Probability-density-function analysis

Fig. 14. Example of a probability density function analysis of a natural fault cluster illustrating a relationship between the largest offsets present and the number and size of smaller offset groups in the cluster.

The use of probability-density-function analysis, an important topic in statistical analysis, is mentioned with respect to its utility in nondestructive testing for inspectability, damage analysis, and F-map generation. In addition to the mathematical concepts, several sample problems in composite material and adhesive bond inspection are discussed. A feature map (or F map) is introduced as a new procedure that gives us a new way to examine composite materials and bonded structures. Results of several feasibility studies on aluminum-to-alumi-num bond inspection, along with results of color graphics display samples will be presented. 

Bialkowski, S. E., Data Analysis in the Shot Noise Limit 1. Single Parameter Estimation with Poisson and Normal Probability Density Functions, Anal. Chem. 61, 1989, 2479-2483. 

The multimedia model present in the 2 FUN tool was developed based on an extensive comparison and evaluation of some of the previously discussed multimedia models, such as CalTOX, Simplebox, XtraFOOD, etc. The multimedia model comprises several environmental modules, i.e. air, fresh water, soil/ground water, several crops and animal (cow and milk). It is used to simulate chemical distribution in the environmental modules, taking into account the manifold links between them. The PBPK models were developed to simulate the body burden of toxic chemicals throughout the entire human lifespan, integrating the evolution of the physiology and anatomy from childhood to advanced age. That model is based on a detailed description of the body anatomy and includes a substantial number of tissue compartments to enable detailed analysis of toxicokinetics for diverse chemicals that induce multiple effects in different target tissues. The key input parameters used in both models were given in the form of probability density function (PDF) to allow for the exhaustive probabilistic analysis and sensitivity analysis in terms of simulation outcomes [71]. 

The key input parameters used in the 2 FUN model were given in the form of probability density function (PDF) to allow the exhaustive probabilistic analysis and sensitivity analysis in terms of simulation outcomes. 

Two consequences of this simple analysis are far-reaching. First, the common perception that normal or log-normal functions may be used as catch-all probability density functions is physically untenable since these functions are not time-invariant relative to most geological processes (mixing, differentiation,. ..). Second, there is more information on the physics of geological processes contained in the density function of concentrations, ratios, and other geochemical parameters than what is reflected by their mean or variance. Obviously, this information is deeply buried and convoluted, but deserves attention anyway. 

Quantitative uncertainty analysis is not appropriate when in a worst-case approach, risk is found to be negligible when held evidence indicates obvious and severe effects when information is insufficient to adequately characterize the model equation, input probability density functions (PDFs), and the relationships between the PDFs or when it is more cost-effective to take action than to conduct more analyses. 

So, MCBA builds a covariance matrix of the residuals around the inner model and from this matrix it obtains a probability density function as bayesian analysis does, taking into account that the dimensionality of the inner space correspondingly reduces the rank of the covariance matrix from which a minor must be extracted. 

A third measure of location is the mode, which is defined as that value of the measured variable for which there are the most observations. Mode is the most probable value of a discrete random variable, while for a continual random variable it is the random variable value where the probability density function reaches its maximum. Practically speaking, it is the value of the measured response, i.e. the property that is the most frequent in the sample. The mean is the most widely used, particularly in statistical analysis. The median is occasionally more appropriate than the mean as a measure of location. The mode is rarely used. For symmetrical distributions, such as the Normal distribution, the mentioned values are identical. 

The movement of the particles in this stage is very complex and extremely random, so that to determine accurately the residence time distribution and the mean residence time is difficult, whether by theoretical analysis or experimental measurement. On the other hand, the residence time distribution in this stage is unimportant because this subspace is essentially inert for heat and mass transfer. Considering the presence of significant back-mixing, the flow of the particles in this stage is assumed also to be in perfect mixing, as a first-order approximation, and thus the residence time distribution probability density function is of the form below ... 

In an unmodified Monte Carlo method, simple random sampling is used to select each member of the 777-tuple set. Each of the input parameters for a model is represented by a probability density function that defines both the range of values that the input parameters can have and the probability that the parameters are within any subinterval of that range. In order to carry out a Monte Carlo sampling analysis, each input is represented by a cumulative distribution function (CDF) in which there is a one-to-one correspondence between a probability and values. A random number generator is used to select probability in the range of 0-1. This probability is then used to select a corresponding parameter value. 

Probabilistic uncertainty analysis A technique that assigns a probability density function to each input parameter, and then randomly selects values from each of the distributions and inserts them into the exposure equation. Repeated calculations produce a distribution of predicted values reflecting the combined... 

Because this analysis is required at each point X, we drop the subscript 0, and discuss the properties of SP(X) in general. The function Sf (X), called the probability density function for X, is plotted as a continuous function above the X-axis. It is defined for all points in an interval (a, b) whose end points depend on the nature of X. In some cases the end points can include -l-oo,-oo, or both. Note that Sf (X) has physical dimensions of X since the product Sf (X)dX must be dimensionless. 

Thus, this analysis allows for a distribution (more accurately termed a probability density function or... 

The Monte Carlo method is a well-established approach used in characterizing uncertainty that can be used to incorporate ranges of data (distributions) into calculations. The Monte Carlo method involves choosing values from a random selection scheme drawn from probability density functions based on a range of data that characterize the parameters of interest. Monte Carlo analysis can be selectively used to generate input parameters and mixed with point estimates, as appropriate, to calculate risk. 

High-efficiency filtration is the most common method of collecting particulate mailer for the determination of chemical composition. Chemical analysis of filter. samples provides information on the composition of the aerosol averaged over all particle sizes and over the time interval of sampling. For a constant gas-sampling rate, the mass concentration of species i averaged over particle size and time is related to the size compo.sition probability density function as follows ... 

For example, many methods are available for the chemical analysis of deposited aerosol particles. Individual particles can be analyzed as well as heavier deposits. A serious gap in aerosol instrumentation is the lack of instrument.s for on-line measurement of aerosol chemical constituents without removing them from the gas. Very large amounts of information on multicomponent, polydi.sperse aerosols would be generated by an instrument capable of continuously sizing and chemically analyzing each particle individually, thereby permitting the determination of the size-composition probability density function, g (Chapter I), From this function, in principle, many of the chemical... 

The same analysis holds for density functions in general, including probability density functions. 

Zaichik, L. I. Aupchenkov, V. M. 1998 Kinetic equation for the probability density function of velocity and temperature of particles in an inhomogeneous turbulent flow analysis of flow in a shear layer. High Temperature 36 (4), 572-582. 

---