Nonlinear data

The analysis of nonlinear data is covered in the following papers. 

Zielinski, T. J. Allendoerfer, R. D. Least Squares Litting of Nonlinear Data in the Undergraduate Laboratory, /. Chem. Educ. 1997, 74, 1001-1007. 

As mentioned previously, most agrochemicals do not exhibit linear degradation patterns. As a result, Hamaker proposed another variation of the linear-fit equation that allows better description of nonlinear data sets ... 

Suppose that the actual behavior of temperature versus enthalpy is known and is highly nonlinear, as shown in Figure 19.4. How can the nonlinear data be linearized so that the construction of composite curves and the problem table algorithm can be performed Figure 19.4 shows the nonlinear streams being represented by a series of linear segments. The linearization of the hot streams should... 

The ability of ANNs to model nonlinear data is often crucial. Antoniewicz, Stephanopoulos, and Kelleher have studied the use of ANNs in the estimation of physiological parameters relevant to endocrinology and metabolism.9... 

In principle, in the absence of noise, the PLS factor should completely reject the nonlinear data by rotating the first factor into orthogonality with the dimensions of the x-data space which are spawned by the nonlinearity. The PLS algorithm is supposed to find the (first) factor which maximizes the linear relationship between the x-block scores and the y-block scores. So clearly, in the absence of noise, a good implementation of PLS should completely reject all of the nonlinearity and return a factor which is exactly linearly related to the y-block variances. (Richard Kramer)... 

Figure 63-1 Linear and nonlinear data. Figure 63-la Even when the overall trend of the data is to follow a straight line none of the data points meet the strict criterion of having the test results strictly proportional to the analyte concentration. Figure 63-lb shows that for nonlinear data there are systematic departures from the straight line as well as random departures.

In both the linear and the nonlinear cases the total variation of the residuals is the sum of the random error, plus the departure from linearity. When the data is linear, the variance due to the departure from nonlinearity is effectively zero. For a nonlinear set of data, since the X-difference between adjacent data points is small, the nonlinearity of the function makes minimal contribution to the total difference between adjacent residuals and most of that difference contributing to the successive differences in the numerator of the DW calculation is due to the random noise of the data. The denominator term, on the other hand, is dependent almost entirely on the systematic variation due to the curvature, and for nonlinear data this is much larger than the random noise contribution. Therefore the denominator variance of the residuals is much larger than the numerator variance when nonlinearity is present, and the Durbin-Watson statistic reflects this by assuming a value less than 2. 

Figure 64-2 A graphic illustration of the behavior of nonlinear data. Figure 64-2a - Nonlinear data does not surround a straight line evenly. Figure 64-2b - The residuals from nonlinear data are not spread out around zero.

The improvement in the fit from the quadratic polynomial applied to the nonlinear data indicated that the square term was indeed an important factor in fitting that data. In fact, including the quadratic term gives well-nigh a perfect fit to that data set, limited only by the computer truncation precision. The coefficient obtained for the quadratic term is comparable in magnitude to the one for linear term, as we might expect from the amount of curvature of the line we see in Anscombe s plot [7], The coefficient of the quadratic term for the normal data, on the other hand, is much smaller than for the linear term. 

The performance statistics, the SEE and the correlation coefficient show that including the square term in the fitting function for Anscombe s nonlinear data set gives, as we noted above, essentially a perfect fit. It is clear that the values of the coefficients obtained are the ones he used to generate the data in the first place. The very large /-values of the coefficients are indicative of the fact that we are near to having only computer round-off error as operative in the difference between the data he provided and the values calculated from the polynomial that included the second-degree term. 

In this section we will explore the applicability of different techniques for solving the nonlinear data reconciliation problem. 

Islam, K., Weiss, G., and Romagnoli, J. A. (1994). Nonlinear data reconciliation for an industrial pyrolysis... 

Finally, yet another issue enters into the interpretation of nonlinear Arrhenius plots of enzyme-catalyzed reactions. As is seen in the examples above, one typically plots In y ax (or. In kcat) versus the reciprocal absolute temperature. This protocol is certainly valid for rapid equilibrium enzymes whose rate-determining step does not change throughout the temperature range studied (and, in addition, remains rapid equilibrium throughout this range). However, for steady-state enzymes, other factors can influence the interpretation of the nonlinear data. For example, for an ordered two-substrate, two-product reaction, kcat is equal to kskjl ks + k ) in which ks and k are the off-rate constants for the two products. If these two rate constants have a different temperature dependency (e.g., ks > ky at one temperature but not at another temperature), then a nonlinear Arrhenius plot may result. See Arrhenius Equation Owl Transition-State Theory van t Hoff Relationship... 

Poly(3-alkyl-a-thiophene) systems show significant third-order nonlinear susceptibilities ( ) Though, oligothiophenes have been studied for their third-order susceptibilities, accurate third-order optical nonlinearity data obtained by degenerate four-wave mixing or electric-field-induced second harmonic generation (EFISH) are difficult to attain reliably on samples with poor solubility characteristics (92MM1901). 

In addition to being easier to fit than the hyperbolic Michaelis-Menten equation, Lineweaver-Burk graphs clearly show differences between types of enzyme inhibitors. This will be discussed in Section 4.5. However, Lineweaver-Burk equations have their own distinct issues. Nonlinear data, possibly indicating cooperative multiunit enzymes or allosteric effects, often seem nearly linear when graphed according to a Lineweaver-Burk equation. Said another way, the Lineweaver-Burk equation forces nonlinear data into a linear relationship. Variations of the Lineweaver-Burk equation that are not double reciprocal relationships include the Eadie-Hofstee equation7 (V vs. V7[S]) (Equation 4.14) and the Hanes-Woolf equation8 ([S]/V vs. [S]) (Equation 4.15). Both are... 

Nordstrom A, O Mai lie G, Qin C, Siuzdak G (2006) Nonlinear data alignment for UPLC-MS and HPLC-MS based metabolomics quantitative analysis of endogenous and exogenous metabolites in human serum. Anal Chem 78 3289-3295... 

Using artificial neural networks to develop calibration models is also possible. The reader is referred to the literature [68-70] for further information. Neural networks are commonly utilized when the data set maintains a large degree of nonlinearity. Additional multivariate approaches for nonlinear data are described in the literature [71, 72],... 

A key factor in modeling is parameter estimation. One usually needs to fit the established model to experimental data in order to estimate the parameters of the model both for simulation and control. However, a task so common in a classical system is quite difficult in a chaotic one. The sensitivity of the system s behavior to the initial conditions and the control parameters makes it very hard to assess the parameters using tools such as least squares fitting. However, efforts have been made to deal with this problem [38]. For nonlinear data analysis, a combination of statistical and mathematical tests on the data to discern inner relationships among the data points (determinism vs. randomness), periodicity, quasiperiodicity, and chaos are used. These tests are in fact nonparametric indices. They do not reveal functional relationships, but rather directly calculate process features from time-series records. For example, the calculation of the dimensionality of a time series, which results from the phase space reconstruction procedure, as well as the Lyapunov exponent are such nonparametric indices. Some others are also commonly used ... 

EXAAiPLJE iJ Linear Curve-Fitting of Nonlinear Data... 

Wongrat, M., Srinophakun, T. Srinophakun, P., 2005. Modified genetic algorithm for nonlinear data reconciliation. Comput. Chem. Eng. 29, 1059. 

Figure 2. Fluorescence quenching of 15 ppm soil fulvic acid at 0.1 molar ionic strength titrated with Cu(II) ion (O) pH 5, (V) pH 6, and ( ) pH 7. The solid lines (—) illustrate the calculated intensity values from the nonlinear data treatment approach.

Careful examination reveals that the modified Stem-Volmer equation is mathematically identical to the original nonlinear model developed by Ryan and Weber (22). Fluorescence quenching curves for Cu -FA and application of the modified Stem-Volmer data treatment to the experimental information are shown in figure 2. Since the nonlinear data treatment and the modified Stem-Volmer equations are algebraically identical, their ability to fit experimental data and provide meaningful parameters is the same. 

---