Graphics data exploration plots

Data from GEOSECS, TTO, BATS, and HOTS and other major oceanographic research projects, such as the WOCE (World Ocean Circulation Experiment) are available online. The GEOSECS, TTO, and WOCE datasets are part of the Java Ocean Atlas, which provides a graphic exploration environment for generating vertical profiles, cross-sections, and property-property plots. Many of the data presented in this text were obtained from this source. 

The experimental procedures for obtaining ECD and NIMS data have been described. Examples of the calculations are given for the various classes of molecules. For each group specific test molecules are provided. The aromatic hydrocarbons and aldehydes are Eql(l/lor 1/2) molecules, CS2 is a Eql(2/2) molecule, haloalkanes are DEC(l) molecules, and the halobenzenes and nitromethane are DEC(2) molecules that dissociate via a molecular ion. A graphical procedure for obtaining parameters from ECD data and the calibration of NIMS data using SF6 and nitrobenzene is presented. The use of multiple electron affinities of O2 to define negative-ion states from ECD data is illustrated. A method for the analysis of published NIMS spectra measured at two temperatures reveals the electron affinities of molecules when combined with substitution effects. We then explored the use of precision and accuracy plots and timelines for the evaluation of electron affinities. 

The available data are the reactant concentration as a function of time for a single experiment, so we will need to use graphical techniques to determine the order of the reaction. There are three possibilities we can explore using the integrated rate laws we ve examined. The reaction could be zero order, first order, or second order with respect to NO2. We will need to manipulate and plot the data in various ways to determine whether there is a good fit with any of these models. (Other orders are also possible, so we should be aware that all three tests could conceivably fail.) With a spreadsheet or a graphing calculator, such manipulation of data is easy. For this example, first we will calculate all of the data needed for all three plots and then make the appropriate graphs to find the linear relationship and determine the rate law. 

Several criteria and rules of thumb have been formulated [26,28,46] to answer the question How many PCs In EMDA, criteria based on statistical inference, that is, on formal tests of hypothesis, should be avoided as we do not want to assume, in the model estimation phase, our PCs to follow a specific distribution. In this context, more intuitive criteria, albeit not formal, but simple and working in practice, are preferable, especially graphics-based criteria, such as sequential exploration of scores plots and/or inspection of residuals plots plots of eigenvalues (scree plots [47]) or cumulative variance versus number of components. Different consideration holds when PCA is used to generate data models that are further used, for example, for regression, classification tasks or process monitoring [48,49] (Section 3.1.5), where PCA model validatiOTi, for example, by cross-validation, in terms of performance on the assessment of future samples has to be taken into account. 

---