BibSonomy publications for /tag/statisticsThu Sep 04 15:27:07 CEST 2008Wildlife Society Bulletin4875--881Landscape Fragmentation Assessment Using a Single Measure282000spatial landscape fragmentation geostatistics statistics Measurement of fragmentation is crucial for determining its consequences and to develop policy for nature conservation. We propose a fragmentation measure |φ| which combines, using a multidimensional Euclidean distance, 4 main characteristics of fragmented landscapes: total habitat area, total habitat perimeter, number of patches, and patch isolation. Its properties can be summarized as: 1) |φ| reflects the overall fragmentation status; 2) every component of |φ| is accepted as a measure of fragmentation; 3) every component of |φ| is a normalized variable; 4) every component of |φ| is easy to compute; 5) average patch size, interior habitat, and habitat connectedness are included indirectly in |φ|; 6) |φ| is independent of the land-use type; and 7) |φ| can be calculated for raster and vector data. We show that the normalized values composing |φ| prevent misinterpretation of features as fragment number or boundary length. A sensitivity analysis, based upon artificial patterns, showed that increasing fragmentation is correlated with smaller values of |φ|. Wildlife managers are encouraged to use |φ| for objective evaluation of fragmented landscapes.Thu Sep 04 14:52:17 CEST 2008JOURNAL OF GEOPHYSICAL RESEARCHFractal properties of isolines at varying altitude revealing different dominant geological processes on Earth 1132008physics 2008 geophysics geomorphology statistics myown isoline fracal fractals Geometrical properties of landscapes result from the geological processes that have acted through time. The quantitative analysis of natural relief represents an objective form of aiding in the visual interpretation of landscapes, as studies on coastlines, river networks, and global topography, have shown. Still, an open question is whether a clear relationship between the quantitative properties of landscapes and the dominant geomorphologic processes that originate them can be established. In this contribution, we show that the geometry of topographic isolines is an appropriate observable to help disentangle such a relationship. A fractal analysis of terrestrial isolines yields a clear identification of trenches and abyssal plains, differentiates oceanic ridges from continental slopes and platforms, localizes coastlines and river systems, and isolates areas at high elevation (or latitude) subjected to the erosive action of ice. The study of the geometrical properties of the lunar landscape supports the existence of a correspondence between principal geomorphic processes and landforms. Our analysis can be easily applied to other planetary bodies.Mon Sep 01 14:32:20 CEST 2008The American Journal of Psychology3/4441-471The Proof and Measurement of Association between Two Things1001987statistics ranking correlation Tue Aug 26 19:00:22 CEST 2008Cultural Statistics, http://epp.eurostat.ec.europa.eu/, (retrieved 23/08/2008)2007culture statistics Thu Aug 21 17:54:06 CEST 2008The Annals of Applied Probabilityaug3577--602Hidden Markov Random Fields51995statistics markovrandomfields bayes models imageprocessing A noninvertible function of a first-order Markov process or of a nearest-neighbor Markov random field is called a hidden Markov model. Hidden Markov models are generally not Markovian. In fact, they may have complex and long range interactions, which is largely the reason for their utility. Applications include signal and image processing, speech recognition and biological modeling. We show that hidden Markov models are dense among essentially all finite-state discrete-time stationary processes and finite-state lattice-based stationary random fields. This leads to a nearly universal parameterization of stationary processes and stationary random fields, and to a consistent nonparametric estimator. We show the results of attempts to fit simple speech and texture patterns.Thu Aug 21 17:50:27 CEST 2008Computational Statistics & Data AnalysisoctLoads of interesting reference within.2855--868Hidden Markov random field models for TCA image analysis522007statistics models Gabor HiddenMarkovFields bayes Tooth Cementum Annulation (TCA) is an age estimation method carried out on thin cross sections of the root of mammalian teeth. Age is computed by adding the tooth eruption age to the count of annual incremental lines which are called tooth rings and appear in the cementum band. The number of rings is computed from an intensity (gray scale) image of the cementum band, by estimating the average ring width and then dividing the area of the cementum band by this estimate. The ring width is estimated by modelling the image by a hidden Markov random field, where intensities are assumed to be pixelwise conditionally independent and normally distributed, given a Markov random field of hidden binary labels, representing the"true scene". To incorporate image macro-features (the long-range dependence among intensities and the quasi-periodicity in the placement of tooth rings), the label random field is defined by an energy function that depends on a parametric Gabor filter, convolved with the true scene. The filter parameter represents the unknown of main interest, i.e. the average width of the rings. The model is estimated through an EM algorithm, relying on the mean field approximation of the hidden label distribution and allows to predict the locations of the rings in the image.Tue Aug 19 17:16:00 CEST 200811th European Colloquium on Quantitative and Theoretical Geography. Durham Castle, UKThe Metropolis-Hastings algorithm, a handy tool for the practice of environmental model estimation : illustration with biochemical oxygen demand data 2001uncertainty models model inference bayes statistics Tue Aug 19 15:07:09 CEST 2008Journal of Econometrics001-2183--206Bayes inference in regression models with ARMA (p, q) errors641994models mcmc statistics regression inference Bayes ARMA Tue Aug 19 15:04:38 CEST 2008The American StatisticianNov4327-335Understanding the Metropolis-Hastings Algorithm491995uncertainty kalmanfilter metropolishastings mcmc statistics bayes We provide a detailed, introductory exposition of the Metropolis-Hastings algorithm, a powerful Markov chain method to simulate multivariate distributions. A simple, intuitive derivation of this method is given along with guidance on implementation. Also discussed are two applications of the algorithm, one for implementing acceptance-rejection sampling when a blanketing function is not available and the other for implementing the algorithm with block-at-a-time scans. In the latter situation, many different algorithms, including the Gibbs sampler, are shown to be special cases of the Metropolis-Hastings algorithm. The methods are illustrated with examples.Tue Aug 12 15:41:04 CEST 2008Journal of Statistical Software9121--20Reshaping Data with the reshape Package212007statistics software 15This paper presents the reshape package for R, which provides a common framework for many types of data reshaping and aggregation. It uses a paradigm of ‘melting’ and ‘casting’, where the data are ‘melted’ into a form which distinguishes measured and iden- tifying variables, and then ‘cast’ into a new shape, whether it be a data frame, list, or high dimensional array. The paper includes an introduction to the conceptual framework, practical advice for melting and casting, and a case study. Wed Aug 06 11:08:26 CEST 2008The Balancing Act: Combining Symbolic and Statistical Approaches to Language1--26{Statistical Methods and Linguistics}1996linguistics statistics classic Fri Jul 18 14:25:32 CEST 2008Erfassung und Analyse von Tierpopulationen - Eine Einführung in Methoden und Anwendungsmöglichkeiten im Naturschutzin prepstatistics metapopulation dispersal schätzer recapture Inhaltsverzeichnis Vorwort 1 Einführung 2 Population und Metapopulation 2.1 Konzepte und Abgrenzung 2.2 Populationsparameter 3 Methodenwahl und Versuchsplanung 3.1 Methodenwahl und Anwendungsmöglichkeiten im Naturschutz 3.2 Versuchsplanung und Datenprotokollierung 4 Relative Häufigkeit 4.1 Generelle Grundlagen 4.2 Häufigkeitsindices 4.2.1 Zählungen von Tierspuren 4.2.2 Zählungen von Tieren 4.2.3 Fang von Tieren 4.3 Häufigkeitsklassen 4.4 Schätzmethoden 4.4.1 Linientaxierung und Punkt-Stop-Methoden 4.4.2 Nachweisfrequenzen 4.4.3 Nachbarschaftsdistanzen 4.5 Korrekturfaktoren 5 Absolute Häufigkeit 5.1 Vermutungen 5.2 Totalerfassung 5.2.1 Totalerfassung im Gesamtgebiet 5.2.2 Totalerfassung auf Probeflächen 5.2.2.1 Homogene Untersuchungsgebiete 5.2.2.2 Stratifizierte Erfassung in heterogenen Untersuchungsgebieten 5.3 Distanzerfassungen zur Schätzung von Populationsgröße und -dichte 5.3.1 Linientransektschätzungen 5.3.2 Punkt-Radius-Methode 5.4 Abfangen und Hinzufügen von Individuen 5.4.1 Selektives Abfangen und Hinzufügen (KELKER’s Methode) 5.4.2 Unselektives Abfangen (Fang-Aufwand- Methoden) 6 Reproduktion und Mortalität 6.1 Reproduktion 6.2 Lebenserwartung 6.3 Mortalität 6.4 Lebenstafeln 7 Markierung-Wiederfang-Analysen 7.1 Grundannahmen von Markierung- Wiederfang-Analysen 7.2 Geschlossene Populationen (Populationsgröße) 7.2.1 LINCOLN-PETERSEN-Schätzung 7.2.2 Fangfrequenzmodelle 7.2.3 BAYES’sche Schätzverfahren 7.2.4 Modell CAPTURE 7.3 Populationsdichte 7.4 Offene Populationen 7.4.1 Mindest-Populationsgröße und Mindest- Überlebensraten 7.4.2 JOLLY-SEBER-Modell 7.4.3 MANLY-PARR-Modell 7.4.4 Robuster Versuchsplan 7.4.5 Von der Tagespopulationsgröße zur Gesamtpopulationsgröße 7.4.6 Ringfund- und Jagdmarkenanalysen 7.4.7 Vergleich von Mortalitätsraten für unterschiedliche Zeiträume 7.4.8 Separation von Emigration und Mortalität 8 Aktivitätsraum und Dispersion 9 Artenzahl und relative Häufigkeit von Arten Appendix I - Bezugsquellen von Computerprogrammen Appendix II - Computerprogramme Literatur StichwortverzeichnisThu Jul 10 17:12:31 CEST 2008New York, NY, USAWWW '08: Proceeding of the 17th international conference on World Wide Web327--336Flickr tag recommendation based on collective knowledge2008flickr co-occurrence yahoo wordnet www2008 tags recommendation tagging statistics imported Tue Jul 08 11:55:35 CEST 2008New York, NY, USAWSDM '08: Proceedings of the international conference on Web search and web data mining195--206Can social bookmarking improve web search?2008delicious data statistics folksonomy tagging search Thu Jun 19 17:35:00 CEST 2008International Journal of Knowledge-Based and Intelligent Engineering Systems5337--346A novel approach to decoding: Exploiting anticipated attack information using genetic programming102006genetic Statistics Transform Programming Watermarking, Decoder, algorithms, and (DCT), Genetic Sufficient (GP), Discrete Cosine programming, In a water marking system, the decoder structures are mostly fixed. They do not account for the normal processing or intentional attacks. In the present work, a method of automatically modifying the decoder structure in accordance to the given cover image and conceivable attack is illustrated. The proposed Genetic Programming based watermark decoding scheme is a blind one. It exploits the search space regarding types of dependencies of the decoder on different factors. Especially, information pertaining to watermarked cover coefficients is utilized to reduce host interference, while the conceivable-attack information is utilized to circumvent the anticipated distortion. The actual performance of the genetic decoder is assessed through experiments, which justify the use of intelligent search techniques in signal detection/decoding. Simulation results show that the resultant genetic decoder has superior performance as compared to the conventional decoder against the attacks of Checkmark benchmark.Thu Jun 19 17:35:00 CEST 2008Computers and Chemical Engineering28 February3413--425Non-linear principal components analysis using genetic programming231999component multivariate methods, distillation principal analysis, genetic nonlinear programming, reduction, algorithms, mathematical statistical data plants, systems, statistics, operations, statistics columns, chemical Principal components analysis (PCA) is a standard statistical technique, which is frequently employed in the analysis of large highly correlated data sets. As it stands, PCA is a linear technique which can limit its relevance to the non-linear systems frequently encountered in the chemical process industries. Several attempts to extend linear PCA to cover non-linear data sets have been made, and will be briefly reviewed in this paper. We propose a symbolically oriented technique for non-linear PCA, which is based on the genetic programming (GP) paradigm. Its applicability will be demonstrated using two simple non-linear systems and data collected from an industrial distillation column.Thu Jun 19 17:35:00 CEST 2008New YorkGECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference9-13 July889How Statistics Can Help In Limiting The Number Of Fitness Cases In Genetic Programming2002statistics fitness Cases, entropy, poster paper, genetic programming, algorithms, Thu Jun 19 16:22:54 CEST 2008New York; LondonApplied spatial data analysis with R--Applied spatial data analysis with R2008spatial_statistics R statistics Bivand Tue Jun 03 22:07:05 CEST 2008Cambridge, MA, USAComputational Linguistics195--101The kappa statistic: a second look302004statistics nlp In recent years, the kappa coefficient of agreement has become the de facto standard for evaluating intercoder agreement for tagging tasks. In this squib, we highlight issues that affect κ and that the community has largely neglected. First, we discuss the assumptions underlying different computations of the expected agreement component of κ. Second, we discuss how prevalence and bias affect the κ measure.Sun Jun 01 16:51:41 CEST 20082007/12/2721CNNIC Releases 2007 Survey Report on China Weblog Market Number of Blog Writers Reaches 47 million Equaling One Fourth of Total NetizensWebsite2007statistics internet_user blog internet netizens blogging China On Dec. 26th, 2007, CNNIC published “the Survey Report on Blogs in China 2007”. According to the report, by the end of Nov. 2007, the number of blog spaces has reached 72.82 million in China, and with 47 million blog writers, it is reaching one fourth of the total netizens. This indicates the rapid growth of the blog market in China. The survey statistics show that by the end of Nov. 2007, the number of blog spaces has reached 72.82 million in China, while that of blog writers has totaled 47 million, which means that one out of every 30 Chinese, or one out of four netizens writes blogs. Also, the active blog writers have taken up 36% of the total blog writers, approximately 17 million, and the number of valid blog spaces of the active blog users is 28.75 million. By the end of 2006, the number of blog writers was 17.5 million, and within one year the increasement reached nearly 30 million, indicating the large-scale growth in number of the blog writer group. However, as indicated by the survey, the future growth of the blogs will slow down: 65% of the investigated said they only registered one blog, and showed little tendency to register another in half a year; only 11% of the investigated said they would definitely register a blog in the future half a year. The survey also indicates that the blog covers almost all the areas of people’s daily life, including the cultural, military, economic, tourist, living areas, etc. therefore the blog has also become the important channel for people to obtain information. Among the blog writers surveyed in this report, the male gender take up 43% while the female is 57%, which is contrary to the traditional gender ratio of 55:45 (male: female) among netizens, and shows a higher popularity of blogs among female users. In terms of major content the blogs covered, 47% of the blogs are written about the inner monologues or record of emotions of the writers. Next are the narration of daily life, personal interests and hobbies. Most of the blogs are for the writers to record their own life status and conduct self demonstration, with the blogs having a more and more obvious tendency of self-media attributes. The survey also finds that among the motives for reading blogs, entertainment comes first, which is reported to occupy 43% of the surveyed. It will become one of the directions for further probing of the profitable blog model to make full use of the participative, interactive, and circulative characteristics of the blog and dig out the entertainment value of blogs. In addition, although blogs have become an important information channel, the readers obviously have more confident in online news than in blog content. 63% of the surveyed said they trust more in the online news while only 20% have more trust in the blog content. This shows that compared to online news, the blog content at present calls for improvement in its credibility. And as a kind of transmission media, the blogs need the self discipline of the blog writers in order to raise the credibility. The survey shows, in terms of the methods that blog writers choose to access most frequently visited blogs, the primary choice is through the links on the blogs and through the browser bookmarks. 12% of the blog writers directly key in the blog addresses in the address bar, which means 5.64 million blog writers browse their blogs directly by keying in the addresses of the blogs. Judging from the accessing habits, the market of individual domain names looks optimistic in the blog area. Meanwhile, 66% of the surveyed expressed interests in using the individual domain names. And as many as 31% of the surveyed said that if a blog website offers the simple or customized blog domain names at 10 yuan/name, they would consider changing the blog platforms. So for the 1 yuan registration price of .CN domain names, the individual .CN domain names would have a lot to commit itself to in the blog area. The function that blog writers use most frequently is the upload/display function of pictures, also with a high frequency in using music and videos on the blog. Among the new functions or tools the writers mostly long for, the blog writers wish the most is to expand the storage of the blogs space, and being provided with the customized design models of the blog. Meanwhile，10% of the writers responded that they are willing to buy the blog space service. This indicates that the functions of blogs have set apart from the monotone written record, and headed for multi-functions. With the continuous progress in Internet technology, the continuous expansion of Internet cyberspace, and the continuous raise in networking speed, the future blogs will include various technologies such as character, images, audio, video, flash, etc., combing the instant messaging, social network, online shopping and etc., demonstrating having the tendency of becoming the all-around personal space which cover all aspects of information of the blog writer. China Internet Network Information Center (CNNIC), the state network information center of China, was founded as a non-profit organization on Jun. 3rd 1997. CNNIC takes orders from the Ministry of Information Industry (MII) to conduct daily business, while it was administratively operated by Chinese Academy of Sciences (CAS). Computer Network Information Center of Chinese Academy of Sciences takes the responsibility of running and administrating CNNIC. CNNIC Steering Committee..statisticsCommunity for tag(s) statistics