Atnaujinkite slapukų nuostatas

El. knyga: Bayesian Methods for the Physical Sciences: Learning from Examples in Astronomy and Physics

,
Kitos knygos pagal šią temą:
Bayesian Methods for the Physical Sciences: Learning from Examples in Astronomy and PhysicsDidesnis paveikslėlis
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

Statistical literacy is critical for the modern researcher in Physics and Astronomy. This book empowers researchers in these disciplines by providing the tools they will need to analyze their own data. Chapters in this book provide a statistical base from which to approach new problems, including numerical advice and a profusion of examples. The examples are engaging analyses of real-world problems taken from modern astronomical research. The examples are intended to be starting points for readers as they learn to approach their own data and research questions. Acknowledging that scientific progress now hinges on the availability of data and the possibility to improve previous analyses, data and code are distributed throughout the book. The JAGS symbolic language used throughout the book makes it easy to perform Bayesian analysis and is particularly valuable as readers may use it in a myriad of scenarios through slight modifications.

This book is comprehensive, well written, and will surely be regarded as a standard text in both astrostatistics and physical statistics.

Joseph M. Hilbe, President, International Astrostatistics Association, Professor Emeritus, University of Hawaii, and Adjunct Professor of Statistics, Arizona State University

Recenzijos

Andreon and Weaver have written a book that could be a valuable component in the new Computational Data Analysis course. Bayesian Methods for the Physical Sciences begins with basic probability calculus and introduces complex models and concepts as it goes along. Most of the content is presented through real-world examples that could easily be adopted or adapted to new tasks. (David W. Hogg, Physics Today, Issue 6, June, 2016)

Daugiau informacijos

Bayesian statistical methods are fast becoming the statistical method of choice among the majority of physicists and astrophysicists who find they must statistically evaluate their study data. Bayesian Methods for the Physical Sciences is co-authored by a noted astrophysicist and an accomplished Los Alamos statistician who specializes in this area of application. Together they have produced a true guidebook to the Bayesian modeling of astrophysical data. JAGS code is used and displayed for the many examples employed in the text. The book is comprehensive, well written, and will surely be regarded as a standard text in both astrostatistics and physical statistics. Joseph M. Hilbe, President, International Astrostatistics Association, Professor Emeritus, University of Hawaii, and Adjunct Professor of Statistics, Arizona State University
1 Recipes for a Good Statistical Analysis 1(2)
2 A Bit of Theory 3(12)
2.1 Axiom 1: Probabilities Are in the Range Zero to One
3(1)
2.2 Axiom 2: When a Probability Is Either Zero or One
3(1)
2.3 Axiom 3: The Sum, or Marginalization, Axiom
4(1)
2.4 Product Rule
5(1)
2.5 Bayes Theorem
5(2)
2.6 Error Propagation
7(1)
2.7 Bringing It All Home
8(1)
2.8 Profiling Is Not Marginalization
8(2)
2.9 Exercises
10(3)
References
13(2)
3 A Bit of Numerical Computation 15(6)
3.1 Some Technicalities
17(1)
3.2 How to Sample from a Generic Function
18(2)
References
20(1)
4 Single Parameter Models 21(14)
4.1 Step-by-Step Guide for Building a Basic Model
21(5)
4.1.1 A Little Bit of (Science) Background
21(1)
4.1.2 Bayesian Model Specification
22(1)
4.1.3 Obtaining the Posterior Distribution
22(1)
4.1.4 Bayesian Point and Interval Estimation
23(1)
4.1.5 Checking Chain Convergence
24(1)
4.1.6 Model Checking and Sensitivity Analysis
25(1)
4.1.7 Comparison with Older Analyses
25(1)
4.2 Other Useful Distributions with One Parameter
26(6)
4.2.1 Measuring a Rate: Poisson
26(2)
4.2.2 Combining Two or More (Poisson) Measurements
28(1)
4.2.3 Measuring a Fraction: Binomial
28(4)
4.3 Exercises
32(2)
References
34(1)
5 The Prior 35(16)
5.1 Conclusions Depend on the Prior
35(6)
5.1.1 ...Sometimes a Lot: The Malmquist-Eddington Bias
35(2)
5.1.2 ...by Lower Amounts with Increasing Data Quality
37(2)
5.1.3 ...but Eventually Becomes Negligible
39(1)
5.1.4 ...and the Precise Shape of the Prior Often Does Not Matter
40(1)
5.2 Where to Find Priors
41(1)
5.3 Why There Are So Many Uniform Priors in this Book?
42(1)
5.4 Other Examples on the Influence of Priors on Conclusions
42(5)
5.4.1 The Important Role of the Prior in the Determination of the Mass of the Most Distant Known Galaxy Cluster
42(2)
5.4.2 The Importance of Population Gradients for Photometric Redshifts
44(3)
5.5 Exercises
47(2)
References
49(2)
6 Multi-parameters Models 51(48)
6.1 Common Simple Problems
51(16)
6.1.1 Location and Spread
51(3)
6.1.2 The Source Intensity in the Presence of a Background
54(5)
6.1.3 Estimating a Fraction in the Presence of a Background
59(3)
6.1.4 Spectral Slope: Hardness Ratio
62(2)
6.1.5 Spectral Shape
64(3)
6.2 Mixtures
67(8)
6.2.1 Modeling a Bimodal Distribution: The Case of Globular Cluster Metallicity
67(6)
6.2.2 Average of Incompatible Measurements
73(2)
6.3 Advanced Analysis
75(17)
6.3.1 Source Intensity with Over-Poisson Background Fluctuations
75(2)
6.3.2 The Cosmological Mass Fraction Derived from the Cluster's Baryon Fraction
77(3)
6.3.3 Light Concentration in the Presence of a Background
80(2)
6.3.4 A Complex Background Modeling for Geo-Neutrinos
82(7)
6.3.5 Upper Limits from Counting Experiments
89(3)
6.4 Exercises
92(4)
References
96(3)
7 Non-random Data Collection 99(22)
7.1 The General Case
100(2)
7.2 Sharp Selection on the Value
102(1)
7.3 Sharp Selection on the Value, Mixture of Gaussians: Measuring the Gravitational Redshift
103(3)
7.4 Sharp Selection on the True Value
106(3)
7.5 Probabilistic Selection on the True Value
109(2)
7.6 Sharp Selection on the Observed Value, Mixture of Gaussians
111(2)
7.7 Numerical Implementation of the Models
113(5)
7.7.1 Sharp Selection on the Value
113(1)
7.7.2 Sharp Selection on the True Value
114(2)
7.7.3 Probabilistic Selection on the True Value
116(1)
7.7.4 Sharp Selection on the Observed Value, Mixture of Gaussians
117(1)
7.8 Final Remarks
118(1)
Reference
119(2)
8 Fitting Regression Models 121(70)
8.1 Clearing Up Some Misconceptions
121(7)
8.1.1 Pay Attention to Selection Effects
121(2)
8.1.2 Avoid Fishing Expeditions
123(1)
8.1.3 Do Not Confuse Prediction with Parameter Estimation
124(4)
8.2 Non-linear Fit with No Error on Predictor and No Spread: Efficiency and Completeness
128(3)
8.3 Fit with Spread and No Errors on Predictor: Varying Physical Constants?
131(3)
8.4 Fit with Errors and Spread: The Magorrian Relation
134(3)
8.5 Fit with More Than One Predictor and a Complex Link: Star Formation Quenching
137(4)
8.6 Fit with Upper and Lower Limits: The Optical-to-X Flux Ratio
141(5)
8.7 Fit with An Important Data Structure: The Mass-Richness Scaling
146(3)
8.8 Fit with a Non-ignorable Data Collection
149(5)
8.9 Fit Without Anxiety About Non-random Data Collection
154(5)
8.10 Prediction
159(6)
8.11 A Meta-Analysis: Combined Fit of Regressions with Different Intrinsic Scatter
165(3)
8.12 Advanced Analysis
168(18)
8.12.1 Cosmological Parameters from SNIa
168(7)
8.12.2 The Enrichment History of the ICM
175(6)
8.12.3 The Enrichment History After Binning by Redshift
181(1)
8.12.4 With An Over-Poissons Spread
182(4)
8.13 Exercises
186(3)
References
189(2)
9 Model Checking and Sensitivity Analysis 191(16)
9.1 Sensitivity Analysis
192(5)
9.1.1 Check Alternative Prior Distributions
192(1)
9.1.2 Check Alternative Link Functions
193(3)
9.1.3 Check Alternative Distributional Assumptions
196(1)
9.1.4 Prior Sensitivity Summary
197(1)
9.2 Model Checking
197(6)
9.2.1 Overview
197(2)
9.2.2 Start Simple: Visual Inspection of Real and Simulated Data and of Their Summaries
199(1)
9.2.3 A Deeper Exploration: Using Measures of Discrepancy
200(2)
9.2.4 Another Deep Exploration
202(1)
9.3 Summary
203(1)
References
204(3)
10 Bayesian vs Simple Methods 207(22)
10.1 Conceptual Differences
208(1)
10.2 Maximum Likelihood
208(5)
10.2.1 Average vs. Maximum Likelihood
209(3)
10.2.2 Small Samples
212(1)
10.3 Robust Estimates of Location and Scale
213(3)
10.3.1 Bayes Hasa Lower Bias
214(1)
10.3.2 Bayes Is Fairer and Has Less Noisy Errors
215(1)
10.4 Comparison of Fitting Methods
216(10)
10.4.1 Fitting Methods Generalities
216(1)
10.4.2 Regressions Without Intrinsic Scatter
217(6)
10.4.3 One More Comparison, with Different Data Structures
223(3)
10.5 Summary and Experience of a Former Non-Bayesian Astronomer
226(1)
References
227(2)
A Probability Distributions 229(8)
A.1 Discrete Distributions
229(2)
A.1.1 Bernoulli
229(1)
A.1.2 Binomial
229(1)
A.1.3 Poisson
230(1)
A.2 Continuous Distributions
231(6)
A.2.1 Gaussian or Normal
231(1)
A.2.2 Beta
231(1)
A.2.3 Exponential
232
A.2.4 Gamma and Schechter
212(2)
A.2.5 Lognormal
214(20)
A.2.6 Pareto or Power Law
234(1)
A.2.7 Central Student-t
235(1)
A.2.8 Uniform
235(1)
A.2.9 Weibull
236(1)
B The Third Axiom of Probability, Conditional Probability, Independence and Conditional Independence 237
B.1 The Third Axiom of Probability
237(1)
B.2 Conditional Probability
237(1)
B.3 Independence and Conditional Independence
238
Stefano Andreon is an astronomer of the National Institute of Astrophysics, Brera Observatory (Milan, Italy). Stefano's research is focused on understanding the evolution of galaxies and of galaxy clusters, near and far, and adopting Bayesian methods. He also teaches Bayesian methods to PhD students of various Italian and French Universities, is a Member of the Executive Board of International Astrostatistics Association, and is first author of more than 50 referred papers.

Brian Weaver is a scientist with the Statistical Sciences group at Los Alamos National Laboratory. His research interests include Monte Carlo methods, parallel computing, Bayesian design of experiments, dynamic linear models, model calibration, and applying statistics to the physical and engineering sciences. He is a mentor to both graduate and undergraduate students in statistics at Los Alamos and is a recipient of the Llyod S. Nelson award.
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97833191528752e.html
Raktažodžiai: