N. I. FisherCambridge University PressEdition: New Ed, 10/12/1995EAN 9780521568906, ISBN10: 0521568900Paperback, 296 pages, 24.7 x 17.4 x 1.7 cmLanguage: EnglishData measured as angles or two-dimensional orientations are found almost everywhere in science. They commonly arise in biology, geography, geophysics, medicine, meteorology and oceanography, and many other areas. Examples of such data include departure directions of birds from release points, fracture plane orientations, the directional movement of animals after stimulation, wind and ocean current directions, and biorhythms. Statistical methods for handling such data have developed rapidly in the last twenty years, particularly data display, correlation, regression and analysis of tempered or spatially structured data. Further, some of the exciting modern developments in general statistical methodology, particularly nonparametric smoothing methods and bootstrap-based methods, have contributed significantly to relatively intractable data analysis problems. This book provides a unified and up-to-date account of techniques for handling circular data.Preface1. The purpose of the book2. Survey of contents3. How to use the book4. Notation, terminology and conventions5. AcknowledgementsPart I. IntroductionPart II. Descriptive Methods2.1. Introduction2.2. Data display2.3. Simple summary quantities2.4. Modifications for axial dataPart III. Models3.1. Introduction3.2. Notationtrigonometric moments3.3. Probability distributions on the circlePart IV. Analysis of a Single Sample of Data4.1. Introduction4.2. Exploratory analysis4.3. Testing a sample of unit vectors for uniformity4.4. Nonparametric methods for unimodal data4.5. Statistical analysis of a random sample of unit vectors from a von Mises distribution4.6. Statistical analysis of a random sample of unit vectors from a multimodal distribution4.7. Other topicsPart V. Analysis of Two or More Samples, and of Other Experimental Layouts5.1. Introduction5.2. Exploratory analysis5.3. Nonparametric methods for analysing two or more samples of unimodal data5.4. Analysis of two or more samples from von Mises distributions5.5. Analysis of data from more complicated experimental designsPart VI. Correlation and Regression6.1. Introduction6.2. Linear-circular association and circular-linear association6.3. Circular-circular association6.4. Regression models for a circular response variablePart VII. Analysis of Data with Temporal or Spatial Structure7.1. Introduction7.2. Analysis of temporal data7.3. Spatial analysisPart VIII. Some Modern Statistical Techniques for Testing and Estimation8.1. Introduction8.2. Bootstrap methods for confidence intervals and hypothesis testsgeneral description8.3. Bootstrap methods for circular dataconfidence regions for the mean direction8.4. Bootstrap methods for circular datahypothesis tests for mean directions8.5. Randomisation, or permutation, testsAppendix A. TablesAppendix B. Data setsReferencesIndex.
