Downloads & Free Reading Options - Results

,Approved For Release 2000/08/17 LP78-04723A000200040005-6 Attachment 1 25X1A 25X1A is a carefully organized set of 70 statistical programs which provide nearly complete support to research in the Social Sciences area. These statistical programs operate under the direction of an executive program which is part of the system. A executive portion of the system was recently completed 25X1A at . This contract was initiated by the Assessment and Evaluation Staff, Office of Medical Services and funded by Life Sciences Division, Office of Research and Development. The executive system revision resulted in the simplification of user procedures for initiating llllllllllllllllll~operations by reducing the number and com- plexity of the required control cards. 25X1A 25X1A The benefits obtained accrue mainly to the user of the system. 25X1A The user no longer needs a basic familiarity with the FORTRAN programming language; he was instead a language which approximates the research language he normally uses. 25X1 A was designed for an 1H4 7090 computer; it has however been suet emulated on an IBM 360/65. The above revision did not affect the operating characteristics of the system except that the executive program takes longer (in microseconds) to run since it must do more than previously required of it. The computer is initially used to score and report results of tests administered to applicants for Agency employment. A by-product of this opera- tion is a magnetic tape file of test results for approximately 25,000 people. 25X1A _ makes possible a wide variety of descriptive and inferential statistical projects with these test data. There have been 10 such projects in the past six months using samples of 50 to 3,000 cases. Much of the work 25X1A performed by the - system is based on data matrices larger than 10 X 50- The Assessment and Evaluation Staff is hiring a contract employee on a half-time basis to initiate and monitor - runs as required. 25X1A Approved For Release 2000/08/17 ? A-RDP78-04723A000200040005-6 S ECE

,Approved For Release 2000/08/17 LP78-04723A000200040005-6 Attachment 1 25X1A 25X1A is a carefully organized set of 70 statistical programs which provide nearly complete support to research in the Social Sciences area. These statistical programs operate under the direction of an executive program which is part of the system. A executive portion of the system was recently completed 25X1A at . This contract was initiated by the Assessment and Evaluation Staff, Office of Medical Services and funded by Life Sciences Division, Office of Research and Development. The executive system revision resulted in the simplification of user procedures for initiating llllllllllllllllll~operations by reducing the number and com- plexity of the required control cards. 25X1A 25X1A The benefits obtained accrue mainly to the user of the system. 25X1A The user no longer needs a basic familiarity with the FORTRAN programming language; he was instead a language which approximates the research language he normally uses. 25X1 A was designed for an 1H4 7090 computer; it has however been suet emulated on an IBM 360/65. The above revision did not affect the operating characteristics of the system except that the executive program takes longer (in microseconds) to run since it must do more than previously required of it. The computer is initially used to score and report results of tests administered to applicants for Agency employment. A by-product of this opera- tion is a magnetic tape file of test results for approximately 25,000 people. 25X1A _ makes possible a wide variety of descriptive and inferential statistical projects with these test data. There have been 10 such projects in the past six months using samples of 50 to 3,000 cases. Much of the work 25X1A performed by the - system is based on data matrices larger than 10 X 50- The Assessment and Evaluation Staff is hiring a contract employee on a half-time basis to initiate and monitor - runs as required. 25X1A Approved For Release 2000/08/17 ? A-RDP78-04723A000200040005-6 S ECE

,Approved For Release 2000/08/17 LP78-04723A000200040005-6 Attachment 1 25X1A 25X1A is a carefully organized set of 70 statistical programs which provide nearly complete support to research in the Social Sciences area. These statistical programs operate under the direction of an executive program which is part of the system. A executive portion of the system was recently completed 25X1A at . This contract was initiated by the Assessment and Evaluation Staff, Office of Medical Services and funded by Life Sciences Division, Office of Research and Development. The executive system revision resulted in the simplification of user procedures for initiating llllllllllllllllll~operations by reducing the number and com- plexity of the required control cards. 25X1A 25X1A The benefits obtained accrue mainly to the user of the system. 25X1A The user no longer needs a basic familiarity with the FORTRAN programming language; he was instead a language which approximates the research language he normally uses. 25X1 A was designed for an 1H4 7090 computer; it has however been suet emulated on an IBM 360/65. The above revision did not affect the operating characteristics of the system except that the executive program takes longer (in microseconds) to run since it must do more than previously required of it. The computer is initially used to score and report results of tests administered to applicants for Agency employment. A by-product of this opera- tion is a magnetic tape file of test results for approximately 25,000 people. 25X1A _ makes possible a wide variety of descriptive and inferential statistical projects with these test data. There have been 10 such projects in the past six months using samples of 50 to 3,000 cases. Much of the work 25X1A performed by the - system is based on data matrices larger than 10 X 50- The Assessment and Evaluation Staff is hiring a contract employee on a half-time basis to initiate and monitor - runs as required. 25X1A Approved For Release 2000/08/17 ? A-RDP78-04723A000200040005-6 S ECE

This paper proposes a method to solve multivariable nonlinear optimization problem based on MCMC statistical sampling. Theoretical analysis proves that the maximum statistic converges to the maximum point of probability density. From this convergence property, we establish a newly algorithm to find the best solution of an optimization through largely MCMC sampling in condition that the exact generalized probability density function has been designed. The MCMC optimization algorithm needs less iterate variables reserved so that the computing speed is relatively high. Finally, we build a Markov chain model to demonstrate the dynamic movement of ladderlike labour transfer with multiparamter, and we practice this MCMC sampling optimization algorithm to find parameters estimations. The optimization results are reasonable and from which we obtain the short-term and long-term forecast of labour movements.

This paper proposes a method to solve multivariable nonlinear optimization problem based on MCMC statistical sampling. Theoretical analysis proves that the maximum statistic converges to the maximum point of probability density. From this convergence property, we establish a newly algorithm to find the best solution of an optimization through largely MCMC sampling in condition that the exact generalized probability density function has been designed. The MCMC optimization algorithm needs less iterate variables reserved so that the computing speed is relatively high. Finally, we build a Markov chain model to demonstrate the dynamic movement of ladderlike labour transfer with multiparamter, and we practice this MCMC sampling optimization algorithm to find parameters estimations. The optimization results are reasonable and from which we obtain the short-term and long-term forecast of labour movements.

Based on a new theory, two computer codes were developed specifically to calculate the exact statistical tolerance limits for normal distributions within unknown means and variances for the one-sided and two-sided cases for the tolerance factor, k. The quantity k is defined equivalently in terms of the noncentral t-distribution by the probability equation. Two of the four mathematical methods employ the theory developed for the numerical simulation. Several algorithms for numerically integrating and iteratively root-solving the working equations are written to augment the program simulation. The program codes generate some tables of k's associated with the varying values of the proportion and sample size for each given probability to show accuracy obtained for small sample sizes.

This paper deals with some computational aspects in the Bayesian analysis of statistical models with intractable normalizing constants. In the presence of intractable normalizing constants in the likelihood function, traditional MCMC methods cannot be applied. We propose an approach to sample from such posterior distributions. The method can be thought as a Bayesian version of the MCMC-MLE approach of Geyer and Thompson (1992). To the best of our knowledge, this is the first general and asymptotically consistent Monte Carlo method for such problems. We illustrate the method with examples from image segmentation and social network modeling. We study as well the asymptotic behavior of the algorithm and obtain a strong law of large numbers for empirical averages.

This report describes development and documentation of a set of programs for interactive use with graphics (IBM 360/370 with 2250 terminal), for the construction and evaluation of response surfaces, and for plotting and expanding statistical distribution functions. A facility is included to update and add new functions. Examples and sample displays are included for response surface optimization, process evaluation, likelihood function, power functions, multiple correlation distributions, Lelimann test, and distribution of the largest characteristic root. (Author)

This report describes development and documentation of a set of programs for interactive use with graphics (IBM 360/370 with 2250 terminal), for the construction and evaluation of response surfaces, and for plotting and expanding statistical distribution functions. A facility is included to update and add new functions. Examples and sample displays are included for response surface optimization, process evaluation, likelihood function, power functions, multiple correlation distributions, Lelimann test, and distribution of the largest characteristic root. (Author)

Based on a new theory, two computer codes were developed specifically to calculate the exact statistical tolerance limits for normal distributions within unknown means and variances for the one-sided and two-sided cases for the tolerance factor, k. The quantity k is defined equivalently in terms of the noncentral t-distribution by the probability equation. Two of the four mathematical methods employ the theory developed for the numerical simulation. Several algorithms for numerically integrating and iteratively root-solving the working equations are written to augment the program simulation. The program codes generate some tables of k's associated with the varying values of the proportion and sample size for each given probability to show accuracy obtained for small sample sizes.

Systems of spin 1, such as triplet pairs of spin-1/2 fermions (like orthohydrogen nuclei) make useful three-terminal elements for quantum computation, and when interconnected by qubit equality relations are universal for quantum computation. This is an instance of quantum-statistical computation: some of the logical relations of the problem are satisfied identically in virtue of quantum statistics, which takes no time. We show heuristically that quantum-statistical ground-mode computation is substantially faster than pure ground-mode computation when the ground mode is reached by annealing.

The intuition that a long history is required for the emergence of complexity in natural systems is formalized using the notion of depth. The depth of a system is defined in terms of the number of parallel computational steps needed to simulate it. Depth provides an objective, irreducible measure of history applicable to systems of the kind studied in statistical physics. It is argued that physical complexity cannot occur in the absence of substantial depth and that depth is a useful proxy for physical complexity. The ideas are illustrated for a variety of systems in statistical physics.

The intuition that a long history is required for the emergence of complexity in natural systems is formalized using the notion of depth. The depth of a system is defined in terms of the number of parallel computational steps needed to simulate it. Depth provides an objective, irreducible measure of history applicable to systems of the kind studied in statistical physics. It is argued that physical complexity cannot occur in the absence of substantial depth and that depth is a useful proxy for physical complexity. The ideas are illustrated for a variety of systems in statistical physics.

A new sub-grid-scale stochastic model of drops air-blast breakup is presented in this paper. The stochastic process is considered in the framework of cascade of uncorrelated breakage events in series down to the critical size, independently from the initial distribution of sizes. To this end, the Kolmogorov's discrete model of particle breakup has been reproduced in the form of evolution equation for distribution function. The asymptotic solution of this equation has been applied to simulate the drop breakup alongside with Lagrangian model of spray dynamics. Performed computations of air-blast atomization are related to a spray close to the rocket engine configuration. A broad spectra of droplet size is simulated at each spray location with a co-existence of large drops and small droplets. The evolution of shape of the droplet-size pdF's is shown at different sections in downstream direction.

A new sub-grid-scale stochastic model of drops air-blast breakup is presented in this paper. The stochastic process is considered in the framework of cascade of uncorrelated breakage events in series down to the critical size, independently from the initial distribution of sizes. To this end, the Kolmogorov's discrete model of particle breakup has been reproduced in the form of evolution equation for distribution function. The asymptotic solution of this equation has been applied to simulate the drop breakup alongside with Lagrangian model of spray dynamics. Performed computations of air-blast atomization are related to a spray close to the rocket engine configuration. A broad spectra of droplet size is simulated at each spray location with a co-existence of large drops and small droplets. The evolution of shape of the droplet-size pdF's is shown at different sections in downstream direction.

Contents: Papers Submitted to Refereed Journals (and not yet published); Papers Published in Refereed Journals; Books (and sections thereof) Published; Invited Presentations at Topical or Scientific/Technical Society Conferences; Contributed Presentation at Topical or Scientific/Technical Society Conferences; Honors/Awards/Prizes; Technical Reports. Keyword: Bibliographies.

The past century has seen a steady increase in the need of estimating and predicting complex systems and making (possibly critical) decisions with limited information. Although computers have made possible the numerical evaluation of sophisticated statistical models, these models are still designed by humans because there is currently no known recipe or algorithm for dividing the design of a statistical model into a sequence of arithmetic operations.With the purpose of addressing this problem this program has developed (1) the foundations of a rigorous framework for the scientific computation of optimal statistical estimators/models and (2) the required calculus enabling the reduction of optimization problems over measures over spaces of measures and functions. Two highlights of the work accomplished consist of (1) the application of the calculus to the identification of brittleness in Bayesian inference and (2) the application of the framework to the automated identification of scalable linear solvers for PDEs with rough coefficients.

We analytically study the input-output properties of a neuron whose active dendritic tree, modeled as a Cayley tree of excitable elements, is subjected to Poisson stimulus. Both single-site and two-site mean-field approximations incorrectly predict a non-equilibrium phase transition which is not allowed in the model. We propose an excitable-wave mean-field approximation which shows good agreement with previously published simulation results [Gollo et al., PLoS Comput. Biol. 5(6) e1000402 (2009)] and accounts for finite-size effects. We also discuss the relevance of our results to experiments in neuroscience, emphasizing the role of active dendrites in the enhancement of dynamic range and in gain control modulation.

We analytically study the input-output properties of a neuron whose active dendritic tree, modeled as a Cayley tree of excitable elements, is subjected to Poisson stimulus. Both single-site and two-site mean-field approximations incorrectly predict a non-equilibrium phase transition which is not allowed in the model. We propose an excitable-wave mean-field approximation which shows good agreement with previously published simulation results [Gollo et al., PLoS Comput. Biol. 5(6) e1000402 (2009)] and accounts for finite-size effects. We also discuss the relevance of our results to experiments in neuroscience, emphasizing the role of active dendrites in the enhancement of dynamic range and in gain control modulation.

This addendum details the statistical procedures used in preparing the report, Decision Risk Analysis for XM204, 105mm Howitzer, Towed Reliability/ Durability Requirements (AD-763 204). A computer program was developed for this study to simulate DT/OT II testing analysis of data, the decision made based on this analysis, and the funding implications of this decision. A two-parameter Weibull family was assumed to describe durability failures. The test results were used to estimate the two parameters for each subsystem: carriage, recoil system, tube, and breech. This was followed by a test of hypothesis which tested whether sufficient information was available to reject the hypothesis that the required durability had been obtained. The subsystem durability was then used to compute replacement requirements over the system lifetime.

The climate belongs to the class of non-equilibrium forced and dissipative systems, for which most results of quasi-equilibrium statistical mechanics, including the fluctuation-dissipation theorem, do not apply. We show for the first time how the Ruelle linear response theory, developed for studying rigorously the impact of perturbations on general observables of non-equilibrium statistical mechanical systems, can be applied to analyze the climatic response. We choose as test bed the Lorenz 96 model, which has a well-recognized prototypical value. We recapitulate the main aspects of the response theory and propose some new results. We then analyze the frequency dependence of the response of both local and global observables to perturbations with localized as well as global spatial patterns. We derive analytically the asymptotic behaviour, validity of Kramers-Kronig relations, and sum rules for the susceptibilities, and related them to parameters describing the unperturbed properties of the system. We verify the theoretical predictions from the outputs of the simulations with great precision. The theory is used to explain differences in the response of local and global observables, in defining the intensive properties of the system and in generalizing the concept of climate sensitivity to all time scales. We also show how to reconstruct the linear Green function, which maps perturbations of general time patterns into changes in the expectation value of the considered observable. Finally, we propose a general methodology to study Climate Change problems by resorting to few, well selected simulations and discuss the specific case of surface temperature response to changes of the $CO_2$ concentration. This approach may provide a radically new perspective to study rigorously the problem of climate sensitivity and climate change.

This paper proposes a method to solve multivariable nonlinear optimization problem based on MCMC statistical sampling. Theoretical analysis proves that the maximum statistic converges to the maximum point of probability density. From this convergence property, we establish a newly algorithm to find the best solution of an optimization through largely MCMC sampling in condition that the exact generalized probability density function has been designed. The MCMC optimization algorithm needs less iterate variables reserved so that the computing speed is relatively high. Finally, we build a Markov chain model to demonstrate the dynamic movement of ladderlike labour transfer with multiparamter, and we practice this MCMC sampling optimization algorithm to find parameters estimations. The optimization results are reasonable and from which we obtain the short-term and long-term forecast of labour movements.

We show two fascinating topics lying between quantum information processing and statistical mechanics. First, we introduce an elaborated technique, the surface code, to prepare the particular quantum state with robustness against decoherence. Second, we show another interesting technique to employ quantum nature, quantum annealing. Through both of the topics, we would shed light on the birth of the interdisciplinary field between quantum mechanics and statistical mechanics.

In this work, we investigate the statistical computation of the Boltzmann entropy of statistical samples. For this purpose, we use both histogram and kernel function to estimate the probability density function of statistical samples. We find that, due to coarse-graining, the entropy is a monotonic increasing function of the bin width for histogram or bandwidth for kernel estimation, which seems to be difficult to select an optimal bin width/bandwidth for computing the entropy. Fortunately, we notice that there exists a minimum of the first derivative of entropy for both histogram and kernel estimation, and this minimum point of the first derivative asymptotically points to the optimal bin width or bandwidth. We have verified these findings by large amounts of numerical experiments. Hence, we suggest that the minimum of the first derivative of entropy be used as a selector for the optimal bin width or bandwidth of density estimation. Moreover, the optimal bandwidth selected by the minimum of the first derivative of entropy is purely data-based, independent of the unknown underlying probability density distribution, which is obviously superior to the existing estimators. Our results are not restricted to one-dimensional, but can also be extended to multivariate cases. It should be emphasized, however, that we do not provide a robust mathematical proof of these findings, and we leave these issues with those who are interested in them.

Journal of Statistical Computation and Simulation is an active peer-reviewed academic journal covering papers on computer algorithms related to probability or statistics, studies in statistical inference and the implementation of interactive statistical systems. It was established in 1972 and is published 18 times a year by Taylor & Francis. The journal publishes original research articles, methodological developments, and review papers that contribute to the understanding of computational statistics, simulation algorithms, statistical modeling, and the application of statistical methods to diverse fields such as finance, biology, engineering, social sciences, and environmental studies. It serves as a platform for researchers, statisticians, and data scientists to explore innovative computational and simulation techniques for statistical analysis, modeling, and inference, disseminating research, facilitating interdisciplinary collaborations, and informing the development of new statistical methodologies and software tools. Journal of Statistical Computation and Simulation can be found online at: www.tandfonline.com/journals/gscs20 The ISSN is: 0094-9655