Muutke küpsiste eelistusi

Statistical Analysis of Spatial and Spatio-Temporal Point Patterns 3rd edition [Kõva köide]

3.83/5 (10 hinnangut Goodreads-ist)
(Lancaster University, UK)
Teised raamatud teemal:
Statistical Analysis of Spatial and Spatio-Temporal Point Patterns 3rd editionSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781466560239.html
Märksõnad:

Written by a prominent statistician and author, the first edition of this bestseller broke new ground in the then emerging subject of spatial statistics with its coverage of spatial point patterns. Retaining all the material from the second edition and adding substantial new material, Statistical Analysis of Spatial and Spatio-Temporal Point Patterns, Third Edition presents models and statistical methods for analyzing spatially referenced point process data.

Reflected in the title, this third edition now covers spatio-temporal point patterns. It explores the methodological developments from the last decade along with diverse applications that use spatio-temporally indexed data. Practical examples illustrate how the methods are applied to analyze spatial data in the life sciences.

This edition also incorporates the use of R through several packages dedicated to the analysis of spatial point process data. Sample R code and data sets are available on the author’s website.

Arvustused

" a valuable addition to the existing literature as it covers a number of topics in point pattern analysis, ranging from the basics of spatial point pattern statistical analysis to more recent developments in the spatio-temporal context. A number of examples are discussed throughout the chapters, which should facilitate the reading for practitioners of applied statistics from various disciplines. Besides this, the fact that data sets and R codes are available online certainly constitutes a nice addition to this application-oriented textbook." Mathematical Reviews, January 2015

" well written, concise, and handy. there are remarkable changes in fundamentals [ in this edition]. All concepts are well illustrated using interesting examples. an excellent introduction to point process statistics, in particular for beginners." Biometrical Journal, 2014

List of Figures
xv
List of Tables
xxvii
Preface xxix
1 Introduction
1(16)
1.1 Spatial point patterns
1(5)
1.2 Sampling
6(2)
1.3 Edge-effects
8(1)
1.4 Complete spatial randomness
9(2)
1.5 Objectives of statistical analysis
11(1)
1.6 The Dirichlet tessellation
12(1)
1.7 Monte Carlo tests
13(3)
1.8 Software
16(1)
2 Preliminary testing
17(22)
2.1 Tests of complete spatial randomness
17(1)
2.2 Inter-event distances
18(6)
2.2.1 Analysis of Japanese black pine saplings
21(1)
2.2.2 Analysis of redwood seedlings
21(1)
2.2.3 Analysis of biological cells
22(1)
2.2.4 Small distances
23(1)
2.3 Nearest neighbour distances
24(2)
2.3.1 Analysis of Japanese black pine saplings
25(1)
2.3.2 Analysis of redwood seedlings
25(1)
2.3.3 Analysis of biological cells
26(1)
2.4 Point to nearest event distances
26(3)
2.4.1 Analysis of Japanese black pine seedlings
28(1)
2.4.2 Analysis of redwood seedlings
28(1)
2.4.3 Analysis of biological cells
28(1)
2.5 Quadrat counts
29(3)
2.5.1 Analysis of Japanese black pine seedlings
30(1)
2.5.2 Analysis of redwood seedlings
31(1)
2.5.3 Analysis of biological cells
32(1)
2.6 Scales of pattern
32(3)
2.6.1 Analysis of Lansing Woods data
33(1)
2.6.2 Scales of dependence
34(1)
2.7 Recommendations
35(4)
3 Methods for sparsely sampled patterns
39(16)
3.1 General remarks
39(1)
3.2 Quadrat counts
40(3)
3.2.1 Tests of CSR
41(1)
3.2.2 Estimators of intensity
42(1)
3.2.3 Analysis of Lansing Woods data
42(1)
3.3 Distance measurements
43(9)
3.3.1 Distribution theory under CSR
44(2)
3.3.2 Tests of CSR
46(3)
3.3.3 Estimators of intensity
49(1)
3.3.4 Analysis of Lansing Woods data
50(1)
3.3.5 Catana's wandering quarter
51(1)
3.4 Tests of independence
52(1)
3.5 Recommendations
53(2)
4 Spatial point processes
55(28)
4.1 Processes and summary descriptions
55(2)
4.2 Second-order properties
57(3)
4.2.1 Univariate processes
57(3)
4.2.2 Extension to multivariate processes
60(1)
4.3 Higher order moments and nearest neighbour distributions
60(1)
4.4 The homogeneous Poisson process
61(2)
4.5 Independence and random labelling
63(1)
4.6 Estimation of second-order properties
64(12)
4.6.1 Stationary processes
64(7)
4.6.2 Estimating the pair correlation function
71(1)
4.6.3 Intensity-reweighted stationary processes
72(1)
4.6.4 Multivariate processes
73(1)
4.6.5 Examples
74(2)
4.7 Displaced amacrine cells in the retina of a rabbit
76(2)
4.8 Estimation of nearest neighbour distributions
78(1)
4.8.1 Examples
79(1)
4.9 Concluding remarks
79(4)
5 Nonparametric methods
83(16)
5.1 Introduction
83(1)
5.2 Estimating weighted integrals of the second-order intensity
83(1)
5.3 Nonparametric estimation of a spatially varying intensity
84(6)
5.3.1 Estimating spatially varying intensities for the Lansing Woods data
87(3)
5.4 Analysing replicated spatial point patterns
90(7)
5.4.1 Estimating the K-function from replicated data
92(2)
5.4.2 Between-group comparisons in designed experiments
94(3)
5.5 Parametric or nonparametric methods?
97(2)
6 Models
99(32)
6.1 Introduction
99(1)
6.2 Contagious distributions
100(1)
6.3 Poisson cluster processes
101(3)
6.4 Inhomogeneous Poisson processes
104(2)
6.5 Cox processes
106(3)
6.6 Trans-Gaussian Cox processes
109(1)
6.7 Simple inhibition processes
110(2)
6.8 Markov point processes
112(6)
6.8.1 Pairwise interaction point processes
114(4)
6.8.2 More general forms of interaction
118(1)
6.9 Other constructions
118(5)
6.9.1 Lattice-based processes
118(1)
6.9.2 Thinned processes
119(1)
6.9.3 Superpositions
120(1)
6.9.4 Interactions in an inhomogeneous environment
121(2)
6.10 Multivariate models
123(8)
6.10.1 Marked point processes
123(1)
6.10.2 Multivariate point processes
123(1)
6.10.3 How should multivariate models be formulated?
124(1)
6.10.4 Cox processes
125(3)
6.10.5 Markov point processes
128(3)
7 Model-fitting using summary descriptions
131(20)
7.1 Introduction
131(1)
7.2 Parameter estimation using the K-function
132(3)
7.2.1 Least squares estimation
132(1)
7.2.2 Simulated realisations of a Poisson cluster process
133(1)
7.2.3 Procedure when K(t) is unknown
134(1)
7.3 Goodness-of-fit assessment using nearest neighbour distributions
135(1)
7.4 Examples
136(11)
7.4.1 Redwood seedlings
136(3)
7.4.2 Bramble canes
139(8)
7.5 Parameter estimation via goodness-of-fit testing
147(4)
7.5.1 Analysis of hamster tumour data
148(3)
8 Model-fitting using likelihood-based methods
151(22)
8.1 Introduction
151(1)
8.2 Likelihood inference for inhomogeneous Poisson processes
152(3)
8.2.1 Fitting a trend surface to the Lansing Woods data
153(2)
8.3 Likelihood inference for Markov point processes
155(12)
8.3.1 Maximum pseudo-likelihood estimation
156(2)
8.3.2 Non-parametric estimation of a pairwise interaction function
158(1)
8.3.3 Fitting a pairwise interaction point process to the displaced amacrine cells
158(2)
8.3.4 Monte Carlo maximum likelihood estimation
160(3)
8.3.5 The displaced amacrine cells re-visited
163(2)
8.3.6 A bivariate model for the displaced amacrine cells
165(2)
8.4 Likelihood inference for Cox processes
167(5)
8.4.1 Predictive inference in a log-Gaussian Cox process
169(1)
8.4.2 Non-parametric estimation of an intensity surface: hickories in Lansing Woods
170(2)
8.5 Additional reading
172(1)
9 Point process methods in spatial epidemiology
173(22)
9.1 Introduction
173(3)
9.2 Spatial clustering
176(3)
9.2.1 Analysis of the North Humberside childhood leukaemia data
177(1)
9.2.2 Other tests of spatial clustering
178(1)
9.3 Spatial variation in risk
179(3)
9.3.1 Primary biliary cirrhosis in the North East of England
181(1)
9.4 Point source models
182(7)
9.4.1 Childhood asthma in north Derbyshire, England
185(1)
9.4.2 Cancers in North Liverpool
186(3)
9.5 Stratification and matching
189(4)
9.5.1 Stratified case-control designs
189(2)
9.5.2 Individually matched case-control designs
191(2)
9.5.3 Is stratification or matching helpful?
193(1)
9.6 Disentangling heterogeneity and clustering
193(2)
10 Spatio-temporal point processes
195(14)
10.1 Introduction
195(1)
10.2 Motivating examples
196(3)
10.2.1 Gastro-intestinal illness in Hampshire, UK
196(2)
10.2.2 The 2001 foot-and-mouth epidemic in Cumbria, UK
198(1)
10.2.3 Bovine tuberculosis in Cornwall, UK
198(1)
10.3 A classification of spatio-temporal point patterns and processes
199(3)
10.4 Second-order properties
202(2)
10.5 Conditioning on the past
204(3)
10.6 Empirical and mechanistic models
207(2)
11 Exploratory analysis
209(14)
11.1 Introduction
209(1)
11.2 Animation
210(1)
11.3 Marginal and conditional summaries
210(3)
11.3.1 Bovine tuberculosis in Cornwall, UK
210(3)
11.4 Second-order properties
213(10)
11.4.1 Stationary processes
213(3)
11.4.2 Intensity-reweighted stationary processes
216(1)
11.4.3 Campylobacteriosis in Lancashire, UK
217(6)
12 Empirical models and methods
223(12)
12.1 Introduction
223(1)
12.2 Poisson processes
224(1)
12.3 Cox processes
224(2)
12.3.1 Separable and non-separable models
225(1)
12.4 Log-Gaussian Cox processes
226(1)
12.5 Inference
227(1)
12.6 Gastro-intestinal illness in Hampshire, UK
227(3)
12.7 Concluding remarks: point processes and geostatistics
230(5)
13 Mechanistic models and methods
235(10)
13.1 Introduction
235(1)
13.2 Conditional intensity and likelihood
235(2)
13.3 Partial likelihood
237(1)
13.4 The 2001 foot-and-mouth epidemic in Cumbria, UK
238(2)
13.5 Nesting patterns of Arctic terns
240(5)
References 245(18)
Index 263
Peter Diggle is a Distinguished University Professor and group leader of CHICAS at Lancaster University. Dr. Diggle is also an adjunct professor of biostatistics at both Johns Hopkins Universitys and Yale Universitys Schools of Public Health, adjunct senior researcher in the International Research Institute for Climate and Society at Columbia University, professor of epidemiology and statistics at the University of Liverpool, a trustee for Biometrika, founding co-editor and advisory board member for Biostatistics, and chair of the Strategic Skills Fellowships Panel of the Medical Research Council. His research focuses on the development and application of statistical methods to the biomedical and health sciences.