Stochastic finite element method for slope stability analysis Kiyoshi Ishii and Makoto Suzuki Ohsaki Research
Institute, Shimizu Construction Co., Ltd., FukokuSeimei Bldg., 2-2-2, Uchisaiwai-cho, Chiyoda-ku, Tokyo, 100, Japan Civil Engineering Development Dept., Shimizu Construction Co., Ltd., Mita-43-Mori Bldg., No. 13-16, Mita 3-chome, Minato-ku, Tokyo, 108, Japan Received 2 August 1985; accepted 4 March 1986. ; Available online 22 January 2003.
This paper describes a stochastic finite element method using the first-order approximation at a failure point of a set of random variables. The method is extended to equivalent normal represtation of non-normal distributions and offers two advantages: (1) It gives a consistent measure of failure probability for the limit-states defined in terms of different but equivalent performance function formulations, (2). It can be applied to reliability analysis for non-normal variants. Results using this method are compared favorably with that of Monte Carlo simulation in a simple example. Furthermore, this method will be applied to earth slope stability analysis to give probability levels for local and global failures on a potential failure surface. Author Keywords: Soil mechanics; probability theory; stability; finite element method; failure; safety
The stochastic finite element method in structural reliability*1 Armen Der Kiureghian and Jyh-Bin Ke Department of Engineering, University of California, Berkeley, CA 94720, USA
Available online 21 February 2003.
First-order reliability and finite element methods are used to develop a methodology for reliability analysis of structures with stochastically varying properties and subjected to random loads. Two methods for discretization of random fields are examined and the influence of the correlation length of random property or load fields on the reliability of example structures are investigated. It is found that the correlation length of load fields has significant influence on the reliability against displacement or stress limit states. The correlation length of property fields is significant for displacement limit states, but may not be significant for stress limit states. Examples studied include a fixed ended beam with stochastic rigidity and a plate with stochastic elasticity.
The presence of weak materials, bedding, or discontinuities at critical locations could lead to local or large-scale failures of natural or excavated slopes or tunnels. Material spatial variation of Eagle Ford Shale in Texas was established based on laboratory and field testing results. A random field model was used to characterize the material spatial variation, and the correlation distance for the Eagle Ford Shale strength variability was evaluated. Impacts of material property variability and spatial variability on slope stability were analyzed using Monte Carlo simulation with distinct element modeling using random field elements implicitly embedded in the numerical analyses. This study provides
insight into the significance of material spatial variation on stability, possible failure mechanisms, and critical locations of weak materials in a shale mass.
Monte Carlo method
From Wikipedia, the free encyclopedia Jump to: navigation, search
Numerical analysis · Simulation Data analysis · Visualization
[show]Fluid dynamics [show]Monte Carlo methods [show]Particle [show]Scientists
Monte Carlo methods (or Monte Carlo experiments) are a class of computational algorithms that rely on repeated random sampling to compute their results. Monte Carlo methods are often used in simulating physical and mathematical systems. Because of their reliance on repeated computation of random or pseudo-random numbers, these methods are most suited to calculation by a computer and tend to be used when it is unfeasible or impossible to compute an exact result with a deterministic algorithm.
disordered materials. such as fluids. cost overruns and schedule overruns are routinely better predicted by the simulations than by human intuition or alternative "soft" methods.
. particularly multidimensional integrals with complicated boundary conditions. It is a widely successful method in risk analysis when compared with alternative methods or human intuition. More broadly. such as the calculation of risk in business. When Monte Carlo simulations have been applied in space exploration and oil exploration. The term "Monte Carlo method" was coined in the 1940s by physicists working on nuclear weapon projects in the Los Alamos National Laboratory. These methods are also widely used in mathematics: a classic use is for the evaluation of definite integrals. and cellular structures (see cellular Potts model). Monte Carlo methods are useful for modeling phenomena with significant uncertainty in inputs. strongly coupled solids.Monte Carlo simulation methods are especially useful in studying systems with a large number of coupled degrees of freedom. actual observations of failures.
• • •
1 Overview 2 History 3 Applications
o o o o o o o
3.3 Other methods employing Monte Carlo
• • •
8 Notes 9 References 10 External links
.3 Inverse problems 5.2 Engineering 3.5 Finance and business 3.1 Integration methods 5.1.4 Design and visuals 3.7 Games
4 Monte Carlo simulation versus “what if” scenarios 5 Use in mathematics
o o o o
5.2 Application areas 7.1 General 7.3 Applied statistics 3.6 Telecommunications 3.1 Physical sciences 3.1 Optimization methods
5.4 Computational mathematics
6 Monte Carlo and random numbers 7 See also
o o o
The Monte Carlo method can be illustrated as a game of Battleship. Next the player applies algorithms (i. Perform a deterministic computation using the inputs. First a player makes some random shots. Generate inputs randomly from the domain using a certain specified probability distribution. the value of π can be approximated using a Monte Carlo method:
. a battleship is four dots in the vertical or horizontal direction).
There is no single Monte Carlo method. these approaches tend to follow a particular pattern:
For example. Finally based on the outcome of the random sampling and the algorithm the player can determine the likely locations of the other player's ships. Define a domain of possible inputs. Aggregate the results of the individual computations into the final result. 4. the term describes a large and widely-used class of approaches. However.e. instead. 3.
At the end. Next. For example. we aggregate the results into our final result. Since the two areas are in the ratio π / 4. Thus. we generate inputs randomly (scatter individual grains within the square). 4. An approximation will also be poor if only a few grains are randomly dropped into the whole square. the approximation of π. for example. we define a domain of inputs: in this case.
. then inscribe a circle within it. also. two other common properties of Monte Carlo methods: the computation's reliance on good random numbers. counting the number of objects in the circle and dividing by the total number of objects in the square will yield an approximation for π / 4.
Notice how the π approximation follows the general pattern of Monte Carlo algorithms. and its slow convergence to a better approximation as more data points are sampled. Physicists at Los Alamos Scientific Laboratory were investigating radiation shielding and the distance that neutrons would likely travel through various materials. the ratio of the area of an inscribed circle to that of the surrounding square is π / 4. Multiplying the result by 4 will then yield an approximation for π itself. From plane geometry. the objects should fall in the areas in approximately the same ratio. Ulam later contacted John von Neumann to work on it. Note. First. If grains are purposefully dropped into only. Thus. it's the square which circumscribes our circle.1. then perform a computation on each input (test whether it falls within the circle). 2. Despite having most of the necessary data. Draw a square on the ground. and so our approximation will be poor. Uniformly scatter some objects of uniform size throughout the square. 3.
Enrico Fermi in the 1930s and Stanisław Ulam in 1946 first had the idea. grains of rice or sand. the center of the circle. the approximation of π will become more accurate both as the grains are dropped more uniformly and as more are dropped. they will not be uniformly distributed.
In the 1950s they were used at Los Alamos for early work relating to the development of the hydrogen bomb. and they began to find a wide application in many different fields. physical chemistry. their work required a code name. Buffon's needle. treating deterministic problems by first finding a probabilistic analog (see Simulated annealing). but are more specifically traced to the pre-electronic computing era. and operations research.. John von Neumann and Stanislaw Ulam suggested that the problem be solved by modeling the experiment on a computer using chance. and became popularized in the fields of physics. Therefore. and the work on small samples by William Sealy Gosset). the problem could not be solved with analytical calculations. The name is a reference to the Monte Carlo Casino in Monaco where Ulam's uncle would borrow money to gamble. Previous methods of simulation and statistical sampling generally did the opposite: using simulation to test a previously understood deterministic problem. Monte Carlo methods were central to the simulations required for the Manhattan Project. though were severely limited by the computational tools at the time. e. it was only after electronic computers were first built (from 1945 on) that Monte Carlo methods began to be studied in depth. Being secret. Though examples of an "inverted" approach do exist historically.S. Von Neumann chose the name "Monte Carlo". Random methods of computation and experimentation (generally considered forms of stochastic simulation) can be arguably traced back to the earliest pioneers of probability theory (see.g. Air Force were two of the major organizations responsible for funding and disseminating information on Monte Carlo methods during this time. The Rand Corporation and the U. The general difference usually described about a Monte Carlo form of simulation is that it systematically "inverts" the typical mode of simulation.
. they were not considered a general method until the popularity of the Monte Carlo method spread.such as the average distance a neutron would travel in a substance before it collided with an atomic nucleus or how much energy the neutron was likely to give off following a collision.
Monte Carlo methods are widely used in engineering for sensitivity analysis and quantitative probabilistic analysis in process design. particularly Monte Carlo molecular modeling as an alternative for computational molecular dynamics as well as to compute statistical field theories of simple particle and polymer models .
As mentioned. In experimental particle physics. For example. Specific areas of application include:
 Physical sciences
Monte Carlo methods are very important in computational physics.Uses of Monte Carlo methods require large amounts of random numbers.
. understanding their behavior and comparing experimental data to theory. Monte Carlo simulation methods are especially useful for modeling phenomena with significant uncertainty in inputs and in studying systems with a large number of coupled degrees of freedom. and related applied fields. physical chemistry. and have diverse applications from complicated quantum chromodynamics calculations to designing heat shields and aerodynamic forms. and it was their use that spurred the development of pseudorandom number generators. The Monte Carlo method is widely used in statistical physics. Monte Carlo methods are also used in the ensemble models that form the basis of modern weather forecasting operations. see Monte Carlo method in statistical physics. which were far quicker to use than the tables of random numbers which had been previously used for statistical sampling. The need arises from the interactive. these methods are used for designing detectors. or on vastly large scale of the galaxy modelling. co-linear and non-linear behaviour of typical process simulations.
The Type I error and power properties of statistics are obtainable for data drawn from classical theoretical distributions (e.Whitney U test can be conducted using asymptotic critical values. This enables designers to estimate realistic 3 sigma corners and effectively optimise circuit yields. For example. found frequently as an option to asymptotic or exact tests in statistics software. Monte Carlo methods are applied to analyze correlated and uncorrelated variations in analog and digital integrated circuits. normal curve. An approximate randomization test is based on a specified subset of all permutations (which entails
. in SPSS version 18 with the Exact module installed. a Monte Carlo option by specifing the number of samples. infinite sample size and infinitesimally small treatment effect).
in geostatistics and geometallurgy.g. Monte Carlo methods underpin the design of mineral processing flowsheets and contribute to quantitative risk analysis. but such results often have little bearing on statistics' properties for realistic conditions. realistic data conditions. e.
 Applied statistics
Monte Carlo methods are generally used for two purposes in applied statistics. or via exact methods by specifying the time limit to be alloted to the analysis. is to provide a more efficacious approach to data analysis than the time consuming (and often impossibility to compute) permutation methodology. The Monte Carlo option is more accurate than relying on hypothesis tests' asymptotically derived critical values. Monte Carlo methods are also a compromise between approximate randomization and permutation tests.. and yet not as time consuming to obtain as are exact tests. such as permutation tests.•
in microelectronics engineering. a two independent samples Wilcoxon Rank Sum / Mann . Cauchy distribution) for asymptotic conditions (i. The second purpose for Monte Carlo methods. One purpose is to provide a methodology to compare and contrast competing statistics for small sample.
50 designate the outcome as tails.potentially enormous housekeeping of which permutations have been considered).1]. A Monte Carlo study is a technique that can be used to solve a mathematical or statistical problem. It is important to differentiate between a simulation. but if the value is greater than 0. but not a simulation.or more frequently . is a Monte Carlo simulation of the behavior of repeatedly tossing a coin.50 as tails. This is a simulation.50 designate the outcome as heads.
Drawing a large number of pseudo-random uniform variates from the interval [0. A simulation is a fictitious representation of reality. Examples:
Drawing a pseudo-random uniform variate from the interval [0. but not a Monte Carlo simulation. This is a Monte Carlo method of determining area. The Monte Carlo approach is based on a specified number of randomly drawn permutations (exchanging a minor loss in precision if a permutation is drawn twice .
The area of an irregular figure inscribed in a unit square can be determined by throwing darts at the square and computing the ratio of hits within the irregular figure to the total number of darts thrown. g.
Sawilowsky listed the characteristics of a high quality Monte Carlo simulation:
the pseudo-random number generator has certain characteristics (e.50 as heads and greater than 0.1] can be used to simulate the tossing of a coin: If the value is less than or equal to 0. a long “period” before repeating values) the pseudo-random number generator produces values that pass tests for randomness
. A Monte Carlo simulation uses repeated sampling to determine the properties of some phenomenon. and assigning values less than or equal to 0. and a Monte Carlo simulation.for the efficiency of not having to track which permutations have already been selected). Monte Carlo study.
with applications in video games.
When planning a wireless network.
 Design and visuals
Monte Carlo methods have also proven efficient in solving coupled integral differential equations of radiation fields and energy transport. For use in the insurance industry. design must be proved to work for a wide variety of scenarios that depend mainly on the number of users. Monte Carlo methods used in these cases allow the construction of stochastic or probabilistic financial models as opposed to the traditional static and deterministic models.• • • •
the number of repetitions of the experiment is sufficiently large to ensure accuracy of results the proper sampling technique is used the algorithm used is valid for what is being modeled the study simulates the phenomenon in question. The network performance is then evaluated and. architecture.
. if results are not satisfactory. thereby enhancing the treatment of uncertainty in the calculation. Monte Carlo methods are typically used to generate these users and their states. the network design goes through an optimization process. computer generated films. and thus these methods have been used in global illumination computations which produce photorealistic images of virtual 3D models. or to evaluate financial derivatives. and cinematic special effects.
 Finance and business
Monte Carlo methods in finance are often used to calculate the value of companies. design. to evaluate investments in projects at a business unit or corporate level. their locations and the services they want to use. see stochastic modelling.
These approaches are often strong strategically but weak tactically.Monte Carlo methods have recently been applied in game playing related artificial intelligence theory. as tactical decisions tend to rely on a small number of crucial moves which are easily missed by the randomly searching Monte Carlo algorithm. For example. and most likely case). a comparison of a spreadsheet cost construction model run using traditional “what if” scenarios. Each uncertain variable within a model is assigned a “best guess” estimate. Various combinations of each input variable are manually chosen (such as best case.
 Monte Carlo simulation versus “what if” scenarios
The opposite of Monte Carlo simulation might be considered deterministic modeling using single-point estimates. and the results recorded for each so-called “what if” scenario. This is because the “what if” analysis gives equal weight to all scenarios. Monte Carlo simulation considers random sampling of probability distribution functions as model inputs to produce hundreds or thousands of possible outcomes instead of a few discrete scenarios. see quantifying uncertainty under corporate finance. By contrast.
. One of the main problems that this approach has in game playing is that it sometimes misses an isolated. The results provide probabilities of different outcomes occurring. Most notably the game of Go and Battleship have seen remarkably successful Monte Carlo algorithm based computer players. worst case. very good move. and then run again with Monte Carlo simulation and Triangular probability distributions shows that the Monte Carlo analysis has a narrower range than the “what if” analysis. For further discussion.
this method will display convergence—i. By the law of large numbers. Use in mathematics
In general.) Monte Carlo methods provide a way out of this exponential timeincrease. In general. deterministic quadrature methods can be very inefficient. For instance a 10x10 grid requires 100 points. the same spacing on the grid would require 10100 points—far too many to be computed. However. equally spaced grid points over a twodimensional surface are required. To numerically integrate a function of a twodimensional vector. it can be estimated by randomly selecting points in 100dimensional space. for functions of vectors. If the vector has 100 dimensions. As long as the function in question is reasonably wellbehaved. quadrupling the number of sampled
points will halve the error. (See Curse of dimensionality. The most common application of the Monte Carlo method is Monte Carlo integration. this works very well for functions of one variable. Monte Carlo methods are used in mathematics to solve various problems by generating suitable random numbers and observing that fraction of the numbers which obeys some property or properties. The method is useful for obtaining numerical solutions to problems which are too complicated to solve analytically. since in many physical problems. regardless of the number of dimensions.
Main article: Monte Carlo integration
Deterministic methods of numerical integration usually operate by taking a number of evenly spaced samples from a function. a "dimension" is equivalent to a degree of freedom. 100 dimensions is by no means unusual.
.e. and taking some kind of average of the function values at these points.
the points should be drawn from a distribution similar in form to the integrand. but there are approximate methods available: from simply making up an integrable function thought to be similar. Essentially. tending to move in directions which lead to a lower function. Another powerful and very popular application for random numbers in numerical simulation is in numerical optimization.A refinement of this method is to somehow make the points random. the program will move around a marker in multidimensional space. Quasi-Monte Carlo methods can often be more efficient at numerical integration because the sequence "fills" the area better in a sense and samples more of the most important points that can make the simulation converge to the desired solution more quickly. but sometimes moving against the gradient. A similar approach involves using low-discrepancy sequences instead —the quasi-Monte Carlo method. but more likely to come from regions of high contribution to the integral than from regions of low contribution. doing this precisely is just as difficult as solving the integral in the first place. These problems use
. In other words. to one of the adaptive routines discussed in the topics listed below. Understandably.  Integration methods
Direct sampling methods
o o o o
Importance sampling Stratified sampling Recursive stratified sampling VEGAS algorithm Metropolis-Hastings algorithm
Random walk Monte Carlo including Markov chains
Most Monte Carlo optimization methods are based on random walks.
When analyzing an inverse problem. say. As. obtaining a maximum likelihood model is usually not sufficient. 10 moves which produces the best evaluation function at the end. In the general case we may have a large number of model parameters. and an inspection of the marginal probability densities of interest may be impractical. Many problems can be phrased in this way: for example a computer chess program could be seen as trying to find the optimal set of. such as multidisciplinary design optimization. The traveling salesman problem is another optimization problem. in the general case. or even useless. etc. as we normally also wish to have information on the resolution power of the data. the theory linking data with model parameters is nonlinear.  Optimization methods
• • • • • •
Evolution strategy Genetic algorithms Parallel tempering Simulated annealing Stochastic optimization Stochastic tunneling
 Inverse problems
Probabilistic formulation of inverse problems leads to the definition of a probability distribution in the model space.functions of some often large-dimensional vector that are to be minimized (or maximized). There are also applications to engineering design. some moments may not be defined. This probability distribution combines a priori information with new information obtained by measuring some observable parameters (data). the a posteriori probability in the model space may not be easy to describe (it may be multimodal.). But it is possible to pseudorandomly generate a large collection of models according to the posterior probability distribution and to analyze and display the models in such a way that information on the relative likelihoods of model properties is conveyed to the
such as primality testing. A classic example is Rabin's algorithm for primality testing: for any n which is not prime.
 Computational mathematics
Monte Carlo methods are useful in many areas of computational mathematics. and x proves it so.spectator. we have observed a onein-a-million event. a random x has at least a 75% chance of proving that n is not prime. For details. but different. Hence. The only quality usually necessary to make good simulations is for the pseudo-random sequence to appear "random enough" in a certain sense. can be generalized. or Tarantola (2005). The best-known importance sampling method. making it easy to test and re-run simulations. where a lucky choice can find the correct result. In general a Monte Carlo algorithm of this kind produces one correct answer with a guarantee n is composite. and this gives a method that allows analysis of (possibly highly nonlinear) inverse problems with complex a priori information and data with an arbitrary noise distribution. even in cases where no explicit formula for the a priori distribution is available. we have observed at most a 1-in-4 event. the Metropolis algorithm. idea. See also Las Vegas algorithm for a related. pseudo-random sequences. if n is not prime.
. If 10 different random x say that "n is probably prime" when it is not. but with a guarantee of not getting this answer when it is wrong too often — in this case at most 25% of the time. but another one without.
 Monte Carlo and random numbers
Interestingly. This can be accomplished by means of an efficient Monte Carlo method. Monte Carlo simulation methods do not always require truly random numbers to be useful — while for some applications. but x says that it might be. Many of the most useful techniques use deterministic. unpredictability is vital (see Davenport (1995)). see Mosegaard and Tarantola (1995).
 See also
Statistics portal • • • • • • • • • • • • •
Auxiliary field Monte Carlo Bootstrapping (statistics) Demon algorithm Evolutionary computation FERMIAC Markov chain Molecular dynamics Monte Carlo option model Monte Carlo integration Quasi-Monte Carlo method Random number generator Randomness Resampling (statistics)
 Application areas
Graphics. but typically they should pass a series of statistical tests. Testing that the numbers are uniformly distributed or follow another desired distribution when a large enough number of elements of the sequence are considered is one of the simplest.What this means depends on the application. and most common ones. particularly for ray tracing. a version of the Metropolis-Hastings algorithm is also used for ray tracing where it is known as Metropolis light transport
• • • •
Modeling light transport in biological tissue Monte Carlo methods in finance Reliability engineering In simulated annealing for protein structure prediction
Models used to predict the drift of a life raft or movement of an oil slick at sea. particularly for simulations involving atomic clusters In biomolecular simulations In polymer physics
o o o o o o
Bond fluctuation model Monte Carlo algorithm Las Vegas algorithm LURCH Computer go General Game Playing
In computer science
Modeling the movement of impurity atoms (or ions) in plasmas in existing and tokamaks (e. electrons) in three-dimensional systems by means of the Monte Carlo method
EGS — Stanford's simulation code for coupled transport of electrons and photons
. to model the transport of current carriers Environmental science. Search And Rescue and Counter-Pollution. Nuclear and particle physics codes using the Monte Carlo method:
o o o o o o
GEANT — CERN's simulation of high energy particles interacting with a detector. CompHEP. In probabilistic design for simulating and understanding the effects of variability In physical chemistry. a code to calculate the penetration and energy deposition of ions in matter.LANL's radiation transport codes MCU: universal computer code for simulation of particle transport (neutrons.• • • • • • • • •
In semiconductor device research. to invert seismic refraction data.: DIVIMP).g. PYTHIA — Monte-Carlo generators of particle collisions MCNP(X) . dealing with contaminant behavior In geophysics. photons. FLUKA — INFN and CERN's simulation package for the interaction and transport of particles and nuclei in matter SRIM.
o o o o • • • •
PEREGRINE: LLNL's Monte Carlo tool for radiation therapy dose calculations BEAMnrc — Monte Carlo code system for modeling radiotherapy sources (LINAC's) PENELOPE — Monte Carlo for coupled transport of photons and electrons. i.g. Bayesian inference. Markov chain Monte Carlo
 Other methods employing Monte Carlo
• • • • • • • • • • • • • • • • •
Assorted random models. with applications in radiotherapy MONK — Serco Assurance's code for the calculation of k-effective of nuclear systems
Modelling of foam and cellular structures Modeling of tissue morphogenesis Computation of holograms Phylogenetic analysis. e.e. self-organized criticality Direct simulation Monte Carlo Dynamic Monte Carlo method Kinetic Monte Carlo Quantum Monte Carlo Quasi-Monte Carlo method using low-discrepancy sequences and self avoiding walks Semiconductor charge transport and the like Electron microscopy beam-sample interactions Stochastic optimization Cellular Potts model Markov chain Monte Carlo Cross-entropy method Applied information economics Monte Carlo localization Evidence-based Scheduling Binary collision approximation List of software for Monte Carlo molecular modeling
ubc. J. Los Alamos Science (1987 Special Issue dedicated to Stanislaw Ulam): 125–130. showing graph 14.gov/la-pubs/00326866. ^ http://www. (2003). 2000. ^ Nicholas Metropolis (1987). Dodd. Monte Carlo and the MANIAC.html
. ^ H. p. ^ Douglas Hubbard "The Failure of Risk Management: Why It's Broken and How to Fix It". (2003). 11.fr/~tarantola/Files/Professional/Papers_PDF/Monte Carlo_latex. 218-225.pdf 15. ^ Ibid.pdf 5. p. MacGillivray. 14. 1986. ^
Douglas Hubbard "How to Measure Anything: Finding the Value of
Intangibles in Business" pg. ^ David Vose: “Risk Analysis. John Wiley & Sons. doi:10. 1011. ^ Stephan A. http://www. "The beginning of the Monte Carlo method". Rochester Hills. 8. Springer Netherlands  9. 13.ipgp. You think you've got trivials? Journal of Modern Applied Statistical Methods. ^ http://www. T. 16 13.jussieu. 46. Shlomo S. 10. A Quantitative Guide. Monte-Carlo simulations of galaxy systems. Anderson. 7. 2007 2. Notes 1. "Multiscale modeling of polymer materials using field-theoretic methodologies: a survey about recent developments". Journal of Mathematical Chemistry 46 (2): 363–426. ^ Sawilowsky. "Metropolis. ^ Sawilowsky.1007/s10910-008-9467-3. ^ Ibid. MI: JMASM. Baeurle (2009). Fahoome.pdf. 12.fr/~tarantola/Files/Professional/SIAM/index.cs.ca/~nando/papers/mlintro. Volume 86.com/content/xl057580272w8703/. Statistics via Monte Carlo Simulation with Fortran.L. 4. ^ Charles Grinstead & J. ISBN 09740236-0-4. American Mathematical Society. 1997 6. Laurie Snell "Introduction to Probability" pp. 2(1). S." Los Alamos Science..springerlink. pp. John Wiley & Sons. 1982. R. 2009 3. ^ H. no. 17. http://library. p. Gail C. Number 2 / September.ipgp. John Wiley & Sons. Astrophysics and Space Science. ^ http://people.lanl.jussieu. 96-108.” Second Edition.
D. (1975). A. Rosenbluth.seismic refraction inversion users manual.143290. D. ISBN 9812389350. J. Gould. Freitas. http://doi. Monte Carlo and quasi-Monte Carlo methods. 17. Applications to Physical Systems.. Monte Carlo Methods..1699114.acm.com/wb/pages/home/product/usersmanual.1145/143242. ISBN 0416523404. NJ: World Scientific. Neil (2001). (2004). Gordon. Part 2.
. An Introduction to Computer Simulation Methods. London: Methuen. ISBN 020116504X.
Metropolis.org/10. 7. H..
Metropolis.. 1–49. Teller.php  References Constructs such as ibid.acm. Hackensack. ^ Desman Geophysics .143290. S.2307/2280232.
Caflisch.. Handscomb. The Monte Carlo Method in Condensed Matter Physics. New York: Springer. Journal of Chemical Physics 21 (6): 1087. Teller. are discouraged by Wikipedia's style guide for footnotes. Judgement under Uncertainty: Heuristics and Biases. as they are easily broken. Doucet.desmangeophysics. Nicholas. Ulam. Arianna W.
Binder. doi:10.16. Bernd A. "The Monte Carlo Method". Journal of the American Statistical Association (American Statistical Association) 44 (247): 335–341. Retrieved 2007-08-19. Augusta H. ISBN 0387543694. E. Kahneman. Markov Chain Monte Carlo Simulations and Their Statistical Analysis (With Web-Based Fortran Code). Arnaud. N. C. ^ Davenport. Marshall N. cit. J. PMID 18139350. M. doi:10. Tobochnik. "Equation of State Calculations by Fast Computing Machines". Please improve this article by replacing them with named references (quick guide). Rosenbluth.1145/143242. Jan (1988). Reading: Addison-Wesley.org/10. Harvey. (1998).. and loc. Berg. (1982).1063/1. http://jstor. R. Acta Numerica. doi:http://doi.org/stable/2280232. Tversky. Cambridge University Press. (1949). pp.. "Primality testing revisited". Nando de. Edward (1953).
• • •
Hammersley. New York: Springer. ISBN 0387951466. http://www. Sequential Monte Carlo methods in practice. Kurt (1995). Cambridge University Press. or an abbreviated title.
J.ipgp. G. (2004)..Overview and Concept. Kevin (1997). brighton-webs. University of Nebraska-Lincoln Introduction to Monte Carlo simulation (for Microsoft Excel).
 External links
• • • • • • • • • • •
Overview and reference list. G.fr/~tarantola/Files/Professional/SIAM/index. Stochastic Simulation in Physics. New York: Springer. a practical example.co. Kroese. doi:10. (2007). Savvakis C. Savvides Monte Carlo Method Example. Winston Monte Carlo Methods .). Geophys.. Mosegaard. Prof. and Applications. C.
Tarantola.). The Application of Monte Carlo Methodology in Project Appraisal. (1995). 100 (B7): 12431–12447. Wayne L. R. Rubinstein. ISBN 9813083263. ISBN 0898715725. New York: Springer. New York: John Wiley & Sons. Computational Science Education Project The Basics of Monte Carlo Simulations.uk Molecular Monte Carlo Intro. ISBN 038794527X. ISBN 0387212396. Inverse Problem Theory. Tarantola. New York: Springer. Robert. "Monte Carlo sampling of solutions to inverse problems". Simulation and the Monte Carlo Method (2nd ed. D. P. Monte Carlo: Concepts.1029/94JB03097. ISBN 9780470177938. P. S. Klaus.html. A step-by-step guide to creating a monte carlo excel spreadsheet Pricing using Monte Carlo simulation. Cooper Union Monte Carlo techniques applied in physics Risk Analysis in Investment Appraisal. Res. Y. Mathworld Introduction to Monte Carlo Methods. Albert (1995). MacKeown.jussieu. Giancarlo Vercellino Approximate And Double Check Probability Problems Using Monte Carlo method at Orcik Dot Net
. Casella. Philadelphia: Society for Industrial and Applied Mathematics.• • • • •
Fishman. P. http://www. Albert (2005). Algorithms. Monte Carlo Statistical Methods (2nd ed.
Harmonic) · Median · Mode s data Dispersio Range · Standard deviation · Coefficient of variation · n Percentile · Interquartile range Shape Variance · Skewness · Kurtosis · Moments · L-moments
Count dataIndex of dispersion Summary Grouped data · Frequency distribution · Contingency table tables Dependen Pearson product-moment correlation · Rank correlation (Spearman's ce rho.[hide]
[show] Descriptive statistics Continuou Location Mean (Arithmetic. Geometric. Kendall's tau) · Partial correlation · Scatter plot Statistical Bar chart · Biplot · Box plot · Control chart · Correlogram · Forest graphics plot · Histogram · Q-Q plot · Run chart · Scatter plot · Stemplot · Radar chart [show] Data collection Designing studies Effect size · Standard error determination · Statistical power · Sample size
Survey Sampling · Stratified sampling · Opinion poll · Questionnaire methodolog y Controlled Design of experiments · Randomized experiment · Random experiment assignment · Replication · Blocking · Regression discontinuity · Optimal design Uncontrolle Natural experiment · Quasi-experiment · Observational study d studies [show]
Statistical inference Bayesian Bayesian probability · Prior · Posterior · Credible interval · Bayes inference factor · Bayesian estimator · Maximum posterior estimator Classical Confidence interval · Hypothesis testing · Sampling distribution · inference Meta-analysis Specific tests Z-test (normal) · Student's t-test · F-test · Chi-square test · Pearson's chi-square · Wald test · Mann–Whitney U · Shapiro–Wilk · Signed-rank
General Mean-unbiased · Median-unbiased · Maximum likelihood · Method of estimatio moments · Minimum distance · Maximum spacing · Density n estimation [show] Correlation and regression analysis Correlation Pearson product-moment correlation · Partial Confounding variable · Coefficient of determination Linear regression Nonstandard predictors correlation ·
Simple linear regression · Ordinary least squares · General linear model · Bayesian regression Nonlinear regression · Nonparametric · Semiparametric · Isotonic · Robust
Generalized Exponential families · Logistic (Bernoulli) · Binomial · Poisson linear model Formal analyses Analysis of variance Multivariate ANOVA (ANOVA) · Analysis of covariance ·
[show] Data analyses and models for other specific data types
Multivariat Multivariate regression · Principal components · Factor analysis · e statistics Cluster analysis · Copulas Time seriesDecomposition · Trend estimation · Box–Jenkins · ARMA models · analysis Spectral density estimation Survival analysis Survival function · Kaplan–Meier · Logrank test · Failure rate · Proportional hazards models · Accelerated failure time model
Categorical McNemar's test · Cohen's kappa data [show] Applications EnvironmentaGeostatistics · Climatology l statistics Medical statistics Social statistics Epidemiology · Clinical trial · Clinical study design
Actuarial science · Population · Demography Psychometrics · Official statistics · Crime statistics
Category · Portal · Outline · Index Retrieved from "http://en.org/wiki/Monte_Carlo_method" Categories: Monte Carlo methods | Randomness | Numerical analysis | Statistical mechanics | Computational physics | Sampling techniques | Statistical approximations | Probabilistic complexity theory Hidden categories: Articles needing cleanup from March 2010 | All pages needing cleanup | Statistics articles with navigational template
Personal tools • •
New features Log in / create account
Namespaces • •
Variants Views • •
Navigation • • • • • •
Main page Contents Featured content Current events Random article Donate
Interaction • • • • •
About Wikipedia Community portal Recent changes Contact Wikipedia Help
Toolbox • • • • • •
What links here Related changes Upload file Special pages Permanent link Cite this page
Print/export • •
Create a book Download as PDF
Languages • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • • •
Català Česky Dansk Deutsch Español
Français 한국어 Hrvatski Bahasa Indonesia Italiano
Latviešu Magyar Nederlands 日本語 Norsk (bokmål) Occitan Polski Português Русский Simple English Slovenčina Basa Sunda Suomi Svenska Türkçe Українська
. Aalborg University.
• • • • • •
WATER RESOURCES RESEARCH. Inc. The new two-step stochastic modeling approach provides a highly time efficient way to analyze consequences of uncertainties in stochastic parameter input at field scale. Text is available under the Creative Commons Attribution-ShareAlike License.• • •
中文 This page was last modified on 20 October 2010 at 05:35. a non-profit organization. PP. additional terms may apply.
. accepted 23 April 1998. Received 3 February 1998. .•
problem can be adequately described by up to two spatially variable parameters.