Residuals scatterplot

Fig. 3. Scatterplots of the Nh residual dipolar couplings of A131A measured in 2, 4, 6, or 8 M urea (y-axes) plotted against the same couplings measured in the absence of urea (x-axis) ris the Pearson correlation coefficient. Alignment was achieved with alkyl PEG bicelles (Ackerman and Shortle, 2002.)...

Fig. 4. Scatterplots of the Nh residual dipolar couplings from three different denatured states of staphylococcal nuclease plotted against each other. (A) Wild-type, full-length nuclease in 4 M urea (y-axis) versus A131A in buffer (x-axis). (B) Wild-type, full-length nuclease denatured by acid (25 mM citrate, pH 3.0) (y-axis) versus A131A in buffer (x-axis).

Regression analysis assumes that all error components are independent, have a mean of zero and have the same variance throughout the range of POM values. Through an examination of residuals, serious violations in these assumptions can usually be detected. The standardized residuals for each of the fitted models were plotted against the sequence of cases in the file and this scatterplot was examined visually for any abnormalities (10, 14). 

All data should be inspected by calculating variable means, standard deviations, skewness and similar parameters. Even better is to plot the data in all potentially useful ways, in particular various kinds of scatterplots of, for example, intervariable correlations and residuals. These methods will not be penetrated further in this paper because they can be found easily in any... 

There are several approaches to population model development that have been discussed in the literature (7, 9, 15-17). The traditional approach has been to make scatterplots of weighted residuals versus covariates and look at trends in the plot to infer some sort of relationship. The covariates identified with the scatterplots are then tested against each of the parameters in a population model, one covariate at a time. Covariates identified are used to create a full model and the final irreducible, given the data, is obtained by backward elimination. The drawback of this approach is that it is only valid for covariates that act independently on the pharmacokinetic (PK) or pharmacokinetic/pharmacodynamic (PK/PD) parameters, and the understanding of the dimensionality of the covariate diata is not taken into account. 

FIGURE 14.2 Scatterplots of partial residuals of clearance [CL (L/h)] of a drug versus (A) creatinine clearance [CLCR (mL/min)] and (B) age (yr) from multiple regression analysis CL (L/h) versus (C) CLCR (mL/min) and (D) age (yr) from GAM analysis. The same scale is used for the ordinate in each plot so that the relative importance of each covariate can be compared. 

Base Model Choice. The choice was a steady-state one-compartment model with first-order absorption or a steady-state oral two-compartment model with first-order absorption. The disposition parameters were to be expressed in volume and clearance. Intersubject variability and residual error were also to be assessed. The best-fit model, using the software NONMEM, was to be the final base model. The criteria for accepting the NONMEM base model included (a) improved fitting of the diagnostic scatterplots (observed vs. predicted concentration, residual/weighted residual vs. predicted concentration... 

Fig. 4. Scatterplots and histograms of the spatial distribution of acceptor or donor sites in ligand molecules about different functional groups of active site residues in ligand-protein crystal structures (PDB) (Adapted from [65]). Note that the distributions are more smeared when compared with those in Fig. 3...

Figure 2.17 Scatterplot of residuals for outlier corrected VARX Z) model of the dealkylation plant...

Least-Squares The method of least-squares is a criterion for fitting a specified model to observed data, in which the parameters of the model are adjusted so as to minimize the sum of the squares of the residuals. For example, it is the most commonly used method of defining a straight line through a set of data points on a scatterplot. 

---