Analysis of data

The analysis of the results depends strongly on the achievement of a steady state. If, moreover, the Burnett effects are unimportant, then from (51) we have the linear profile of labeled-particle number density 

The principal tasks are then to assure the validity of the assumptions and to assign error bounds to the final value of 

On the microscopic level, both spatial and temporal fluctuations in number density are to be expected. The decay of these should be rapid compared to the time and distance scales appropriate to the macroscopic self-diflusion phenomenon. Thus to study the presence of a steady state, the M observations of JVi and /i are pooled AM at a time so that the resulting observations appear to be uncorrelated. Typically (AM)fi 200to seems to be satisfactory for this purpose at a reduced volume t = 3 for hard disks (but pooling over even longer intervals is frequently used to assure the independence of the observations). While there are rather long-time correlation effects, there seems little doubt that on any macroscopic time scale the flow is steady. 

The importance of Burnett effects can be ascertained in several ways. With respect to nonlinear Burnett effects, we simply analyze the results for each probability p separately, with the expectation that the resulting values of should display a trend with p if such effects are present. Effects due to the linear super-Bumett terms in (51) should affect the linearity of the profile (71). The latter is averaged over each layer. 

The pooled observations of Ni are fitted to the linear expression (71) via least squares. No significant departures from linearity are observed, which is consistent with the existence of theoretical reasons to believe that the super-Burnett effects have a much smaller distance scale than the typical layer thicknesses used in these calculations. Similarly the layers adjacent to the boundaries show no atypical behavior, but the layer thicknesses are many mean free paths, while kinetic boundary layers are typically of the order of a mean free path. Thus the absence of effects beyond the linear Pick s law term is essentially a result of the spatial coarse graining used. 

Before data analysis can start the response cvurves generated during the experiment require processing. The unwanted part of a sensorgram, such as a very long baseline before injection and regeneration, can be removed. The 

In the BIAevaluation software, all the described sensorgram operations can be carried out in a graphical way without number manipulations in the data spreadsheets. 

---

Nearly all experimental eoexistenee eurves, whether from liquid-gas equilibrium, liquid mixtures, order-disorder in alloys, or in ferromagnetie materials, are far from parabolie, and more nearly eubie, even far below the eritieal temperature. This was known for fluid systems, at least to some experimentalists, more than one hundred years ago. Versehaflfelt (1900), from a eareflil analysis of data (pressure-volume and densities) on isopentane, eoneluded that the best fit was with p = 0.34 and 8 = 4.26, far from the elassieal values. Van Laar apparently rejeeted this eonelusion, believing that, at least very elose to the eritieal temperature, the eoexistenee eurve must beeome parabolie. Even earlier, van der Waals, who had derived a elassieal theory of eapillarity with a surfaee-tension exponent of 3/2, found (1893)... 

The explorative analysis of data sets by visual data mining applications takes place in a three-step process During the first step (overview), the user can obtain an overview of the data and maybe can identify some basic relationships between specific data points. In the second step (filtering), dynamic and interactive navigation, selection, and query tools will be used to reorganize and filter the data set. Each interaction by the user will lead to an immediate update of the data scene and will reveal the hidden patterns and relationships. Finally, the patterns or data points can be analyzed in detail with specific detail tools. 

Molecules are usually represented as 2D formulas or 3D molecular models. WhOe the 3D coordinates of atoms in a molecule are sufficient to describe the spatial arrangement of atoms, they exhibit two major disadvantages as molecular descriptors they depend on the size of a molecule and they do not describe additional properties (e.g., atomic properties). The first feature is most important for computational analysis of data. Even a simple statistical function, e.g., a correlation, requires the information to be represented in equally sized vectors of a fixed dimension. The solution to this problem is a mathematical transformation of the Cartesian coordinates of a molecule into a vector of fixed length. The second point can... 

The normal distribution of measurements (or the normal law of error) is the fundamental starting point for analysis of data. When a large number of measurements are made, the individual measurements are not all identical and equal to the accepted value /x, which is the mean of an infinite population or universe of data, but are scattered about /x, owing to random error. If the magnitude of any single measurement is the abscissa and the relative frequencies (i.e., the probability) of occurrence of different-sized measurements are the ordinate, the smooth curve drawn through the points (Fig. 2.10) is the normal or Gaussian distribution curve (also the error curve or probability curve). The term error curve arises when one considers the distribution of errors (x — /x) about the true value. 

When designing and evaluating an analytical method, we usually make three separate considerations of experimental error. First, before beginning an analysis, errors associated with each measurement are evaluated to ensure that their cumulative effect will not limit the utility of the analysis. Errors known or believed to affect the result can then be minimized. Second, during the analysis the measurement process is monitored, ensuring that it remains under control. Finally, at the end of the analysis the quality of the measurements and the result are evaluated and compared with the original design criteria. This chapter is an introduction to the sources and evaluation of errors in analytical measurements, the effect of measurement error on the result of an analysis, and the statistical analysis of data. 

The probabilistic nature of a confidence interval provides an opportunity to ask and answer questions comparing a sample s mean or variance to either the accepted values for its population or similar values obtained for other samples. For example, confidence intervals can be used to answer questions such as Does a newly developed method for the analysis of cholesterol in blood give results that are significantly different from those obtained when using a standard method or Is there a significant variation in the chemical composition of rainwater collected at different sites downwind from a coalburning utility plant In this section we introduce a general approach to the statistical analysis of data. Specific statistical methods of analysis are covered in Section 4F. 

The following experiments may he used to introduce the statistical analysis of data in the analytical chemistry laboratory. Each experiment is annotated with a brief description of the data collected and the type of statistical analysis used in evaluating the data. 

The stretching properties of polymers are investigated by examining the effect of polymer orientation, polymer chain length, stretching rate, and temperature. Homogeneity of polymer films and consistency between lots of polymer films also are investigated. Statistical analysis of data includes Q-tests and f-tests. 

Vitha, M. F. Carr, P. W. A Laboratory Exercise in Statistical Analysis of Data, /. Chem. Educ. 1997, 74, 998-1000. Students determine the average weight of vitamin E pills using several different methods (one at a time, in sets of ten pills, and in sets of 100 pills). The data collected by the class are pooled together, plotted as histograms, and compared with results predicted by a normal distribution. The histograms and standard deviations for the pooled data also show the effect of sample size on the standard error of the mean. 

A more comprehensive discussion of the analysis of data, covering all topics considered in this chapter as well as additional material, can be found in any textbook on statistics or data analysis following are several such texts. 

The following experiments may he used to illustrate the application of titrimetry to quantitative, qtmlitative, or characterization problems. Experiments are grouped into four categories based on the type of reaction (acid-base, complexation, redox, and precipitation). A brief description is included with each experiment providing details such as the type of sample analyzed, the method for locating end points, or the analysis of data. Additional experiments emphasizing potentiometric electrodes are found in Chapter 11. 

Values for fQi and K 2 for acids of the form H2A are determined from a least-squares analysis of data from a potentiometric titration. 

For each type of problem, appropriate taste tests are suggested together with the type of panel, number of samples per test, and analysis of data. 

Methodology. Practitioners of chemical market research develop iadividual styles and techniques. However, four elements are essential to every useful study defining the problem, data gathering, analysis of data, and presentation of findings. 

Analysis of Data. A veteran practitioner of chemical market research likened this step to the assembly of a jigsaw puzzle. There are many pieces of unequal size and importance that must be put together to make a picture understandable to everyone. Call reports, secondary data inputs, experience, and judgment are the tools used by the market researcher to analyze the data, reach conclusions, make recommendations, and write the report. 

The Hesketh equation is empirical and is based upon a regression analysis of data from a number of industrial venturi scrubbers ... 

Data should be available at every phase of the service quality loop from soliciting business through client reaction and feedback. The collection and analysis of data is a means of improving the service or conversely can detect the onset of an insidious degradation of the service before it becomes a major issue. 

Analysis and prediction of side-chain conformation have long been predicated on statistical analysis of data from protein structures. Early rotamer libraries [91-93] ignored backbone conformation and instead gave the proportions of side-chain rotamers for each of the 18 amino acids with side-chain dihedral degrees of freedom. In recent years, it has become possible to take account of the effect of the backbone conformation on the distribution of side-chain rotamers [28,94-96]. McGregor et al. [94] and Schrauber et al. [97] produced rotamer libraries based on secondary structure. Dunbrack and Karplus [95] instead examined the variation in rotamer distributions as a function of the backbone dihedrals ( ) and V /, later providing conformational analysis to justify this choice [96]. Dunbrack and Cohen [28] extended the analysis of protein side-chain conformation by using Bayesian statistics to derive the full backbone-dependent rotamer libraries at all... 

Classes II and III include all tests in which the specified gas and/or the specified operating conditions cannot be met. Class II and Class III basically differ only in method of analysis of data and computation of results. The Class II test may use perfect gas laws in the calculation, while Class III must use the more complex real gas equations. An example of a Class II test might be a suction throttled air compressor. An example of a Class III test might be a CO2 loop test of a hydrocarbon compressor. Table 10-4 shows code allowable departure from specified design parameters for Class II and Class III tests. 

Goals and objectives to be defined Determination of customer satisfaction Continual improvement Analysis of data... 

Analysis of data to determine whether goals are being achieved (clause 4.1.5) Monitoring of achievement of goals (clauses 4.1.3.2 and 4.2.8)... 

As mentioned earlier some measures will be chosen because improvements in these areas were part of the project justification. It is most likely that these will be efficiency measures. Calculation of these measures generally requires analysis of data or specific data collection exercises. There is a relatively high cost associated with preparing these measures so they should be used prudently. In choosing efficiency measures, you should use only those where you have comparative data about the current management systems. For example, if there is no information on the number of hours dedicated to PSM and ESH, don t use this to try to demonstrate the improvement in efficiency. 

The analysis of performance provides a powerful technique for identifying potential for improvement. As discussed in the previous chapter, trends can be spotted and action taken to identify and correct any unwanted development. Additionally, analysis of data can help with the identification of underlying problems. For example, a higher than average number of eye injuries at a particular facility might justify further investigation. 

Simplified diagnostics Identification of specific failure modes of plant equipment requires manual analysis of data stored in the computer s memory. The software program should be able to display, modify and compare stored data in a manner that simplifies the analysis of the actual operating condition of the equipment. 

Ratterman, M., An Approach to the Design and Analysis of Data from the Standpipe System on FCC Units, Gulf Research and Development. Pittsburgh, Pennsylvania, October 1983. 

Statistical analysis of data from tests with an apparatus by Wesley has demonstrated satisfactory reproducibility of results not only among specimens in a particular test, but also from test to test undertaken at different times. 

Analysis of data pertaining to the modulus of PEO gels obtained by the polyaddition reaction [90] shows that even in this simplified case the network structure substantially deviates from the ideal one. For all samples studied, the molecular weight between crosslinks (M p) exceeds the molecular weight of the precursor (MJ. With decreasing precursor concentration the M xp/Mn ratio increases. Thus, at Mn = 5650 a decrease in precursor concentration from 50 to 20% increases the ratio from 2.3 to 12 most probably due to intramolecular cycle formation. 

Cholesterol Treatment Trialists (CTT) Collaborators (2005) Efficacy and safety of cholesterol-lowering treatment prospective meta-analysis of data from 90 056 participants in 14 randomised trials of statins. Lancet 366 1267-1278... 

From this we can see that knowledge of k f and Rf in a conventional polymerization process readily yields a value of the ratio kp fkt. In order to obtain a value for kf wc require further information on kv. Analysis of / , data obtained under non-steady state conditions (when there is no continuous source of initiator radicals) yields the ratio kvlkx. Various non-stcady state methods have been developed including the rotating sector method, spatially intermittent polymerization and pulsed laser polymerization (PLP). The classical approach for deriving the individual values of kp and kt by combining values for kp kx. with kp/k, obtained in separate experiments can, however, be problematical because the values of kx are strongly dependent on the polymerization conditions (Section... 

Given what has gone before, the reader can readily deduce how to apply these equations to the numerical and linear graphical analysis of data. Consider the following examples. Figure 2-7 shows simulated data for these three dependences. Each gives... 

From an analysis of data for polypyrrole, Albery and Mount concluded that the high-frequency semicircle was indeed due to the electron-transfer resistance.203 We have confirmed this using a polystyrene sulfonate-doped polypyrrole with known ion and electron-transport resistances.145 The charge-transfer resistance was found to decrease exponentially with increasing potential, in parallel with the decreasing electronic resistance. The slope of 60 mV/decade indicates a Nemstian response at low doping levels. 

Ionic Reactions in TD/D2 Ethane Mixtures. The data in Table III show that deuteron transfer occurs in irradiated mixtures of D2 and ethane as well. Data are shown only for temperatures (<25°C.) at which ionic reactions clearly predominate. Analysis of data concerning thermal atomic and free-radical reactions at higher temperatures will be published elsewhere in the near future. The reaction of D3 + with ethane has been observed directly (1) and postulated (2) by other workers. Both groups have proposed that the sequence initiated by deuteron transfer to ethane proceeds as follows ... 

The World Health Organization (WHO) promotes the use of an Anatomical Therapeutic Chemical (ATC) classification system for the collection and analysis of data on drug use. This was originally developed by Scandinavian authorities, and uses a combination of anatomical, therapeutic and chemical criteria to assign drugs to an individual class. The top-level categories, which are anatomically based, are listed in Table 3.2. 

Analysis of Data (Analyse effectiveness and identify improvements)... 

Analysis of data - Analyse performance of quality system based on feedback, conformity of product to requirements, trends and supplier performance... 

---