Bayesian method

The Revea-nd Thomas Bayes, in a posthumously published paper (1763)., pren ided a systematic framework for the introduction of prior knowledge into probability estimates (C rellin, 1972), Indeed, Bayesian methods may be viewed as nothing more than convoluting two distributions. If it were this simple, why the controversy  

The controversy (for a lucid discussion refer to Mann, Shefer and Singpurwala, 1976) between Bayesians and classicists has nothing to do with precedence, for Bayes preceded much of classical statistics. The argument hinges on a) what prior knowledge is acceptable, and b) the treatment of probabilities as random variables themselves. 

Classicists believe that probability has a precise value uncertainty is in finding the value. Bayesians believe that probability is not precise but distributed over a range of values from heterogeneities in the database, past histories, construction tolerances, etc. This difference is subtle but changes the two approaches. 

Bayes s methods aim to satisfy two needs the concept of probability as degree of belief, and the need to use all available information in a probability cstimaie. Cia icists reject all 

Equation 2.4-2 may be considered to be composed of three variables (Tribus, 1969) as shown in equation 2.6-i, where P(A B E) is read as the probability of A and B given E where A, B, and E are observables. (E represents the operating environment.) 

---

Another aspect in which Bayesian methods perform better than frequentist methods is in the treatment of nuisance parameters. Quite often there will be more than one parameter in the model but only one of the parameters is of interest. The other parameter is a nuisance parameter. If the parameter of interest is 6 and the nuisance parameter is ( ), then Bayesian inference on 6 alone can be achieved by integrating the posterior distribution over ( ). The marginal probability of 6 is therefore... 

In the next subsection, I describe how the basic elements of Bayesian analysis are formulated mathematically. I also describe the methods for deriving posterior distributions from the model, either in terms of conjugate prior likelihood forms or in terms of simulation using Markov chain Monte Carlo (MCMC) methods. The utility of Bayesian methods has expanded greatly in recent years because of the development of MCMC methods and fast computers. I also describe the basics of hierarchical and mixture models. 

Maximum likelihood methods used in classical statistics are not valid to estimate the 6 s or the q s. Bayesian methods have only become possible with the development of Gibbs sampling methods described above, because to form the likelihood for a full data set entails the product of many sums of the form of Eq. (24) ... 

A common use of statistics in structural biology is as a tool for deriving predictive distributions of strucmral parameters based on sequence. The simplest of these are predictions of secondary structure and side-chain surface accessibility. Various algorithms that can learn from data and then make predictions have been used to predict secondary structure and surface accessibility, including ordinary statistics [79], infonnation theory [80], neural networks [81-86], and Bayesian methods [87-89]. A disadvantage of some neural network methods is that the parameters of the network sometimes have no physical meaning and are difficult to interpret. 

E Parent, P Hubert, B Bobee, I Miquel, eds. Statistical and Bayesian Methods in Hydrological Sciences. Pans UNESCO Press, 1998. 

The nuclear equipment failure rate database has not changed markedly since the RSS and chemical process data contains information for non-chemical process equipment in a more benign environment. Uncertainty in the database results from the statistical sample, heterogeneity, incompleteness, and unrepresentative environment, operation, and maintenance. Some PSA.s use extensive studies of plant-specific data to augment the generic database by Bayesian methods and others do not. No standard guidance is available for when to use which and the improvement in accuracy that is achieved thereby. Improvements in the database and in the treatment of data requires, uhstaiui.il indu.sinal support but it is expensive. 

Papoular, R.J., Ressouche, E., Schweizer, J. et al. (1993) MaxEnt enhancement of 2D projections from 3D phased Fourier data an application to polarised neutron diffraction, In Maximum Entropy and Bayesian Methods, Mohammad-Djafari, A. and Demoments, G. (Eds.), Kluwer Academic Publisher, Dordrecht, Vol. 53, pp. 311-318. 

Racine, A., Grieve, A.P. and Fluhler, H. (1986). Bayesian methods in practice Experiences in the pharmaceutical industry. Applied Stat. 35 93-150. 

Sheiner, L.B. and Beal, S.L., Bayesian individualisation of pharmacokinetics simple implementation and comparison with non-Bayesian methods, /. Pharm. Sci., 71,... 

Jaynes, E.T. (1986). Where do we stand on maximum entropy ln J.H.Justice (ed.). Maximum Entropy and Bayesian Methods in AppliedStatistics, Cambridge University Press, Cambridge, pp 26-58. 

T. Leonard and J. S. J. Hsu, Bayesian Methods, Cambridge University Press, Cambridge, 1999. 

While the use of Bayes Theorem in this context is not generally controversial its use more generally in medical and clinical research has not always been positively received." It is not the scope of the present chapter to illustrate the use of Bayesian statistics in a more general context and interested readers should read the excellent introduction to the use of Bayesian methods in health-care evaluation provided by Spiegelhalter et alP... 

Papoular, R. J., Prandl, W., and Schiebel, P., in Maximum Entropy and Bayesian Methods,... 

One sometimes encounters remarks on Bayesian methodology suggesting that the essence of the approach is a substitution of professional judgment for data, used in case the latter is substantially lacking. While this viewpoint contains a kernel of trnth, the chapter on Bayesian methods provides a more complete picture of the approach (see Chapter 5 of this book). Bayesian methodology does provide tools for integration of information, possibly for very different types. Thus, the approach may be valuable for ensuring use of as much as possible of the (possibly limited) information available. 

Erdy DM. 1989. The confidence profile method a Bayesian method for assessing health technologies. Operations Res 37 210-228. 

Iman RL, Hora SC. 1989. Bayesian methods for modeling recovery time with an application to the loss of off-site power at nuclear power plants. Risk Anal 9 25-36. 

Patwardhan A, Small MJ. 1992. Bayesian methods for model uncertainty analysis with applications to future sea level rise. Risk Anal 12 513-523. 

Bayesian approaches are discussed throughout this book. Unfortunately, because frequentist methods are typically presented in introductory statistics courses, most environmental scientists do not clearly understand the basic premises of Bayesian methods. This lack of understanding could hamper appreciation for Bayesian approaches and delay the adaptation of these valuable methods for analyzing uncertainty in risk assessments. 

Bayesian statistics are applicable to analyzing uncertainty in all phases of a risk assessment. Bayesian or probabilistic induction provides a quantitative way to estimate the plausibility of a proposed causality model (Howson and Urbach 1989), including the causal (conceptual) models central to chemical risk assessment (Newman and Evans 2002). Bayesian inductive methods quantify the plausibility of a conceptual model based on existing data and can accommodate a process of data augmentation (or pooling) until sufficient belief (or disbelief) has been accumulated about the proposed cause-effect model. Once a plausible conceptual model is defined, Bayesian methods can quantify uncertainties in parameter estimation or model predictions (predictive inferences). Relevant methods can be found in numerous textbooks, e.g., Carlin and Louis (2000) and Gelman et al. (1997). 

Central to any risk assessment is a model of causality. At the onset, a conceptual model is needed that identifies a plausible cause-effect relationship linking stressor exposure to some effect. Most ecological risk assessments rely heavily on weight-of-evidence or expert opinion methods to foster plausibility of the causal model. Unfortunately, such methods are prone to considerable error (Lane et al. 1987 Hutchinson and Lane 1989 Lane 1989), and attempts to quantify that error are rare. Although seldom used in risk assessment, Bayesian methods can explicitly quantify the plausibility of a causal model. 

Loredo TJ. 1990. Prom Laplace to Supernova SN 1987A A Bayesian inference in astrophysics. In Pougere PE, editor. Maximum entropy and Bayesian methods. Dordrecht (DE) Kluwer. 

Robust Bayes redresses some of the most commonly heard criticisms of the Bayesian approach. For instance, robust Bayes relaxes the requirement for an analyst to specify a particular prior distribution and reflects the analyst s confidence about the choice of the prior. Bayesian methods generally preserve zero probabilities. That is, any values of the real line for which the prior distribution is surely zero will remain with zero probability in the posterior, no matter what the likelihood is and no matter what new data may arrive. This preservation of zero probabilities means that an erroneous prior conception about what is possible is immutable in the face of... 

Sander P, Badoux R, editors. 1991. Bayesian methods in reliability. Dordrecht (NL) Kluwer. 

Bayesian methods are very amenable to applying diverse types of information. An example provided during the workshop involved Monte Carlo predictions of pesticide disappearance from a water body based on laboratory-derived rate constants. Field data for a particular time after application was used to adjust or update the priors of the Monte Carlo simulation results for that day. The field data and laboratory data were included in the analysis to produce a posterior estimate of predicted concentrations through time. Bayesian methods also allow subjective weight of evidence and objective evidence to be combined in producing an informed statement of risk. 

Efforts should be made to provide and improve user-friendly software, especially for those approaches where it currently appears to be lacking (e.g., Bayesian methods and Monte Carlo with more than 2 dimensions). 

---