Simulation: Sensitivity Analysis and Optimization Through Regression Analysis and Experimental Design

1996 ◽  
pp. 429-441 ◽  
Author(s):  
Jack P. C. Kleijnen
Keyword(s):  
Sensitivity Analysis ◽  
Regression Analysis ◽  
Experimental Design

scholarly journals Value of Variation of End-Tidal Carbon Dioxide for Predicting Fluid Responsiveness During the Passive Leg Raising Test in Patients with Mechanical Ventilation: A Systematic Review and Meta-Analysis

2021 ◽  
Author(s):  
Haijun Huang ◽  
Chenxia Wu ◽  
Qinkang Shen ◽  
Yixin Fang ◽  
Hua Xu
Keyword(s):  
Carbon Dioxide ◽  
Mechanical Ventilation ◽  
Sensitivity Analysis ◽  
Regression Analysis ◽  
Fluid Responsiveness ◽  
Meta Analysis ◽  
End Tidal Carbon Dioxide ◽  
Meta Regression ◽  
Meta Regression Analysis ◽  
End Tidal

Abstract Background: The variation of end-tidal carbon dioxide(ΔEtCO2) has have been extensively studied with respect to its value in predicting fluid responsiveness, but the results are conflicting. This meta-analysis aimed to explore the value of ΔEtCO2 for predicting fluid responsiveness during the passive leg raising(PLR) test in patients with mechanical ventilation. Methods: PubMed, Embase, and Cochrane Central Register of Controlled Trials were searched up to November 2021. The diagnostic odds ratio (DOR), sensitivity, and specificity were calculated. The summary receiver operating characteristic curve was estimated, and the area under the curve (AUROC) was calculated. We performed meta-regression analysis for heterogeneity exploration and sensitivity analysis for the publication bias.Results: Overall, 298 patients were included in this review, of whom 149 (50%) were fluid responsive. The cutoff values of ΔEtCO2 varied across studies, ranging from 5% to 5.8% or absolute increase 2mmHg. Heterogeneity between studies was assessed with an overall Q = 4.098, I2 = 51%, and P = 0.064. The pooled sensitivity and specificity for the overall population were 0.79 (95% CI: 0.72–0.85) and 0.90 (95% CI: 0.77–0.96), respectively. The DOR was 35 (95% CI: 12–107) (Fig. 4). The pooled AUROC was 0.81 (95% CI: 0.77–0.84). On meta-regression analysis, the number of patients was sources of heterogeneity. The sensitivity analysis showed that the pooled DOR ranged from 21 to 140 and the pooled AUC ranged from 0.92 to 0.96 when one study was omitted.Conclusions: This study was the first meta-analysis to evaluate the diagnostic accuracy of ΔEtCO2 in predicting fluid responsiveness during PLR test in patients with mechanical ventilation. This study confirmed that the ΔEtCO2 performed well in predicting fluid responsiveness in patients with mechanical ventilation.

A Sensitivity Analysis for Effective Parameters on 2D Fracture-Network Permeability

2009 ◽  
Vol 12 (03) ◽  
pp. 455-469 ◽  
Author(s):  
Alireza Jafari ◽  
Tayfun Babadagli
Keyword(s):  
Sensitivity Analysis ◽  
Experimental Design ◽  
Fractured Reservoirs ◽  
Fracture Network ◽  
Static Model ◽  
Naturally Fractured Reservoirs ◽  
Single Fracture ◽  
Data Sets ◽  
Fracture Networks ◽  
Fractal Characteristics

Summary Fracture-network mapping and estimation of its permeability constitute two major steps in static-model preparation of naturally fractured reservoirs. Although several different analytical methods were proposed in the past for calculating fracture-network permeability (FNP), different approaches are still needed for practical use. We propose a new and practical approach to estimate FNP using statistical and fractal characteristics of fracture networks. We also provide a detailed sensitivity analysis to determine the relative importance of fracture-network parameters on the FNP in comparison to single-fracture conductivity using an experimental-design approach. The FNP is controlled by many different fracture-network parameters such as fracture length, density, orientation, aperture, and single-fracture connectivity. Five different 2D fracture data sets were generated for random and systematic orientations. In each data set, 20 different combinations of fracture density and length for different orientations were tested. For each combination, 10 different realizations were generated. The length was considered as constant and variable. This yielded a total of 1,000 trials. The FNPs were computed through a commercial discrete-fracture-network (DFN) modeling simulator for all cases. Then, we correlated different statistical and fractal characteristics of the networks to the measured FNPs using multivariable-regression analysis. Twelve fractal (sandbox, box counting, and scanline fractal dimensions) and statistical (average length, density, orientation, and connectivity index) parameters were tested against the measured FNP for synthetically generated fracture networks for a wide range of fracture properties. All cases were above the percolation threshold to obtain a percolating network, and the matrix effect was neglected. The correlation obtained through this analysis using four data sets was tested on the fifth one with known permeability for verification. High-quality match was obtained. Finally, we adopted an experimental-design approach to identify the most-critical parameters on the FNP for different fracture-network types. The results are presented as Pareto charts. It is believed that the new method and results presented in this paper will be useful for practitioners in static-model development of naturally fractured reservoirs and will shed light on further studies on modeling and understanding the transmissibility characteristics of fracture networks. It should be emphasized that this study was conducted on 2D fracture networks and could be extended to 3D models. This, however, requires further algorithm development to use 2D fractal characteristics for 3D systems and/or development of fractal measurement techniques for a 3D system. This study will provide a guideline for this type of research.

scholarly journals Climatic and basin factors affecting the flood frequency curve: PART II – A full sensitivity analysis based on the continuous simulation approach combined with a factorial experimental design

2000 ◽  
Vol 4 (3) ◽  
pp. 483-498 ◽  
Author(s):  
M. Franchini ◽  
A. M. Hashemi ◽  
P. E. O’Connell
Keyword(s):  
Sensitivity Analysis ◽  
Soil Moisture ◽  
Experimental Design ◽  
Probability Distribution ◽  
Flood Frequency ◽  
Rainfall Regime ◽  
Model Parameters ◽  
Rainfall Runoff ◽  
Factorial Experimental Design ◽  
Frequency Curve

Abstract. The sensitivity analysis described in Hashemi et al. (2000) is based on one-at-a-time perturbations to the model parameters. This type of analysis cannot highlight the presence of parameter interactions which might indeed affect the characteristics of the flood frequency curve (ffc) even more than the individual parameters. For this reason, the effects of the parameters of the rainfall, rainfall runoff models and of the potential evapotranspiration demand on the ffc are investigated here through an analysis of the results obtained from a factorial experimental design, where all the parameters are allowed to vary simultaneously. This latter, more complex, analysis confirms the results obtained in Hashemi et al. (2000) thus making the conclusions drawn there of wider validity and not related strictly to the reference set selected. However, it is shown that two-factor interactions are present not only between different pairs of parameters of an individual model, but also between pairs of parameters of different models, such as rainfall and rainfall-runoff models, thus demonstrating the complex interaction between climate and basin characteristics affecting the ffc and in particular its curvature. Furthermore, the wider range of climatic regime behaviour produced within the factorial experimental design shows that the probability distribution of soil moisture content at the storm arrival time is no longer sufficient to explain the link between the perturbations to the parameters and their effects on the ffc, as was suggested in Hashemi et al. (2000). Other factors have to be considered, such as the probability distribution of the soil moisture capacity, and the rainfall regime, expressed through the annual maximum rainfalls over different durations. Keywords: Monte Carlo simulation; factorial experimental design; analysis of variance (ANOVA)

Simulation in Information Systems Research

2005 ◽  
pp. 2508-2513
Author(s):  
Theresa M. Vitolo ◽  
Chris Coulston
Keyword(s):  
Sensitivity Analysis ◽  
Experimental Design ◽  
Simulation Model ◽  
Natural Sciences ◽  
Critical Values ◽  
Dynamic Interactions ◽  
Validation And Verification ◽  
Systems Research ◽  
Information Systems Research ◽  
Mode Of Development

Simulation is a standard research technique of the natural sciences, social sciences, and engineering disciplines. The paradigm of simulation provides an accepted mode of development, validation, and verification by which complex, highly dynamic interactions can be probed and analyzed. The approach enables researchers to phrase experiments in a controlled environment where the concepts, variables, and relationships of the domain can be manipulated. Then, employing standard experimental design techniques, the simulation represents the behavior of the underlying system. The behavior can be analyzed statistically for its regularity and critical values where the dynamics may become unstable. Further, once the simulation model is developed, sensitivity analysis can be done to probe the interdependencies of the elements of the underlying system upon one another.

Applied regression analysis and experimental design

1990 ◽  
Vol 18 (1) ◽  
pp. 90-91
Author(s):  
Jaroslav Mich�lek
Keyword(s):  
Regression Analysis ◽  
Experimental Design

On the Modeling of Educational Systems: II

1976 ◽  
Vol 4 (4) ◽  
pp. 281-298 ◽  
Author(s):  
Robert T. Grauer
Keyword(s):  
Computer Simulation ◽  
Regression Analysis ◽  
Experimental Design ◽  
Model Building ◽  
Social Scientist ◽  
Educational Systems ◽  
Factorial Designs ◽  
Unified Approach ◽  
Simulation Methodology ◽  
The Social

Recent advances in, and acceptance of, computer simulation methodology make direct experimentation possible for the social scientist. This technique can be used to supplement his traditional tools of experimental design, namely regression analysis and factorial designs. In this paper a unified approach to model building is synthesized from these disparate techniques. The capabilities of each are discussed and then combined into a modeling philosophy which can be applied to a variety of educational problems.

scholarly journals Distiller’s dried grains with solubles (Zea mays L.) in feeding sheep on nitrogen balance

2017 ◽  
Vol 38 (6) ◽  
pp. 3807
Author(s):  
Luiz Juliano Valério Geron ◽  
Jocilaine Garcia ◽  
Sílvia Cristina de Aguiar ◽  
Kallynka Samara Martins Coelho ◽  
Ilda De Souza Santos ◽  
...  
Keyword(s):  
Zea Mays ◽  
Body Weight ◽  
Regression Analysis ◽  
Experimental Design ◽  
Nitrogen Balance ◽  
Zea Mays L ◽  
Latin Square ◽  
Experimental Period ◽  
Average Body ◽  
Average Body Weight

The objective of this study was to evaluate the effects of diets supplemented with 0.0, 8.0, 16.0, and 24.0% distiller’s dried grain solubles (DDGS) on nitrogen (N) intake, fecal and urinary N excretion, and N absorption and retention (N balance, NB) by feeding sheep. Four sheep of unidentified race were used, with an average body weight of 23.5 ± 1.5 kg, and housed in metabolism cages. We used a 4 × 4 Latin square design for the experimental design, and each experimental period lasted for 20 days. Data on N intake (NI), fecal N, urinary N, absorbed N, and NB were expressed in g day-1; percentage of NI and grams per kilogram of metabolic weight g (kg0.75)-1 were subjected to analysis of variance (ANOVA) and regression analysis at 5% probability. Inclusion of the different concentrations of DDGS in sheep diets had no effect on NI (mean of 15.11 g animal-1 day-1), nor on fecal and urinary N excretion (mean of 5.16 and 0.16 g animal-1 day-1, respectively). Moreover, DDGS supplementation did not alter NB or N absorption (mean of 9.79 and 9.95 g animal-1 day-1, respectively). Thus, it can be concluded that inclusion of up to 24% of DDGS in feed does not affect NI, fecal and urinary N excretion, and NB in sheep.

Sign in / Sign up

Export Citation Format

Share Document