A survey of dynamic Nelson-Siegel models, diffusion indexes, and big data methods for predicting interest rates

Hal Pedersen; Norman R. Swanson; Hal Pedersen; Norman R. Swanson

doi:10.3934/QFE.2019.1.22

Quantitative Finance and Economics

2019, Volume 3, Issue 1: 22-45. doi: 10.3934/QFE.2019.1.22

Previous Article Next Article

Research article Special Issues

A survey of dynamic Nelson-Siegel models, diffusion indexes, and big data methods for predicting interest rates

Hal Pedersen ¹,
Norman R. Swanson ^{2
,
,}

1.
Department of Economics, Rutgers University, 75 Hamilton Street, New Brunswick, NJ 08901, USA
2.
Conning, 1 Financial Plaza, Hartford, CT 06103, USA

Received: 31 January 2019 Accepted: 19 February 2019 Published: 04 March 2019
JEL Codes: C12, C22, C53

In this paper we survey a number of recent empirical findings regarding the usefulness of including diffusion indexes in dynamic Nelson-Siegel (DNS) type models used to predict the term structure of interest rates (see e.g., Diebold and Li (2007) and Diebold and Rudebusch (2013)). We also survey various empirical methods used in the construction of DNS models, and used to specify and estimate diffusion index augmented DNS models. In particular, we review (sparse) principal component analysis, factor augmented autoregression, and various dimension reduction, variable selection, machine learning, and shrinkage methods, such as the least absolute shrinkage operator (lasso), the elastic net, and independent component analysis, among others. Finally, we discuss the importance of using real-time data in contexts where datasets are subject to revision; and we compare and contrast the use of targeted versus un-targeted specification methods when including diffusion indexes in DNS type prediction models. Interestingly, as noted in Swanson and Xiong (2018a, 2018b), the usefulness of diffusion indexes is crucially dependent upon whether real-time data are used or not. Specifically, when real-time data are used to estimate the weights in di usion indexes, it is found that relatively few "data rich" models that use big data are preferred to simpler DNS models, post 2010. Instead, pure DNS models that rely only on historical interest rate data deliver mean square error "best" forecasts. However, when data are not real-time, diffusion indexes always have marginal predictive content for interest rates. Moreover, it is clear that in more volatile interest rate regimes, such as prior to 2010, machine learning and related methods have much to offer, regardless of the type of dataset used in their construction.
- real-time forecasting,
- dynamic Nelson-Siegel model,
- term structure of interest rates,
- real-time dataset,
- FRED-MD,
- real-time diffusion index
Citation: Hal Pedersen, Norman R. Swanson. A survey of dynamic Nelson-Siegel models, diffusion indexes, and big data methods for predicting interest rates[J]. Quantitative Finance and Economics, 2019, 3(1): 22-45. doi: 10.3934/QFE.2019.1.22

Related Papers:

Abstract

In this paper we survey a number of recent empirical findings regarding the usefulness of including diffusion indexes in dynamic Nelson-Siegel (DNS) type models used to predict the term structure of interest rates (see e.g., Diebold and Li (2007) and Diebold and Rudebusch (2013)). We also survey various empirical methods used in the construction of DNS models, and used to specify and estimate diffusion index augmented DNS models. In particular, we review (sparse) principal component analysis, factor augmented autoregression, and various dimension reduction, variable selection, machine learning, and shrinkage methods, such as the least absolute shrinkage operator (lasso), the elastic net, and independent component analysis, among others. Finally, we discuss the importance of using real-time data in contexts where datasets are subject to revision; and we compare and contrast the use of targeted versus un-targeted specification methods when including diffusion indexes in DNS type prediction models. Interestingly, as noted in Swanson and Xiong (2018a, 2018b), the usefulness of diffusion indexes is crucially dependent upon whether real-time data are used or not. Specifically, when real-time data are used to estimate the weights in di usion indexes, it is found that relatively few "data rich" models that use big data are preferred to simpler DNS models, post 2010. Instead, pure DNS models that rely only on historical interest rate data deliver mean square error "best" forecasts. However, when data are not real-time, diffusion indexes always have marginal predictive content for interest rates. Moreover, it is clear that in more volatile interest rate regimes, such as prior to 2010, machine learning and related methods have much to offer, regardless of the type of dataset used in their construction.

References

[1]	Altavilla C, Giacomini R, Ragusa G (2017) Anchoring the Yield Curve Using Survey Expectations. J Appl Economet 32: 1055-1068. doi: 10.1002/jae.2588
[2]	Andreou E, Gagliardini P, Ghysels E (2018) Is Industrial Production Still the Dominant Factor for the US Economy? Evidence from a New Class of Mixed Frequency (Group) Factor Models. Swiss Finance Institute Research Paper No. 16-11.
[3]	Ang A, Piazzesi M (2003) A No-Arbitrage Vector Autoregression of Term Structure Dynamics With Macroeconomic and Latent Variables. J Monetary Econ 50: 745-787. doi: 10.1016/S0304-3932(03)00032-1
[4]	Bai J, Ng S (2008) Forecasting Economic Time Series Using Targeted Predictors. J Econom 146: 304-317. doi: 10.1016/j.jeconom.2008.08.010
[5]	Bai J, Ng S (2009) Boosting Diffusion Indices. J Appl Economet 24: 607-629. doi: 10.1002/jae.1063
[6]	Banerjee A, Marcellino M, Marsten I (2008) Forecasting Macroeconomic Variables Using Diffusion Indexes in Short Samples with Structural Change, Forecasting in the Presence of Structural Breaks and Model Uncertainty, Emerald Group Publishing, New York, NY, 149-194.
[7]	Bernanke BS, Boivin J (2003) Monetary Policy in a Data-rich Environment. J Monetary Econo 50: 525-546. doi: 10.1016/S0304-3932(03)00024-2
[8]	Bank of International Settlements (2005) Zero-Coupon Yield Curves: Technical Documentation. Working Paper.
[9]	Boivin J, Ng S(2005) Understanding and Comparing Factor Based Macroeconomic Forecasts. Internation J Cent Bank 1: 117-152.
[10]	Carrasco M, Rossi B (2016) In-Sample Inference and Forecasting in Misspecified Factor Models. J Bus Econ Stat 34: 313-338. doi: 10.1080/07350015.2016.1186029
[11]	Cheng X, Hansen BE (2015) Forecasting with Factor-Augmented Regression: A Frequentist Model Averaging Approach. J Econom 186: 280-293. doi: 10.1016/j.jeconom.2015.02.010
[12]	Christensen JHE, Diebold FX, Rudebusch GD (2011) The Affine Arbitrage Free Class of Nelson-Siegel Term Structure Models. J Econom 164: 4-20. doi: 10.1016/j.jeconom.2011.02.011
[13]	Clark TE, McCrackenMW(2009) Improving Forecast Accuracy by Combining Recursive and Rolling Forecast. Internation Econ Rev 50: 363-395.
[14]	Corradi V, Swanson NR (2006) Predictive Density Evaluation, In G. Elliot, C. W. J. Granger, and A. Timmermann, Handbook of Economic Forecasting, (eds.), Elsevier, Amsterdam, 197-284.
[15]	Corradi V, Swanson NR (2014) Testing for Structural Stability of Factor Augmented Forecasting Models. J Economs 182: 100-111. doi: 10.1016/j.jeconom.2014.04.011
[16]	Coroneo L, Giannone D, Modugno M (2016) Unspanned Macroeconomic Factors in the Yield Curve. J Bus Econ Stat 34: 472-485. doi: 10.1080/07350015.2015.1052456
[17]	De Pooter M (2007) Examining the Nelson-Siegel Class of Term Structure Models: In-Sample Fit versus Out-of-Sample Forecasting Performance. Tinbergen Institute Discussion Paper No. 07-043/4.
[18]	Diebold FX, Li C (2006) Forecasting the Term Structure of Government Bond Yields. J Econom 130: 337-364. doi: 10.1016/j.jeconom.2005.03.005
[19]	Diebold FX, Rudebusch GD (1991) Forecasting Output with the Composite Leading Index: A Real-Time Analysis. J Am Stat Assoc 86: 603-610. doi: 10.1080/01621459.1991.10475085
[20]	Diebold FX, Rudebusch GD, Aruoba SB (2006) The Macroeconomy and the Yield Curve: A Dynamic Latent Factor Approach. J Econom 131: 309-338. doi: 10.1016/j.jeconom.2005.01.011
[21]	Diebold FX, Rudebusch GD (2013) Yield Curve Modeling and Forecasting: The Dynamic Nelson-Siegel Approach, Princeton University Press: Princeton.
[22]	Duffee GR (2011) Information In (and Not In) the Term Structure. Rev Financ Stud 24: 2895-2934. doi: 10.1093/rfs/hhr033
[23]	Duffee GR (2013) Forecasting Interest Rates, Handbook of Economic Forecasting, Elsevier, Amsterdam, 385-426.
[24]	Exterkate P, van Dijk D, Heij C (2013) Forecasting the Yield Curve in a DataRich Environment Using the FactorAugmented NelsonSiegel Model. J Forecasting 32: 193-214. doi: 10.1002/for.1258
[25]	Efron B, Hastie T, Johnstone L, et al. (2004) Least Angle Regression. A Stat 32: 407-499. doi: 10.1214/009053604000000067
[26]	Ghysels E, Marcellino M (2018) Applied Economic Forecasting using Time Series Models, Oxford University Press, London.
[27]	Gürkaynak RS, Sack B, Wright JH (2006) The U.S. Treasury Yield Curve: 1961 to the Present. Working Paper, Federal Reserve Bank-Finance and Economics Discussion Series 2006-28.
[28]	Gürkaynak RS, Wright JH (2012) Macroeconomics and the Term Structure. J Econ Lit 50: 331-67. doi: 10.1257/jel.50.2.331
[29]	Hamilton JD, Perez-Quiros G (1996) What Do the Leading Indicators Lead? J Bus 69: 27-49. doi: 10.1086/209678
[30]	Hamilton JD, Wu JC (2012) The Effectiveness of Alternative Monetary Policy Tools in a Zero Lower Bound Environment. J Money Credit Bank 44: 3-46.
[31]	Hansen PR, Timmermann A (2012) Choice of Sample Split in Out-of-Sample Forecast Evaluation. Working Paper, Rady School of Management, University of California, San Diego.
[32]	Hirano K, Wright JH (2017) Forecasting With Model Uncertainty: Representations and Risk Reduction. Econometrica 85: 617-643. doi: 10.3982/ECTA13372
[33]	Kim HH, Swanson NR (2014) Forecasting Financial and Macroeconomic Variables Using Data Reduction Methods: New Empirical Evidence. J Econom 178: 352-367. doi: 10.1016/j.jeconom.2013.08.033
[34]	Ludvigson SC, Ng S (2009) Macro Factors in Bond Risk Premia Rev Financ Stud 22: 5027-5067.
[35]	McCracken MW (2000) Robust Out-of-Sample Inference. J Econom 99: 195-223. doi: 10.1016/S0304-4076(00)00022-1
[36]	McCracken MW, Ng S (2016) Fred-MD: A Monthly Database for Macroeconomic Research. J Bus Econ Stat 34: 574-589. doi: 10.1080/07350015.2015.1086655
[37]	Mönch E (2008) Forecasting the Yield Curve in a Data-Rich Environment: A No-Arbitrage Factor-Augmented VAR Approach. J Econom 146: 26-43. doi: 10.1016/j.jeconom.2008.06.002
[38]	Nelson C, Siegel A (1985) Parsimonious Nodeling of Yield Curves for US Treasury Bills. Working Paper 1594, National Bureau of Economic Statistics.
[39]	Nelson C, Siegel A (1987) Parsimonious Modeling of Yield Curves. J Bus 60: 473-489. doi: 10.1086/296409
[40]	Rossi B, Sekhposyan S (2011) Understanding Models' Forecasting Performance. J Econom 164: 158-172. doi: 10.1016/j.jeconom.2011.02.020
[41]	Rossi B, Inoue A (2012) Out-of-Sample Forecast Tests Robust to the Choice of Window Size. J Bus Econ Stat 30: 432-453. doi: 10.1080/07350015.2012.693850
[42]	Rudebusch GD, Wu T (2008) A Macro-Finance Model of the Term Structure, Monetary Policy and the Economy. Econ J 118: 906-926. doi: 10.1111/j.1468-0297.2008.02155.x
[43]	Schumacher C (2007) Forecasting German GDP Using Alternative Factor Models Based on Large Datasets. J Forecasting 26: 271-302. doi: 10.1002/for.1026
[44]	Schumacher C (2009) Factor Forecasting Using International Targeted Predictors: The Case of German GDP. Econ Lett 107: 95-98.
[45]	Stark T (2010) Realistic evaluation of real-time forecasts in the Survey of Professional Forecasters. Federal Res Bank Phila Res Division, 1-20.
[46]	Stock JH,WatsonMW(2002a) Macroeconomic Forecasting Using Diffusion Indexes. J Bus Econ Stat 20: 147-162.
[47]	Stock JH, Watson MW (2002b) Forecasting Using Principal Components from a Large Number of Predictors. J Am Stat Assoc 97: 1167-1179.
[48]	Stock JH,WatsonMW(2012) Generalized Shrinkage Methods for Forecasting Using Many Predictors. J Bus Econ Stat 30: 481-493.
[49]	Svensson LE (1994) Estimating and Interpreting Forward Interest Rates: Sweden 1992-1994.Working Paper 4871, National Bureau of Economic Research.
[50]	Swanson NR, Xiong W (2018a) Big Data Analytics In Economics: What Have We Learned So Far, And Where Should We Go From Here? Canadian J Econ 3: 695-746.
[51]	Swanson NR, Xiong W (2018b) Predicting Interest Rates Using Shrinkage Methods, Real-Time Diffusion Indexes, and Model Combinations. Working Paper, Rutgers University.
[52]	Tong L, Liu RW, Soon V, et al. (1991) Indeterminacy and Identifiability of Blind Identification. IEEE Trans on Circ and Syst 38: 499-500. doi: 10.1109/31.76486

Reader Comments

Your name:*

Email:*
© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)