare different measures of statistical information about model parameters in the context of a generalized linear model: classical confidence intervals, bootstrapped confidence intervals, and Bayesian posterior credible intervals from a model that adapts its dimensionality as a function of the information in the data. I find that inference from the adaptive Bayesian model dominates that based on classical and bootstrapped intervals in a given model.

Download Full-text