从别的地方转过来，挺不错的书。

The Econometric Modelling of Financial Time Series 3Ed
By Terence C. Mills, Raphael N. Markellos

Publisher:   Cambridge University Press
Number Of Pages:   468
Publication Date:   2008-04-21
ISBN-10 / ASIN:   0521883814
ISBN-13 / EAN:   9780521883818
Binding:   Hardcover

Contents
List of figures page viii
List of tables xi
Preface to the third edition xiii
1 Introduction 1
2 Univariate linear stochastic models: basic concepts 9
2.1 Stochastic processes, ergodicity and stationarity 9
2.2 Stochastic difference equations 12
2.3 ARMA processes 14
2.4 Linear stochastic processes 28
2.5 ARMA model building 28
2.6 Non-stationary processes and ARIMA models 37
2.7 ARIMA modelling 48
2.8 Seasonal ARIMA modelling 53
2.9 Forecasting using ARIMA models 57
3 Univariate linear stochastic models: testing for unit roots and
alternative trend specifications 65
3.1 Determining the order of integration of a time series 67
3.2 Testing for a unit root 69
3.3 Trend stationarity versus difference stationarity 85
3.4 Other approaches to testing for unit roots 89
3.5 Testing for more than one unit root 96
3.6 Segmented trends, structural breaks and smooth transitions 98
3.7 Stochastic unit root processes 105
4 Univariate linear stochastic models: further topics 111
4.1 Decomposing time series: unobserved component models and
signal extraction 111
5 Univariate non-linear stochastic models: martingales, random
walks and modelling volatility 151
5.1 Martingales, random walks and non-linearity 151
5.2 Testing the random walk hypothesis 153
5.3 Measures of volatility 157
5.4 Stochastic volatility 166
5.5 ARCH processes 174
5.6 Some models related to ARCH 199
5.7 The forecasting performance of alternative volatility models 204
6 Univariate non-linear stochastic models: further models and
testing procedures 206
6.1 Bilinear and related models 207
6.2 Regime-switching models: Markov chains and smooth
transition autoregressions 216
6.3 Non-parametric and neural network models 223
6.4 Non-linear dynamics and chaos 232
6.5 Testing for non-linearity 235
7 Modelling return distributions 247
7.1 Descriptive analysis of returns series 248
7.2 Two models for returns distributions 249
7.3 Determining the tail shape of a returns distribution 254
7.4 Empirical evidence on tail indices 257
7.5 Testing for covariance stationarity 261
7.6 Modelling the central part of returns distributions 264
7.7 Data-analytic modelling of skewness and kurtosis 266
7.8 Distributional properties of absolute returns 268
7.9 Summary and further extensions 271
8 Regression techniques for non-integrated financial time series 274
8.1 Regression models 274
8.2 ARCH-in-mean regression models 287
8.3 Misspecification testing 293
8.4 Robust estimation 304
9 Regression techniques for integrated financial time series 329
9.1 Spurious regression 330
9.2 Cointegrated processes 338
9.3 Testing for cointegration in regression 346
9.4 Estimating cointegrating regressions 352
9.5 VARs with integrated variables 356
9.6 Causality testing in VECMs 373
9.7 Impulse response asymptotics in non-stationary VARs 375
9.8 Testing for a single long-run relationship 377
9.9 Common trends and cycles 383
10 Further topics in the analysis of integrated financial time series 388
10.1 Present value models, excess volatility and cointegration 388
10.2 Generalisations and extensions of cointegration and error
correction models 401
Data appendix 411
References 412
Index 446