Applied Quantitative Methods for Trading and Investment

Edited by
Christian L. Dunis
Jason Laws
and
Patrick Na¨ım

Contents
About the Contributors xi
Preface xv
1 Applications of Advanced Regression Analysis for Trading and
Investment 1
Christian L. Dunis and Mark Williams
Abstract 1
1.1 Introduction 1
1.2 Literature review 3
1.3 The exchange rate and related financial data 4
1.4 Benchmark models: theory and methodology 10
1.5 Neural network models: theory and methodology 20
1.6 Forecasting accuracy and trading simulation 31
1.7 Concluding remarks 36
References 39
2 Using Cointegration to Hedge and Trade International Equities 41
A. Neil Burgess
Abstract 41
2.1 Introduction 41
2.2 Time series modelling and cointegration 42
2.3 Implicit hedging of unknown common risk factors 45
2.4 Relative value and statistical arbitrage 47
2.5 Illustration of cointegration in a controlled simulation 50
2.6 Application to international equities 54
2.7 Discussion and conclusions 66
References 68
vi Contents
3 Modelling the Term Structure of Interest Rates: An Application
of Gaussian Affine Models to the German Yield Curve 71
Nuno Cassola and Jorge Barros Lu´ıs
Abstract 71
3.1 Introduction 71
3.2 Background issues on asset pricing 77
3.3 Duffie–Kan affine models of the term structure 78
3.4 A forward rate test of the expectations theory 83
3.5 Identification 84
3.6 Econometric methodology and applications 87
3.7 Estimation results 106
3.8 Conclusions 126
References 126
4 Forecasting and Trading Currency Volatility: An Application of
Recurrent Neural Regression and Model Combination 129
Christian L. Dunis and Xuehuan Huang
Abstract 129
4.1 Introduction 129
4.2 The exchange rate and volatility data 132
4.3 The GARCH (1,1) benchmark volatility forecasts 135
4.4 The neural network volatility forecasts 137
4.5 Model combinations and forecasting accuracy 142
4.6 Foreign exchange volatility trading models 145
4.7 Concluding remarks and further work 149
Acknowledgements 150
Appendix A 150
Appendix B 152
Appendix C 155
Appendix D 156
Appendix E 157
Appendix F 158
Appendix G 159
References 160
5 Implementing Neural Networks, Classification Trees, and Rule
Induction Classification Techniques: An Application to Credit
Risk 163
George T. Albanis
Abstract 163
5.1 Introduction 163
5.2 Data description 165
5.3 Neural networks for classification in Excel 166
5.4 Classification tree in Excel 172
Contents vii
5.5 See5 classifier 178
5.6 Conclusions 191
References 191
6 Switching Regime Volatility: An Empirical Evaluation 193
Bruno B. Roche and Michael Rockinger
Abstract 193
6.1 Introduction 193
6.2 The model 194
6.3 Maximum likelihood estimation 195
6.4 An application to foreign exchange rates 197
6.5 Conclusion 206
References 206
Appendix A: Gauss code for maximum likelihood for variance
switching models 208
7 Quantitative Equity Investment Management with Time-Varying
Factor Sensitivities 213
Yves Bentz
Abstract 213
7.1 Introduction 213
7.2 Factor sensitivities defined 215
7.3 OLS to estimate factor sensitivities: a simple, popular but
inaccurate method 216
7.4 WLS to estimate factor sensitivities: a better but still
sub-optimal method 222
7.5 The stochastic parameter regression model and the Kalman
filter: the best way to estimate factor sensitivities 223
7.6 Conclusion 236
References 237
8 Stochastic Volatility Models: A Survey with Applications to
Option Pricing and Value at Risk 239
Monica Billio and Domenico Sartore
Abstract 239
8.1 Introduction 239
8.2 Models of changing volatility 244
8.3 Stochastic volatility models 246
8.4 Estimation 250
8.5 Extensions of SV models 261
8.6 Multivariate models 263
8.7 Empirical applications 265
8.8 Concluding remarks 284
Appendix A: Application of the pentanomial model 284
viii Contents
Appendix B: Application to Value at Risk 286
References 286
9 Portfolio Analysis Using Excel 293
Jason Laws
Abstract 293
9.1 Introduction 293
9.2 The simple Markovitz model 294
9.3 The matrix approach to portfolio risk 301
9.4 Matrix algebra in Excel when the number of assets increases 303
9.5 Alternative optimisation targets 308
9.6 Conclusion 310
Bibliography 311
10 Applied Volatility and Correlation Modelling Using Excel 313
Fr´ed´erick Bourgoin
Abstract 313
10.1 Introduction 313
10.2 The Basics 314
10.3 Univariate models 315
10.4 Multivariate models 324
10.5 Conclusion 331
References 332
11 Optimal Allocation of Trend-Following Rules: An Application
Case of Theoretical Results 333
Pierre Lequeux
Abstract 333
11.1 Introduction 333
11.2 Data 333
11.3 Moving averages and their statistical properties 335
11.4 Trading rule equivalence 336
11.5 Expected transactions cost under assumption of random walk 338
11.6 Theoretical correlation of linear forecasters 340
11.7 Expected volatility of MA 341
11.8 Expected return of linear forecasters 342
11.9 An applied example 344
11.10 Final remarks 346
References 347
12 Portfolio Management and Information from Over-the-Counter
Currency Options 349
Jorge Barros Lu´ıs
Abstract 349
12.1 Introduction 349
Contents ix
12.2 The valuation of currency options spreads 353
12.3 RND estimation using option spreads 355
12.4 Measures of correlation and option prices 359
12.5 Indicators of credibility of an exchange rate band 361
12.6 Empirical applications 365
12.7 Conclusions 378
References 379
13 Filling Analysis for Missing Data: An Application to Weather
Risk Management 381
Christian L. Dunis and Vassilios Karalis
Abstract 381
13.1 Introduction 381
13.2 Weather data and weather derivatives 383
13.3 Alternative filling methods for missing data 385
13.4 Empirical results 393
13.5 Concluding remarks 395
Appendix A 396
Appendix B 397
References 398
Index 401