Accurate Statistical Estimates Research Articles

Multisample Online Learning for Probabilistic Spiking Neural Networks.

Spiking neural networks (SNNs) capture some of the efficiency of biological brains for inference and learning via the dynamic, online, and event-driven processing of binary time series. Most existing learning algorithms for SNNs are based on deterministic neuronal models, such as leaky integrate-and-fire, and rely on heuristic approximations of backpropagation through time that enforces constraints such as locality. In contrast, probabilistic SNN models can be trained directly via principled online, local, and update rules that have proven to be particularly effective for resource-constrained systems. This article investigates another advantage of probabilistic SNNs, namely, their capacity to generate independent outputs when queried over the same input. It is shown that the multiple generated output samples can be used during inference to robustify decisions and to quantify uncertainty-a feature that deterministic SNN models cannot provide. Furthermore, they can be leveraged for training in order to obtain more accurate statistical estimates of the log-loss training criterion and its gradient. Specifically, this article introduces an online learning rule based on generalized expectation-maximization (GEM) that follows a three-factor form with global learning signals and is referred to as GEM-SNN. Experimental results on structured output memorization and classification on a standard neuromorphic dataset demonstrate significant improvements in terms of log-likelihood, accuracy, and calibration when increasing the number of samples used for inference and training.

Comparing spatial null models for brain maps

Technological and data sharing advances have led to a proliferation of high-resolution structural and functional maps of the brain. Modern neuroimaging research increasingly depends on identifying correspondences between the topographies of these maps; however, most standard methods for statistical inference fail to account for their spatial properties. Recently, multiple methods have been developed to generate null distributions that preserve the spatial autocorrelation of brain maps and yield more accurate statistical estimates. Here, we comprehensively assess the performance of ten published null frameworks in statistical analyses of neuroimaging data. To test the efficacy of these frameworks in situations with a known ground truth, we first apply them to a series of controlled simulations and examine the impact of data resolution and spatial autocorrelation on their family-wise error rates. Next, we use each framework with two empirical neuroimaging datasets, investigating their performance when testing (1) the correspondence between brain maps (e.g., correlating two activation maps) and (2) the spatial distribution of a feature within a partition (e.g., quantifying the specificity of an activation map within an intrinsic functional network). Finally, we investigate how differences in the implementation of these null models may impact their performance. In agreement with previous reports, we find that naive null models that do not preserve spatial autocorrelation consistently yield elevated false positive rates and unrealistically liberal statistical estimates. While spatially-constrained null models yielded more realistic, conservative estimates, even these frameworks suffer from inflated false positive rates and variable performance across analyses. Throughout our results, we observe minimal impact of parcellation and resolution on null model performance. Altogether, our findings highlight the need for continued development of statistically-rigorous methods for comparing brain maps. The present report provides a harmonised framework for benchmarking and comparing future advancements.

Assessing AMS-RF Test Quality by Defect Simulation

In safety critical applications, there is a demand for estimating defect coverage in order to meet stringent quality levels. However, defect simulation of complex AMS-RF circuits is computationally expensive since achieving a good confidence interval requires sampling many defects. In this paper, we show in practical cases of study that it is beneficial to complement defect coverage with fault coverage and assess the severity of defect escapes to get a complete picture of test quality. The computational burden of defect and fault simulations is taken into account and accurate statistical estimates of defect and fault escapes are provided to allow safe early stopping of the simulations.

MoMo: discovery of statistically significant post-translational modification motifs.

Post-translational modifications (PTMs) of proteins are associated with many significant biological functions and can be identified in high throughput using tandem mass spectrometry. Many PTMs are associated with short sequence patterns called 'motifs' that help localize the modifying enzyme. Accordingly, many algorithms have been designed to identify these motifs from mass spectrometry data. Accurate statistical confidence estimates for discovered motifs are critically important for proper interpretation and in the design of downstream experimental validation. We describe a method for assigning statistical confidence estimates to PTM motifs, and we demonstrate that this method provides accurate P-values on both simulated and real data. Our methods are implemented in MoMo, a software tool for discovering motifs among sets of PTMs that we make available as a web server and as downloadable source code. MoMo re-implements the two most widely used PTM motif discovery algorithms-motif-x and MoDL-while offering many enhancements. Relative to motif-x, MoMo offers improved statistical confidence estimates and more accurate calculation of motif scores. The MoMo web server offers more proteome databases, more input formats, larger inputs and longer running times than the motif-x web server. Finally, our study demonstrates that the confidence estimates produced by motif-x are inaccurate. This inaccuracy stems in part from the common practice of drawing 'background' peptides from an unshuffled proteome database. Our results thus suggest that many of the papers that use motif-x to find motifs may be reporting results that lack statistical support. The MoMo web server and source code are provided at http://meme-suite.org. Supplementary data are available at Bioinformatics online.

Reference point based evolutionary multi-objective optimization with dynamic resampling for production systems improvement

PurposeStochastic simulation is a popular tool among practitioners and researchers alike for quantitative analysis of systems. Recent advancement in research on formulating production systems improvement problems into multi-objective optimizations has provided the possibility to predict the optimal trade-offs between improvement costs and system performance, before making the final decision for implementation. However, the fact that stochastic simulations rely on running a large number of replications to cope with the randomness and obtain some accurate statistical estimates of the system outputs, has posed a serious issue for using this kind of multi-objective optimization in practice, especially with complex models. Therefore, the purpose of this study is to investigate the performance enhancements of a reference point based evolutionary multi-objective optimization algorithm in practical production systems improvement problems, when combined with various dynamic re-sampling mechanisms.Design/methodology/approachMany algorithms consider the preferences of decision makers to converge to optimal trade-off solutions faster. There also exist advanced dynamic resampling procedures to avoid wasting a multitude of simulation replications to non-optimal solutions. However, very few attempts have been made to study the advantages of combining these two approaches to further enhance the performance of computationally expensive optimizations for complex production systems. Therefore, this paper proposes some combinations of preference-based guided search with dynamic resampling mechanisms into an evolutionary multi-objective optimization algorithm to lower both the computational cost in re-sampling and the total number of simulation evaluations.FindingsThis paper shows the performance enhancements of the reference-point based algorithm, R-NSGA-II, when augmented with three different dynamic resampling mechanisms with increasing degrees of statistical sophistication, namely, time-based, distance-rank and optimal computing buffer allocation, when applied to two real-world production system improvement studies. The results have shown that the more stochasticity that the simulation models exert, the more the statistically advanced dynamic resampling mechanisms could significantly enhance the performance of the optimization process.Originality/valueContributions of this paper include combining decision makers’ preferences and dynamic resampling procedures; performance evaluations on two real-world production system improvement studies and illustrating statistically advanced dynamic resampling mechanism is needed for noisy models.

Spatially filtered ridge regression (SFRR): A regression framework to understanding impacts of land cover patterns on urban climate

AbstractUnderstanding the impacts of land cover pattern on the heat island effect is essential for sustainable urban development. Conventional model fitting methods have restricted ability to produce accurate estimates of the land cover‐temperature association due to the lack of procedures to address two important issues: spatial dependence in proximal spatial units and high correlations among predictor variables. In this study, we seek to develop an effective framework called spatially filtered ridge regression (SFRR) to estimate the variations in the quantity and distribution of land surface temperature (LST) in response to various land cover patterns. The SFRR effectively integrates spatial autoregressive models and ridge regression, and it achieves reliable parameter estimates with substantially reduced mean square errors. We show this by comparing the performance of the SFRR to other widely adopted models using Monte Carlo simulation followed by an empirical study over central Phoenix. Results highlight the great potential of the SFRR in producing accurate statistical estimates, providing a positive step toward informed and unbiased decision‐making across a wide variety of disciplines. (Code and data to reproduce the results in the case study are available at: https://github.com/cfan13/SFRRTGIS.git.)

Statistical Analysis of Tourist Food Supply Industry

Objective: The use of statistical methods of analysis in relation to the tourism industry supply. Methods: The statistical method of observation and data grouping was used as well as the method of general indicators. Results: The contemporary role of public catering was disclosed as a branch of economy. Features of the tourist food supply were shown. The statistical groupings of public catering services were presented on the basis of international and Russian classifiers. A brief characteristic of the organizational forms of tourist food supply was given. Estimates of the share of turnover of tourist food supply were made in the context of the analysis of the dynamics of turnover of catering Scientific novelty: For the first time a comparative analysis of classification of public catering services in the Russian and international statistics was conducted. The impossibility to obtain accurate statistical estimates of the share of the tourist –consumers and tourist food supply turnover in the general structure of consumption of public catering services was proved. Practical value: The ability to use the broad grouping method and statistical analysis of data in studies of trends in the development of the tourist industry. DOI: 10.5901/mjss.2014.v5n18p269

Albanian Migration to the U.S.A. Geo-Historical Research Contributions

Typology of the reasons for migration, dominated by forced migration (mainly wars) and labor migration, intensified by the late nineteenth century and early twentieth century. Massive migration periods are: the Roman period (less documented), Middle Ages (XIV-XV century); period between the Albanian national revival and independence; periods during world wars and the period after the fall of Communism (1990). While migrations tipizohen today because of work and living better. Varies according to geography and world developments, especially regional developments (Balkan Mediterranean).Characteristics of today's migration are becoming almost universal. Accurate statistical estimates are difficult (from 150 thousand to 500 thousand) because of its complex integrations, sources of social organizations and illegal migration in certain periods. Selection of emigration countries related to geographical proximity (Greece, Italy); cultural and linguistic proximity; historical ties; economic developments; accessability; regulatory incentives to migration policies, making phenomenon spontaneous and problematic since to the country of origin up to the destination. Referring to official statistics 95% of immigrants are located in Europe. DOI: 10.5901/mjss.2014.v5n2p441

Spatial regression techniques for inter‐population data: studying the relationships between morphological and environmental variation

Understanding the importance of environmental dimensions behind the morphological variation among populations has long been a central goal of evolutionary biology. The main objective of this study was to review the spatial regression techniques employed to test the association between morphological and environmental variables. In addition, we show empirically how spatial regression techniques can be used to test the association of cranial form variation among worldwide human populations with a set of ecological variables, taking into account the spatial autocorrelation in data. We suggest that spatial autocorrelation must be studied to explore the spatial structure underlying morphological variation and incorporated in regression models to provide more accurate statistical estimates of the relationships between morphological and ecological variables. Finally, we discuss the statistical properties of these techniques and the underlying reasons for using the spatial approach in population studies.

Observability analysis and active control for airborne SLAM

An unmanned aerial vehicle (UAV) is tasked to explore an unknown environment and to map the features it finds, but must do so without the use of infrastructure-based localisation systems such as GPS, or any a priori terrain data. The UAV navigates using a statistical estimation technique known as simultaneous localisation and mapping (SLAM) which allows for the simultaneous estimation of the location of the UAV as well as the location of the features it sees. SLAM offers a unique approach to vehicle localisation with potential applications including planetary exploration, or when GPS is denied (for example under intentional GPS jamming, or applications where GPS signals cannot be reached), but more importantly can be used to augment already existing systems to improve robustness to navigation failure. One key requirement for SLAM to work is that it must reobserve features, and this has two effects: firstly, the improvement of the location estimate of the feature; and secondly, the improvement of the location estimate of the platform because of the statistical correlations that link the platform to the feature. So our UAV has two options; should it explore more unknown terrain to find new features, or should it revisit known features to improve localisation quality. These options are instantiated into the online path planner for the UAV. We present the SLAM algorithm and evaluate two important properties about the algorithm which assist in developing a path planning module for the UAV. The first of these is the use of the probabilistic measure of "entropy" as an information-based measure of the certainty in the map and vehicle locations, and is used as a utility function for planning the UAVs trajectory and determining the order in which features in the map are observed. The second is an observability analysis of SLAM which presents the unobservable states which are dependent on vehicle maneuvers. The analysis dictates the type of manoeuvres required by the UAV while observing features in order to maintain accurate statistical estimates of the map and vehicle location. This has the effect of reducing the action space that the path planner needs to search over. Using these two properties, we demonstrate an online path planner that intelligently plans the vehicle's trajectory while exploring unknown terrain in order to maximise the quality of both the map and vehicle location. Results of the online path planning algorithm are presented using a 6-DoF simulator of our UAV. The results show that the vehicle localisation errors are constrained and that the number of features and the size of the map steadily grows during the flight.

Empirical Bayes hierarchical models for regularizing maximum likelihood estimation in the matrix Gaussian Procrustes problem

Procrustes analysis involves finding the optimal superposition of two or more "forms" via rotations, translations, and scalings. Procrustes problems arise in a wide range of scientific disciplines, especially when the geometrical shapes of objects are compared, contrasted, and analyzed. Classically, the optimal transformations are found by minimizing the sum of the squared distances between corresponding points in the forms. Despite its widespread use, the ordinary unweighted least-squares (LS) criterion can give erroneous solutions when the errors have heterogeneous variances (heteroscedasticity) or the errors are correlated, both common occurrences with real data. In contrast, maximum likelihood (ML) estimation can provide accurate and consistent statistical estimates in the presence of both heteroscedasticity and correlation. Here we provide a complete solution to the nonisotropic ML Procrustes problem assuming a matrix Gaussian distribution with factored covariances. Our analysis generalizes, simplifies, and extends results from previous discussions of the ML Procrustes problem. An iterative algorithm is presented for the simultaneous, numerical determination of the ML solutions.

Finding Protein and Nucleotide Similarities with FASTA

AbstractThe FASTA package provides a comprehensive set of similarity searching programs, similar to those provided by the BLAST package, and some additional programs that are not provided by BLAST for searching with short peptides and oligonucleotides. The FASTA programs work with a wide variety of database formats, including mySQL sequence databases. FASTA provides very accurate statistical significance estimates, and is more sensitive than BLASTN when comparing DNA sequences. These protocols describe how to use the FASTA programs to characterize protein and DNA sequences, using protein:protein, protein:DNA, and DNA:DNA comparisons.

Computing Multiple Sequence/Structure Alignments with theT‐Coffee Package

AbstractThe FASTA package provides a comprehensive set of similarity searching programs, similar to those provided by the BLAST package, and some additional programs for searching with short peptides and oligonucleotides that are not provided by BLAST. The FASTA programs work with a wide variety of database formats, including mySQL sequence databases. FASTA provides very accurate statistical significance estimates, and is more sensitive than BLASTN when comparing DNA sequences. These protocols describe how to use the FASTA programs to characterize protein and DNA sequences, using protein:protein, protein:DNA, and DNA:DNA comparisons.

Flexible sequence similarity searching with the FASTA3 program package.

The FASTA3 and FASTA2 packages provide a flexible set of sequence-comparison programs that are particularly valuable because of their accurate statistical estimates and high-quality alignments. Traditionally, sequence similarity searches have sought to ask one question: "Is my query sequence homologous to anything in the database?" Both FASTA and BLAST can provide reliable answers to this question with their statistical estimates; if the expectation value E is < 0.001-0.01 and you are not doing hundreds of searches a day, the answer is probably yes. In general, the most effective search strategies follow these rules: 1. Whenever possible, compare at the amino acid level, rather than the nucleotide level. Search first with protein sequences (blastp, fasta3, and ssearch3), then with translated DNA sequences (fastx, blastx), and only at the DNA level as a last resort (Table 5). 2. Search the smallest database that is likely to contain the sequence of interest (but it must contain many unrelated sequences for accurate statistical estimates). 3. Use sequence statistics, rather than percent identity or percent similarity, as your primary criterion for sequence homology. 4. Check that the statistics are likely to be accurate by looking for the highest-scoring unrelated sequence, using prss3 to confirm the expectation, and searching with shuffled copies of the query sequence [randseq, searches with shuffled sequences should have E approx 1.0]. 5. Consider searches with different gap penalties and other scoring matrices. Searches with long query sequences against full-length sequence libraries will not change dramatically when BLOSUM62 is used instead of BLOSUM50 (20), or a gap penalty of -14/-2 is used in place of -12/-2. However, shallower or more stringent scoring matrices are more effective at uncovering relationships in partial sequences (3,18), and they can be used to sharpen dramatically the scope of the similarity search. However, as illustrated in the last section, the E value is only the first step in characterizing a sequence relationship. Once one has confidence that the sequences are homologous, one should look at the sequence alignments and percent identities, particularly when searching with lower quality sequences. When sequence alignments are very short, the alignment should become more significant when a shallower scoring matrix is used, e.g., BLOSUM62 rather than BLOSUM50 (remember to change the gap penalties). Homology can be reliably inferred from statistically significant similarity. Whereas homology implies common three-dimensional structure, homology need not imply common function. Orthologous sequences usually have similar functions, but paralogous sequences often acquire very different functional roles. Motif databases, such as PROSITE (21), can provide evidence for the conservation of critical functional residues. However, motif identity in the absence of overall sequence similarity is not a reliable indicator of homology.

Time-Variability of NOx Emissions from Portland Cement Kilns

Due to the presence of autocorrelation between sequentially measured nitrogen oxide (NOx) concentrations in stack gas from portland cement kilns, the determination of the average emission rates and the uncertainty of the average has been improperly calculated by the industry and regulatory agencies. Documentation of permit compliance, establishment of permit levels, and the development and testing of control techniques for reducing NOx emissions at specific cement plants requires accurate and precise statistical estimates of parameters such as means, standard deviations, and variances. Usual statistical formulas such as for the variance of the sample mean only apply if sequential measurements of NOx emissions are independent. Significant autocorrelation of NOx emission measurements revealed that NOx concentration values measured by continuous emission monitors are not independent but can be represented by an autoregressive, moving average (ARMA) time series. Three orders of time-variability of NOx emission rates were determined from examination of continuous emission measurements from several cement kilns. Long-term variations are related to changes in process control, feed composition, fuel composition, and types of product produced and are reflected by nonperiodic drift in the time series. Intermediate-term variations result from changes in process control and operator technique. Very short-term variations, which are not normally visible due to the averaging process applied to data collection, are related to the dynamics of the flame. Autocorrelation effects within the emission rates extend over a period of 8−10 h. The high levels of autocorrelation observed between sequential readings result in underestimating the variance of the average emission rate unless autocorrelation effects are considered. Although thousands of NOx measurements may be recorded, autocorrelation of sequential measurements implies that many of them are redundant.

Fast simulation of networks of queues with effective and decoupling bandwidths

A significant difficulty when using Monte Carlo simulation for the performance analysis of communication networks is the long runtime required to obtain accurate statistical estimates. Under the proper conditions, importance sampling (IS) is a technique that can speed up simulations involving rare events in network (queuing) systems. Large speed-up factors in simulation runtime can be obtained with IS if the modification or bias of the underlying probability measures of certain random processes is carefully chosen. Fast simulation methods based on large deviation theory (LTD) have been successfully applied in many cases. In this paper, we set up an IS-based simulation of various elementary network topologies. These configurations are frequenly encountered in broadband ATM-based network components such as switches and multiplexers. Our objective in this study is to obtain the optimal or near-optimal biasing parameter values of the arrival processes for the importance sampling simulation. For this purpose we appropriately apply a technique presented by Chang et al. for certain portions of the networks (intree) while we develop a new algorithm, inspired by the work of De Veciana et al. on decoupling bandwidths, for the non-intree portion of the network.

Empirical statistical estimates for sequence similarity searches

The FASTA package of sequence comparison programs has been modified to provide accurate statistical estimates for local sequence similarity scores with gaps. These estimates are derived using the extreme value distribution from the mean and variance of the local similarity scores of unrelated sequences after the scores have been corrected for the expected effect of library sequence length. This approach allows accurate estimates to be calculated for both FASTA and Smith-Waterman similarity scores for protein/protein, DNA/DNA, and protein/translated-DNA comparisons. The accuracy of the statistical estimates is summarized for 54 protein families using FASTA and Smith-Waterman scores. Probability estimates calculated from the distribution of similarity scores are generally conservative, as are probabilities calculated using the Altschul-Gish λ, K, and H parameters. The performance of several alternative methods for correcting similarity scores for library-sequence length was evaluated using 54 protein superfamilies from the PIR39 database and 110 protein families from the Prosite/SwissProt rel. 34 database. Both regression-scaled and Altschul-Gish scaled scores perform significantly better than unscaled Smith-Waterman or FASTA similarity scores. When the Prosite/SwissProt test set is used, regression-scaled scores perform slightly better; when the PIR database is used, Altschul-Gish scaled scores perform best. Thus, length-corrected similarity scores improve the sensitivity of database searches. Statistical parameters that are derived from the distribution of similarity scores from the thousands of unrelated sequences typically encountered in a database search provide accurate estimates of statistical significance that can be used to infer sequence homology.

Maximum likelihood and optimum location of observation sites in geodetic and spatial surveying

In geodetic and spatial surveying, accurate statistical es-timates of the Cartesian coordinates of a stationary target depend, in general, on such factors as target position, number and type of instruments, their location, their accuracy, and their mix. Direct measurements are assumed to be made in elevation, azimuth, and range with errors independently and normally distributed. For a mix of instruments, theoretical arguments are established using maximum likelihood estimation to determine the optimal siting of the instruments which minimizes (GDOP)2 or the square of the geo-metric dilution of precision = sum of the variances of the estimates in the three orthogonal directions.