scholarly journals A two-stage non-linear program for optimal electrical grid power balance under uncertainty

Author(s):  
Dzung Phan ◽  
Soumyadip Ghosh
2008 ◽  
Vol 3 (1) ◽  
Author(s):  
Shaik Basha ◽  
Z.V.P. Murthy ◽  
B. Jha

A comparison between linear least-squares method and non-linear regression method of the widely used equilibrium isotherms (Langmuir, Freundlich and Redlich-Peterson) for the sorption of Cr(VI) onto Cystoseira indica, which was chemically-modified by cross-linking with epichlorohydrin (CB1, CB2), or oxidized by potassium permanganate (CB3), or only washed by distilled water (RB) was examined. The biosorption equilibriums were established in about 2 h and the maximum removal was observed at pH 3.0 with solid to liquid ratio of 0.05 g/l. The four different linearized forms of Langmuir isotherms are also discussed. Langmuir isotherm parameters obtained from the four Langmuir linear equations are different but they are the same by using non-linear Langmuir equation. The best-fitting isotherms are Langmuir and Redlich-Peterson. The present investigation showed that the non-linear method is the more appropriate method to determine the isotherm parameters. A design procedure was proposed using the Langmuir isotherm to design a two stage sorption system to minimize the amount of biomass required for the treatment of Cr(VI) solution using Cystoseira indica. A two stage sorption system reduced the amount of biomass required by 51.2, 50.7, 51.1 and 51.3%, for CB1, CB2, CB3 and RB, respectively, to achieve the required amount of Cr(VI) removal for any solution volume.


2002 ◽  
Vol 75 (7) ◽  
pp. 502-516 ◽  
Author(s):  
Hag Seong Kim ◽  
Kyo-Il Lee ◽  
Young Man Cho

Biostatistics ◽  
2019 ◽  
Vol 21 (4) ◽  
pp. 676-691
Author(s):  
Klaus Kähler Holst ◽  
Esben Budtz-Jørgensen

Summary Applications of structural equation models (SEMs) are often restricted to linear associations between variables. Maximum likelihood (ML) estimation in non-linear models may be complex and require numerical integration. Furthermore, ML inference is sensitive to distributional assumptions. In this article, we introduce a simple two-stage estimation technique for estimation of non-linear associations between latent variables. Here both steps are based on fitting linear SEMs: first a linear model is fitted to data on the latent predictor and terms describing the non-linear effect are predicted by their conditional means. In the second step, the predictions are included in a linear model for the latent outcome variable. We show that this procedure is consistent and identifies its asymptotic distribution. We also illustrate how this framework easily allows the association between latent variables to be modeled using restricted cubic splines, and we develop a modified estimator which is robust to non-normality of the latent predictor. In a simulation study, we compare the proposed method to MLE and alternative two-stage estimation techniques.


Sign in / Sign up

Export Citation Format

Share Document