Probability and Statistics for Computer Scientists

Höfundur: Michael Baron (Útgáfa: 3)
Probability and Statistics for Computer Scientists

Kaup valmöguleikar

Umsögn um aðra útgáfu: „Höfundurinn hefur unnið heimavinnuna sína varðandi þau tölfræðitæki sem tölvunarfræðingar þurfa á að halda. Hann hefur vandað valið á dæmum sem eru bæði áhugaverð og hagnýt fyrir tölvunarfræðinga. Efnið er skýrt með fjölda mynda og bókin endar á viðaukum og atriðisorðaskrá. Bókin er lærð og gæti vel gengið sem skyldulesning í námskeiði á efri stigum grunnnáms eða í framhaldsnámi.“ (Computing Reviews)

Þriðja útgáfa Probability and Statistics for Computer Scientists hjálpar nemendum að skilja grundvallarhugtök líkinda og tölfræði, almennar aðferðir við slembilíkön, hermun, biðraðafræði og tölfræðilega gagnagreiningu, að taka bestu ákvarðanir við óvissu, að líkja eftir og meta tölvukerfi og að búa sig undir framhaldsnámskeið sem byggja á líkindafræði. Bókin er skrifuð á lifandi og einföldu máli, nú með R til viðbótar við MATLAB, og hentar bæði einnar og tveggja missera námskeiðum.

Meðal efnis er frumsendufræðileg kynning á líkindum og aukin umfjöllun um tölfræðilega ályktun og gagnagreiningu, þar á meðal mat og tilgátupróf, Bayes-nálgun, fjölbreytuaðhvarf, kí-kvaðratpróf fyrir óhæði og gæði aðlögunar, ódreifingarbundna tölfræði og bootstrap-aðferð, auk fjölda dæma og æfinga með tölvuverkefnum.

Nánar um bókina

Útgefandi
Taylor & Francis
ISBN
9781351697392
Print ISBN
9781138044487
Format
ePub
Útgáfa
3
Höfundar
Michael Baron
Tungumál
English
Útgefið
2019-06-25
Prent takmörkun á líftíma
100
Prent takmörkun
2
Afritunar takmörkun
2

Kaflar

  • Cover
  • Half Title
  • Title Page
  • Copyright Page
  • Dedication
  • Table of Contents
  • Preface
  • For whom this book is written
  • Recommended courses
  • Prerequisites, and use of the appendix
  • Style and motivation
  • Computers, data, demos, illustrations, R, and MATLAB®
  • Second edition and advanced statistics topics
  • Third edition and R
  • Thanks and acknowledgments
  • Chapter 1 Introduction and Overview
  • 1.1 Making decisions under uncertainty
  • Summary and conclusion
  • 1.2 Overview of this book
  • Summary and conclusions
  • Exercises
  • Part I Probability and Random Variables
  • Chapter 2 Probability
  • 2.1 Events and their probabilities
  • 2.1.1 Outcomes, events, and the sample space
  • 2.1.2 Set operations
  • 2.2 Rules of Probability
  • 2.2.1 Axioms of Probability
  • 2.2.2 Computing probabilities of events
  • Extreme cases
  • Union
  • Complement
  • Intersection of independent events
  • 2.2.3 Applications in reliability
  • 2.3 Combinatorics
  • 2.3.1 Equally likely outcomes
  • 2.3.2 Permutations and combinations
  • Permutations with replacement
  • Permutations without replacement
  • Combinations without replacement
  • Computational shortcuts
  • Combinations with replacement
  • 2.4 Conditional probability and independence
  • Conditional probability
  • Independence
  • Bayes Rule
  • Law of Total Probability
  • Summary and conclusions
  • Exercises
  • Chapter 3 Discrete Random Variables and Their Distributions
  • 3.1 Distribution of a random variable
  • 3.1.1 Main concepts
  • 3.1.2 Types of random variables
  • 3.2 Distribution of a random vector
  • 3.2.1 Joint distribution and marginal distributions
  • 3.2.2 Independence of random variables
  • 3.3 Expectation and variance
  • 3.3.1 Expectation
  • 3.3.2 Expectation of a function
  • 3.3.3 Properties
  • 3.3.4 Variance and standard deviation
  • 3.3.5 Covariance and correlation
  • 3.3.6 Properties
  • 3.3.7 Chebyshev’s inequality
  • 3.3.8 Application to finance
  • 3.4 Families of discrete distributions
  • 3.4.1 Bernoulli distribution
  • 3.4.2 Binomial distribution
  • Computer notes
  • 3.4.3 Geometric distribution
  • 3.4.4 Negative Binomial distribution
  • 3.4.5 Poisson distribution
  • 3.4.6 Poisson approximation of Binomial distribution
  • Summary and conclusions
  • Exercises
  • Chapter 4 Continuous Distributions
  • 4.1 Probability density
  • Analogy: pmf versus pdf
  • Joint and marginal densities
  • Expectation and variance
  • 4.2 Families of continuous distributions
  • 4.2.1 Uniform distribution
  • The Uniform property
  • Standard Uniform distribution
  • Expectation and variance
  • 4.2.2 Exponential distribution
  • Times between rare events are Exponential
  • Memoryless property
  • 4.2.3 Gamma distribution
  • Expectation, variance, and some useful integration remarks
  • Gamma-Poisson formula
  • 4.2.4 Normal distribution
  • Standard Normal distribution
  • 4.3 Central Limit Theorem
  • Normal approximation to Binomial distribution
  • Continuity correction
  • Summary and conclusions
  • Exercises
  • Chapter 5 Computer Simulations and Monte Carlo Methods
  • 5.1 Introduction
  • 5.1.1 Applications and examples
  • 5.2 Simulation of random variables
  • 5.2.1 Random number generators
  • 5.2.2 Discrete methods
  • Arbitrary discrete distribution
  • 5.2.3 Inverse transform method
  • Arbitrary continuous distribution
  • Discrete distributions revisited
  • Exponential-Geometric relation
  • 5.2.4 Rejection method
  • 5.2.5 Generation of random vectors
  • 5.2.6 Special methods
  • Poisson distribution
  • Normal distribution
  • 5.3 Solving problems by Monte Carlo methods
  • 5.3.1 Estimating probabilities
  • 5.3.2 Estimating means and standard deviations
  • 5.3.3 Forecasting
  • 5.3.4 Estimating lengths, areas, and volumes
  • Lengths
  • Areas and volumes
  • Areas of arbitrary regions with unknown boundaries
  • 5.3.5 Monte Carlo integration
  • Introducing functions in R and MATLAB
  • Accuracy of results
  • Improved Monte Carlo integration method
  • Accuracy of the improved method
  • Summary and conclusions
  • Exercises
  • Part II Stochastic Processes
  • Chapter 6 Stochastic Processes
  • 6.1 Definitions and classifications
  • 6.2 Markov processes and Markov chains
  • 6.2.1 Markov chains
  • Characteristics of a Markov chain
  • 6.2.2 Matrix approach
  • Computing h-step transition probabilities
  • Computing the distribution of X(h)
  • 6.2.3 Steady-state distribution
  • Computing the steady-state distribution
  • The limit of Ph
  • Steady state
  • Existence of a steady-state distribution. Regular Markov chains
  • Conclusion
  • 6.3 Counting processes
  • 6.3.1 Binomial process
  • Relation to real time: frames
  • Markov property
  • 6.3.2 Poisson process
  • Continuous time
  • Poisson process as the limiting case
  • Rare events and modeling
  • 6.4 Simulation of stochastic processes
  • Discrete-time processes
  • Markov chains
  • Binomial process
  • Continuous-time processes
  • Poisson process
  • Summary and conclusions
  • Exercises
  • Chapter 7 Queuing Systems
  • 7.1 Main components of a queuing system
  • Arrival
  • Queuing and routing to servers
  • Service
  • Departure
  • 7.2 The Little’s Law
  • 7.3 Bernoulli single-server queuing process
  • Markov property
  • Steady-state distribution
  • 7.3.1 Systems with limited capacity
  • 7.4 M/M/1 system
  • M/M/1 as a limiting case of a Bernoulli queuing process
  • Steady-state distribution for an M/M/1 system
  • 7.4.1 Evaluating the system’s performance
  • Utilization
  • Waiting time
  • Response time
  • Queue
  • Little’s Law revisited
  • When a system gets nearly overloaded
  • 7.5 Multiserver queuing systems
  • 7.5.1 Bernoulli k-server queuing process
  • Markov property
  • Transition probabilities
  • 7.5.2 M/M/k systems
  • Steady-state distribution
  • 7.5.3 Unlimited number of servers and M/M/∞
  • M/M/∞ queueing system
  • 7.6 Simulation of queuing systems
  • Markov case
  • General case
  • Example: simulation of a multiserver queuing system
  • Summary and conclusions
  • Exercises
  • Part III Statistics
  • Chapter 8 Introduction to Statistics
  • 8.1 Population and sample, parameters and statistics
  • 8.2 Descriptive statistics
  • 8.2.1 Mean
  • Unbiasedness
  • Consistency
  • Asymptotic Normality
  • 8.2.2 Median
  • Understanding the shape of a distribution
  • Computation of a population median
  • Computing sample medians
  • 8.2.3 Quantiles, percentiles, and quartiles
  • 8.2.4 Variance and standard deviation
  • Computation
  • 8.2.5 Standard errors of estimates
  • 8.2.6 Interquartile range
  • Detection of outliers
  • Handling of outliers
  • 8.3 Graphical statistics
  • 8.3.1 Histogram
  • How else may histograms look like?
  • Mixtures
  • The choice of bins
  • 8.3.2 Stem-and-leaf plot
  • 8.3.3 Boxplot
  • Parallel boxplots
  • 8.3.4 Scatter plots and time plots
  • R notes
  • MATLAB notes
  • Summary and conclusions
  • Exercises
  • Chapter 9 Statistical Inference I
  • 9.1 Parameter estimation
  • 9.1.1 Method of moments
  • Moments
  • Estimation
  • 9.1.2 Method of maximum likelihood
  • Discrete case
  • Continuous case
  • 9.1.3 Estimation of standard errors
  • Computer notes
  • 9.2 Confidence intervals
  • 9.2.1 Construction of confidence intervals: a general method
  • 9.2.2 Confidence interval for the population mean
  • 9.2.3 Confidence interval for the difference between two means
  • 9.2.4 Selection of a sample size
  • 9.2.5 Estimating means with a given precision
  • 9.3 Unknown standard deviation
  • 9.3.1 Large samples
  • 9.3.2 Confidence intervals for proportions
  • 9.3.3 Estimating proportions with a given precision
  • 9.3.4 Small samples: Student’s t distribution
  • 9.3.5 Comparison of two populations with unknown variances
  • 9.4 Hypothesis testing
  • 9.4.1 Hypothesis and alternative
  • 9.4.2 Type I and Type II errors: level of significance
  • 9.4.3 Level α tests: general approach
  • 9.4.4 Rejection regions and power
  • 9.4.5 Standard Normal null distribution (Z-test)
  • 9.4.6 Z-tests for means and proportions
  • 9.4.7 Pooled sample proportion
  • 9.4.8 Unknown σ: T-tests
  • 9.4.9 Duality: two-sided tests and two-sided confidence intervals
  • 9.4.10 P-value
  • How do we choose α?
  • P-value
  • Testing hypotheses with a P-value
  • Computing P-values
  • Understanding P-values
  • 9.5 Inference about variances
  • 9.5.1 Variance estimator and Chi-square distribution
  • 9.5.2 Confidence interval for the population variance
  • 9.5.3 Testing variance
  • Level α test
  • P-value
  • 9.5.4 Comparison of two variances. F-distribution
  • 9.5.5 Confidence interval for the ratio of population variances
  • 9.5.6 F-tests comparing two variances
  • R notes
  • MATLAB notes
  • Summary and conclusions
  • Exercises
  • Chapter 10 Statistical Inference II
  • 10.1 Chi-square tests
  • 10.1.1 Testing a distribution
  • 10.1.2 Testing a family of distributions
  • R and MATLAB notes
  • 10.1.3 Testing independence
  • R and MATLAB notes
  • 10.2 Nonparametric statistics
  • 10.2.1 Sign test
  • 10.2.2 Wilcoxon signed rank test
  • R and MATLAB notes
  • Null distribution of Wilcoxon test statistic
  • Exact distribution
  • Normal approximation
  • 10.2.3 Mann–Whitney–Wilcoxon rank sum test
  • Mann–Whitney–Wilcoxon test in R and MATLAB
  • Null distribution of Mann–Whitney–Wilcoxon test statistic
  • Normal approximation
  • 10.3 Bootstrap
  • 10.3.1 Bootstrap distribution and all bootstrap samples
  • Bootstrap distribution
  • 10.3.2 Computer generated bootstrap samples
  • Software notes
  • 10.3.3 Bootstrap confidence intervals
  • Parametric method, based on the bootstrap estimation of the standard error
  • Nonparametric method, based on the bootstrap quantiles
  • 10.4 Bayesian inference
  • 10.4.1 Prior and posterior
  • Conjugate distribution families
  • Gamma family is conjugate to the Poisson model
  • Beta family is conjugate to the Binomial model
  • Normal family is conjugate to the Normal model
  • 10.4.2 Bayesian estimation
  • 10.4.3 Bayesian credible sets
  • 10.4.4 Bayesian hypothesis testing
  • Loss and risk
  • Summary and conclusions
  • Exercises
  • Chapter 11 Regression
  • 11.1 Least squares estimation
  • 11.1.1 Examples
  • 11.1.2 Method of least squares
  • 11.1.3 Linear regression
  • Estimation in linear regression
  • 11.1.4 Regression and correlation
  • 11.1.5 Overfitting a model
  • 11.2 Analysis of variance, prediction, and further inference
  • 11.2.1 ANOVA and R-square
  • 11.2.2 Tests and confidence intervals
  • Degrees of freedom and variance estimation
  • Inference about the regression slope
  • ANOVA F-test
  • F-test and T-test
  • 11.2.3 Prediction
  • Confidence interval for the mean of responses
  • Prediction interval for the individual response
  • Prediction bands
  • 11.3 Multivariate regression
  • 11.3.1 Introduction and examples
  • 11.3.2 Matrix approach and least squares estimation
  • Matrix approach to multivariate linear regression
  • 11.3.3 Analysis of variance, tests, and prediction
  • Testing significance of the entire model
  • Variance estimator
  • Testing individual slopes
  • Prediction
  • 11.4 Model building
  • 11.4.1 Adjusted R-square
  • 11.4.2 Extra sum of squares, partial F-tests, and variable selection
  • Stepwise (forward) selection
  • Backward elimination
  • 11.4.3 Categorical predictors and dummy variables
  • Avoid singularity by creating only (C − 1) dummies
  • Interpretation of slopes for dummy variables
  • R notes
  • MATLAB notes
  • Summary and conclusions
  • Exercises
  • Appendix
  • A.1 Data sets
  • Reading data into R and MATLAB
  • Data inventory
  • A.2 Inventory of distributions
  • A.2.1 Discrete families
  • A.2.2 Continuous families
  • A.3 Distribution tables
  • A.4 Calculus review
  • A.4.1 Inverse function
  • A.4.2 Limits and continuity
  • A.4.3 Sequences and series
  • A.4.4 Derivatives, minimum, and maximum
  • Computing maxima and minima
  • A.4.5 Integrals
  • Integration by substitution
  • Integration by parts
  • Computing areas
  • Gamma function and factorial
  • A.5 Matrices and linear systems
  • Multiplying a row by a column
  • Multiplying matrices
  • Transposition
  • Solving systems of equations
  • Inverse matrix
  • Matrix operations in R
  • Matrix operations in MATLAB
  • A.6 Answers to selected exercises
  • Chapter 2
  • Chapter 3
  • Chapter 4
  • Chapter 5
  • Chapter 6
  • Chapter 7
  • Chapter 8
  • Chapter 9
  • Chapter 10
  • Chapter 11
  • Index