该书可以在此处查阅http://books.google.com.hk/books?id=SmUh4YwE99MC&pg=PA324&lpg=PA324&dq=Introduction+to+Applied+Statistics+A+Modelling+Approach+Instructor&source=bl&ots=bW1fD_PIa8&sig=NJtTabHUyZQpBP87oSvgPayaed8&hl=zh-CN&ei=rAotTZ-INoLyvQOFxJ3MCQ&sa=X&oi=book_result&ct=result&resnum=9&ved=0CGEQ6AEwCA#v=onepage&q&f=false
R code可用在作者的主页上获得
1 Basic concepts 1
1.1 Variables 1
1.1.1 Definition 1
1.1.2 Characteristics of observations 1
1.1.3 Several variables 1
1.2 Summarising data 2
1.2.1 Tables 2
1.2.2 Measuring size and variability 3
1.2.3 Graphics 3
1.2.4 Detecting possible dependencies 3
1.3 Probability 3
1.3.1 Definition 3
1.3.2 Probability laws 4
1.3.3 Plotting probabilities 4
1.3.4 Multinomial distribution 4
1.4 Planning a study 5
1.4.1 Protocols 5
1.4.2 Observational surveys and experiments 5
1.4.3 Study designs 6
1.5 Solutions to the exercises 6
2 Categorical data 21
2.1 Measures of dependence 21
2.1.1 Estimation 21
2.1.2 Independence 22
2.1.3 Comparison of probabilities 22
2.1.4 Characteristics of the odds ratio 22
2.1.5 Simpson’s paradox 22
2.2 Models for binary response variables 23
2.2.1 Models based on linear functions 23
2.2.2 Logistic models 23
2.2.3 One polytomous explanatory variable 24
2.2.4 Several explanatory variables 24
2.2.5 Logistic regression 25
2.3 Polytomous response variables 25
2.3.1 Polytomous logistic models 25
2.3.2 Log linear models 26
2.3.3 Log linear regression 27
2.3.4 Ordinal response 27
2.4 Solutions to the exercises 27
3 Inference 45
3.1 Goals of inference 45
3.1.1 Discovery and decisions 45
3.1.2 Types of model selection 45
3.2 Likelihood 46
3.2.1 Likelihood function 46
3.2.2 Maximum likelihood estimate 46
3.2.3 Normed likelihood and deviance 46
3.2.4 Standard errors 47
3.3 Two special models 47
3.3.1 Saturated models 47
3.3.2 Null models 47
3.4 Calibrating the likelihood 48
3.4.1 Degrees of freedom 48
3.4.2 Model selection criteria 48
3.4.3 Significance tests 48
3.4.4 Prior probability 49
3.5 Goodness of fit 49
3.5.1 Global fit 49
3.5.2 Residuals and diagnostics 49
3.6 Sample size calculations 49
3.7 Solutions to the exercises 49
4 Probability distributions 59
4.1 Constructing probability distributions 59
4.1.1 Multinomial distribution 59
4.1.2 Density functions 59
4.2 Distributions for ordinal variables 60
4.2.1 Uniform distribution 60
4.2.2 Zeta distribution 60
4.3 Distributions for counts 60
4.3.1 Poisson distribution 60
4.3.2 Geometric distribution 61
4.3.3 Binomial distribution 61
4.3.4 Negative binomial distribution 62
4.3.5 Beta-binomial distribution 62
4.4 Distributions for measurement errors 62
4.4.1 Normal distribution 62
4.4.2 Logistic distribution 62
4.4.3 Laplace distribution 62
4.4.4 Cauchy distribution 62
4.4.5 Student t distribution 63
4.5 Distributions for durations 63
4.5.1 Intensity and survivor functions 63
4.5.2 Exponential distribution 63
4.5.3 Weibull distribution 63
4.5.4 Gamma distribution 63
4.5.5 Inverse Gauss distribution 64
4.6 Transforming the response 64
4.6.1 Log transformation 64
4.6.2 Exponential transformation 64
4.6.3 Power transformations 64
4.7 Special families 64
4.7.1 Location-scale family 64
4.7.2 Exponential family 65
4.8 Solutions to the exercises 65
5 Normal regression and ANOVA 103
5.1 General regression models 103
5.1.1 More assumptions or more data 103
5.1.2 Generalised linear models 103
5.1.3 Location regression models 104
5.2 Linear regression 104
5.2.1 One explanatory variable 104
5.2.2 Multiple regression 105
5.3 Analysis of variance 106
5.3.1 One explanatory variable 106
5.3.2 Two explanatory variables 106
5.3.3 Matched pairs 106
5.3.4 Analysis of covariance 106
5.4 Correlation 107
5.5 Sample size calculations 107
5.6 Solutions to the exercises 107
6 Dependent responses 119
6.1 Repeated measurements 119
6.2 Time series 119
6.2.1 Markov chains 119
6.2.2 Autoregression 120
6.3 Clustering 120
6.4 Life tables 120
6.4.1 One possible event 120
6.4.2 Repeated events 120
6.5 Solutions to the exercises 121