Regression Analysis Framework

The regression analysis fi amework, shown in Fig. 3.1, is an iterative procedure that seeks to determine the best model for the data. Before the procedure can be started, three things must be determined  

Data What information is available about the system of interest and which variables can be measured If no data sets are readily available, then it may be necessary to perform experiments to obtain the required data (see Chap. 4 Design of Experiments for further information). 

Model What model (relationship) will be fit How many parameters will be considered The selection of an appropriate model is neither a trivial nor an easy task. Luckily in many processes applications, there may be some idea of what the model should be based on a theoretical analysis of the system. 

Regression Method Which method will be used to determine the model parameters The selection of the correct method will impact the validity of the model obtained and what type of analysis can be performed. 

Once these three aspects have been determined, the regression framework consists 

---

The sample involves a regression analysis framework that estimates the effect on price of the number of generic products of the same molecules. Danzon and Chao (2000) also control for the number of therapeutic substitutes, hrst-mover advantages, molecule age, and several other factors. 

Therefore no longer qualitative statements are cast into a numerical framework but easily measurable values are linked to obtain information on complex stability or bond energies. Thus, by linear regression analysis, two new parameters are obtained which -once they are known for sufficiently many different metal ions, both essential and non-essential ones - in turn can be linked to this biochemical property of essentiality. Electrochemical ligand parameters for different complexes of the same metal ion are correlated... 

Differences in the Si MAS NMR shifts of framework silicon atoms located on crystallographically inequivalent T-sites are mainly caused by different local geometries of Si04 tetrahedra. Empirical correlations and theoretical considerations yielded that the Si NMR shifts, 65,-, of Si( wAl) units are linearly correlated with the mean value, a, of the four Si-O-T bond angles. With linear regression analysis, quantitative relationship between the values of 6si and d, sec a,sin (a/2) and cos a/(cos a-1) have been found [1,71-76]. For Si(4Al) units in sodalite,... 

J0RGENSEN, E., Framework program for non-linear regression analysis with tests, Danish Institute of Computing Machinery, November 1963. 

In contrast to the polynomial model, the multiexponential model is not quasilinear. This makes the determination of the parameters p more complicated. Then iterative methods have to be employed in order to approach a solution. This issue falls into the framework of nonlinear regression analysis. For more details, see [5]. 

Chapter 2 (Statistical Space for Multivariate Correlations) Aims to prepare the conceptual-computational ground for correlating chemical structure with biological activity by the celebrated quantitative stractuie-activity relationships (QSARs). Additionally, the fundamental statistical advanced frameworks are detailed to best understand the classical multilinear regression analysis generalized by an algebraic (in quantum Hilbert space) reformulation in terms of data vectors and orthogonal conditions (explained in see Chapter 3). 

In organic chemistry, decomposition of molecules into substituents and molecular frameworks is a natural way to characterize molecular structures. In QSAR, both the Hansch-Fujita " and the Free-Wilson classical approaches are based on this decomposition, but only the second one explicitly accounts for the presence or the absence of substituent(s) attached to molecular framework at a certain position. While the multiple linear regression technique was associated with the Free-Wilson method, recent modifications of this approach involve more sophisticated statistical and machine-learning approaches, such as the principal component analysis and neural networks. ... 

Another classification method is the discriminant function analysis, which instead of regression as the mathematical framework is based on the same principle as the MANOVA. Whereas the MANOVA deals with whether a number of groups differ significantly with respect to differences on a number of dependent variables, the discriminant function analysis deals with whether a linear combination of predictor... 

In weighted, least-squares analysis, it is assumed that the variance of the individual data points may be variable. In order to reduce this problem to the standard linear regression framework, a weight, w is introduced for each observation that reflects how good the data point is. Thus, the regression model for weighted, least-squares is... 

---