Types of Data

The maximum-likelihood method is not limited to phase equilibrium data. It is applicable to any type of data for which a model can be postulated and for which there are known random measurement errors in the variables. P-V-T data, enthalpy data, solid-liquid adsorption data, etc., can all be reduced by this method. The advantages indicated here for vapor-liquid equilibrium data apply also to other data. 

Usually well logs are only one type of data used to establish a correlation. Any meaningful interpretation will need to be supported by palaeontological data (micro fossils) and... 

The recognition ratios achieved by CBR systems developed as part of this project could not be bettered by either neural-network classifiers or rule-based expert system classifiers. In addition, CBR systems should be mote reliable than simple classifiers as they are programmed to recognise unknown data. The knowledge acquisition necessary to build CBR systems is less expensive than for expert systems, because it is simpler to describe the knowledge how to distinguish between certain types of data than to describe the whole data contents. 

In the context of the structural perturbations at fluid-solid interfaces, it is interesting to investigate the viscosity of thin liquid films. Eaily work on thin-film viscosity by Deijaguin and co-workers used a blow off technique to cause a liquid film to thin. This work showed elevated viscosities for some materials [98] and thin film viscosities lower than the bulk for others [99, 100]. Some controversial issues were raised particularly regarding surface roughness and contact angles in the experiments [101-103]. Entirely different types of data on clays caused Low [104] to conclude that the viscosity of interlayer water in clays is greater than that of bulk water. 

Still another type of adsorption system is that in which either a proton transfer occurs between the adsorbent site and the adsorbate or a Lewis acid-base type of reaction occurs. An important group of solids having acid sites is that of the various silica-aluminas, widely used as cracking catalysts. The sites center on surface aluminum ions but could be either proton donor (Brpnsted acid) or Lewis acid in type. The type of site can be distinguished by infrared spectroscopy, since an adsorbed base, such as ammonia or pyridine, should be either in the ammonium or pyridinium ion form or in coordinated form. The type of data obtainable is illustrated in Fig. XVIII-20, which shows a portion of the infrared spectrum of pyridine adsorbed on a Mo(IV)-Al203 catalyst. In the presence of some surface water both Lewis and Brpnsted types of adsorbed pyridine are seen, as marked in the figure. Thus the features at 1450 and 1620 cm are attributed to pyridine bound to Lewis acid sites, while those at 1540... 

Data type Example of a descriptor with this type of data... 

The choice of which of the many preprocessing methods to apply depends on the type of data involved and the context and objectives of the problem. The importance of appropriate preprocessing caimot be overemphasized improper treatment of the data at this stage may make the rest of the analysis meaningless. 

In principle, this set of equations can be solved for the various constants, a through Q, just as a and b were obtained previously. In practice, however, the actual numerical evaluation involves considerable computation in all but the simplest examples. Computer solution by matrix techniques designed specifically to handle this type of data correlation problem is usually required. 

Type of Data In general, statistics deals with two types of data counts and measurements. Counts represent the number of discrete outcomes, such as the number of defective parts in a shipment, the number of lost-time accidents, and so forth. Measurement data are treated as a continuum. For example, the tensile strength of a synthetic yarn theoretically could be measured to any degree of precision. A subtle aspect associated with count and measurement data is that some types of count data can be dealt with through the application of techniques which have been developed for measurement data alone. This abihty is due to the fact that some simphfied measurement statistics sei ve as an excellent approximation for the more tedious count statistics. 

Normal Distribution of Observations Many types of data follow what is called the gaussian, or bell-shaped, curve this is especially true of averages. Basically, the gaussian curve is a purely mathematical function which has very specif properties. However, owing to some mathematically intractable aspects primary use of the function is restricted to tabulated values. 

Services - including programs for spectra processing and editing, manipulation with different types of data like samples compositions, terms of determination, analytical lines intensities. 

The initial incident report is very important. This document captures the initiator s firsthand knowledge of what occurred in the moments after the specific event. Example 5-2, Sample Toller Initial Incident Report, is an example of the data that should be documented as soon as possible. Note that it should be modified using the company s management system procedure and incident investigation procedure, which should describe the type of data needed, and level of detail desired. 

Data that is not evenly distributed is better represented by a skewed distribution such as the Lognormal or Weibull distribution. The empirically based Weibull distribution is frequently used to model engineering distributions because it is flexible (Rice, 1997). For example, the Weibull distribution can be used to replace the Normal distribution. Like the Lognormal, the 2-parameter Weibull distribution also has a zero threshold. But with increasing numbers of parameters, statistical models are more flexible as to the distributions that they may represent, and so the 3-parameter Weibull, which includes a minimum expected value, is very adaptable in modelling many types of data. A 3-parameter Lognormal is also available as discussed in Bury (1999). 

In its simplest form, a model requires two types of data inputs information on the source or sources including pollutant emission rate, and meteorological data such as wind velocity and turbulence. The model then simulates mathematically the pollutant s transport and dispersion, and perhaps its chemical and physical transformations and removal processes. The model output is air pollutant concentration for a particular time period, usually at specific receptor locations. 

Allows new types of data that were not included in the vendor s application to be entered by the user ... 

If only one type of data is available (e.g. tensile creep curves) then it is possible to make conversions to the other test modes. It should always be remembered, however, that these may not always be absolutely accurate for plastics under all situations. 

The types of data required for incident reporting and root cause analysis systems are specified. Data Collection practices in the CPI are described, and a detailed specification of the types of information needed for causal analyses is provided. 

The model of human error held by management and the plant culture constitutes the environment in which the data collection system operates. Within this environment, all data collection systems need to address the topics listed in Figure 6.1. These topics, from the types of data collected, to the feedback systems that need to be in place, will be addressed in subsequent sections of this chapter. 

The discussion of alternative types of data collection systems serves to emphasize the fact that the design of such systems needs to have very clear objectives. Although a range of data collection systems have been described as if they... 

The type of data collected on human error and the ways in which these data are used for accident prevention will vary depending upon the model of error and accident causation held by the management of an organization. This model will also influence the culture in the plant and the willingness of personnel to participate in data collection activities. In Chapters 1 and 2 a number of alternative viewpoints or models of human error were described. These models will now be briefly reviewed and their implications for the treatment of human error in the process industry will be discussed. 

---