Bayesian Analysis

Beyond Whittle: Nonparametric Correction of a Parametric Likelihood with a Focus on Bayesian Time Series Analysis

Claudia Kirch, Matthew C. Edwards, Alexander Meier, and Renate Meyer

Advance publication

This article is in its final form and can be cited using the date of online publication and the DOI.

Full-text: Open access

Abstract

Nonparametric Bayesian inference has seen a rapid growth over the last decade but only few nonparametric Bayesian approaches to time series analysis have been developed. Most existing approaches use Whittle’s likelihood for Bayesian modelling of the spectral density as the main nonparametric characteristic of stationary time series. It is known that the loss of efficiency using Whittle’s likelihood can be substantial. On the other hand, parametric methods are more powerful than nonparametric methods if the observed time series is close to the considered model class but fail if the model is misspecified. Therefore, we suggest a nonparametric correction of a parametric likelihood that takes advantage of the efficiency of parametric models while mitigating sensitivities through a nonparametric amendment. We use a nonparametric Bernstein polynomial prior on the spectral density with weights induced by a Dirichlet process and prove posterior consistency for Gaussian stationary time series. Bayesian posterior computations are implemented via an MH-within-Gibbs sampler and the performance of the nonparametrically corrected likelihood for Gaussian time series is illustrated in a simulation study and in three astronomy applications, including estimating the spectral density of gravitational wave data from the Advanced Laser Interferometer Gravitational-wave Observatory (LIGO).

Article information

Source
Bayesian Anal., Advance publication (2018), 37 pages.

Dates
First available in Project Euclid: 30 October 2018

Permanent link to this document
https://projecteuclid.org/euclid.ba/1540865702

Digital Object Identifier
doi:10.1214/18-BA1126

Keywords
Bayesian nonparametrics frequency domain laser interferometric gravitational wave data spectral density stationary time series

Rights
Creative Commons Attribution 4.0 International License.

Citation

Kirch, Claudia; Edwards, Matthew C.; Meier, Alexander; Meyer, Renate. Beyond Whittle: Nonparametric Correction of a Parametric Likelihood with a Focus on Bayesian Time Series Analysis. Bayesian Anal., advance publication, 30 October 2018. doi:10.1214/18-BA1126. https://projecteuclid.org/euclid.ba/1540865702


Export citation

References

  • Aasi, J., the LIGO Scientific Collaboration, and the Virgo Collaboration (2015a). “Characterization of the LIGO detectors during their sixth science run.” Classical and Quantum Gravity, 32: 115012.
  • Aasi, J. et al. (2015b). “Advanced LIGO.” Classical and Quantum Gravity, 32: 074001.
  • Abbott, B. P. et al. (2016a). “GW151226: Observation of gravitational waves from a 22-solar-mass binary black hole coalescence.” Physical Review Letters, 116: 241103.
  • Abbott, B. P. et al. (2016b). “Observation of gravitational waves from a binary black hole merger.” Physical Review Letters, 116: 061102.
  • Abbott, B. P. et al. (2016c). “Properties of the binary black hole merger GW150914.” Physical Review Letters, 116: 241102.
  • Abbott, B. P. et al. (2017a). “GW170104: Observation of a 50-Solar-Mass Binary Black Hole Coalescence at Redshift 0.2.” Physical Review Letters, 118: 221101.
  • Abbott, B. P. et al. (2017b). “GW170608: Observation of a 19 Solar-mass Binary Black Hole Coalescence.” The Astrophysical Journal Letters, 851: L35.
  • Abbott, B. P. et al. (2017c). “GW170814: A Three-Detector Observation of Gravitational Waves from a Binary Black Hole Coalescence.” Physical Review Letters, 119: 141101.
  • Abbott, B. P. et al. (2017d). “Multi-messenger Observations of a Binary Neutron Star Merger.” The Astrophysical Journal Letters, 848: L12.
  • Acernese, F. et al. (2015). “Advanced Virgo: A second-generation interferometric gravitational wave detector.” Classical and Quantum Gravity, 32(2): 024001.
  • Andrews, D. W. K. and Monahan, J. C. (1992). “An improved heteroskedasticity and autocorrelation consistent covariance matrix estimator.” Econometrica, 60(4): 953–966.
  • Baldwin, A. and Thomson, P. (1978). “Periodogram analysis of S. Carinae.” Royal Astronomical Society of New Zealand, 6: 31–35.
  • Barnett, G., Kohn, R., and Sheather, S. (1996). “Bayesian estimation of an autoregressive model using Markov chain Monte Carlo.” Journal of Econometrics, 74(2): 237–254.
  • Bauwens, L., Lubrano, M., and Richard, J.-F. (2000). Bayesian inference in dynamic econometric models. Oxford University Press.
  • Bollerslev, T. (1986). “Generalized autoregressive conditional heteroskedasticity.” Journal of Econometrics, 31(3): 307–327.
  • Box, G. E. P., Jenkins, G. M., and Reinsel, G. C. (2013). Time series analysis: Forecasting and control. John Wiley & Sons.
  • Brockwell, P. J. and Davis, R. A. (2009). Time series: Theory and methods. Springer.
  • Cadonna, A., Kottas, A., and Prado, R. (2017). “Bayesian mixture modeling for spectral density estimation.” Statistics & Probability Letters, 125: 189–195.
  • Carter, C. and Kohn, R. (1997). “Semiparametric Bayesian inference for time series with mixed spectra.” Journal of the Royal Statistical Society: Series B (Statistical Methodology), 59(1): 255–268.
  • Chopin, N., Rousseau, J., and Liseo, B. (2013). “Computational aspects of Bayesian spectral density estimation.” Journal of Computational and Graphical Statistics, 22(3): 533–557.
  • Choudhuri, N., Ghosal, S., and Roy, A. (2004). “Bayesian estimation of the spectral density of a time series.” Journal of the American Statistical Association, 99(468): 1050–1059.
  • Christensen, N. (2010). “LIGO S6 detector characterization studies.” Classical and Quantum Gravity, 27: 194010.
  • Contreras-Cristán, A., Gutiérrez-Peña, E., and Walker, S. G. (2006). “A note on Whittle’s likelihood.” Communications in Statistics – Simulation and Computation, 35(4): 857–875.
  • Cornish, N. J. and Littenberg, T. B. (2015). “Bayeswave: Bayesian inference for gravitational wave bursts and instrument glitches.” Classical and Quantum Gravity, 32: 135012.
  • Costa, M. J., Finkenstädt, B., Roche, V., Ladvi, F., Gould, P. D., Foreman, J., Halliday, K., Hall, A., and Rand, D. A. (2013). “Inference on periodicity of circadian time series.” Biostatistics, 14(4): 792–806.
  • Coughlin, M., the LIGO Scientific Collaboration, and the Virgo Collaboration (2010). “Noise Line Identification in LIGO S6 and Virgo VSR2.” Journal of Physics: Conference Series, 243: 012010.
  • Dahlhaus, R. and Janas, D. (1996). “A frequency domain bootstrap for ratio statistics in time series analysis.” The Annals of Statistics, 24(5): 1934–1963.
  • Durbin, J. and Koopman, S. (2012). Time series analysis by state space methods. 38. Oxford University Press.
  • Edwards, M. C., Meyer, R., and Christensen, N. (2015). “Bayesian semiparametric power spectral density estimation with applications in gravitational wave data analysis.” Physical Review D, 92: 064011.
  • Edwards, M. C., Meyer, R., and Christensen, N. (2018). “Bayesian nonparametric spectral density estimation using B-spline priors.” Statistics and Computing. DOI: 10.1007/s11222-017-9796-9.
  • Einstein, A. (1916). “Approximative integration of the field equations of gravitation.” Sitzungsberichte Preußischen Akademie der Wissenschaften, 1916(Part 1): 688–696.
  • Emmanoulopoulos, D., McHardy, I., and Papadakis, I. (2013). “Generating artificial light curves: Revisited and updated.” Monthly Notices of the Royal Astronomical Society, 433(2): 907–927.
  • Engle, R. (1982). “Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation.” Econometrica: Journal of the Econometric Society, 987–1007.
  • Fan, J. and Yao, Q. (2002). Nonlinear time series, volume 2. Springer.
  • Franke, J. and Härdle, W. (1992). “On bootstrapping kernel spectral estimates.” The Annals of Statistics, 121–145.
  • Fuller, W. (1996). Introduction to Statistical Time Series. Wiley Series in Probability and Statistics. Wiley.
  • Gangopadhyay, A., Mallick, B., and Denison, D. (1999). “Estimation of spectral density of a stationary time series via an asymptotic representation of the periodogram.” Journal of Statistical Planning and Inference, 75(2): 281–290.
  • Gelman, A. (2006). “Prior distributions for variance parameters in hierarchical models.” Bayesian Analysis, 1(3): 515–533.
  • Ghosal, S., Ghosh, J., and Ramamoorthi, R. (1999). “Posterior consistency of Dirichlet mixtures in density estimation.” Annals of Statistics, 27: 143–158.
  • Green, P. J. (1995). “Reversible jump Markov chain Monte Carlo computation and Bayesian model determination.” Biometrika, 82(4): 711–732.
  • Häfner, F. and Kirch, C. (2016). “Moving Fourier analysis for locally stationary processes with the bootstrap in view.” Preprint.
  • Härdle, W., Horowitz, J., and Kreiss, J.-P. (2003). “Bootstrap methods for time series.” International Statistical Review, 71(2): 435–459.
  • Härdle, W., Lütkepohl, H., and Chen, R. (1997). “A review of nonparametric time series analysis.” International Statistical Review, 65(1): 49–72.
  • Hermansen, G. H. (2008). “Bayesian nonparametric modelling of covariance functions, with application to time series and spatial statistics.” Ph.D. thesis, Universitetet i Oslo.
  • Hidalgo, J. (2008). “Specification testing for regression models with dependent data.” Journal of Econometrics, 143(1): 143–165.
  • Hjort, N. L. and Glad, I. K. (1995). “Nonparametric density estimation with a parametric start.” The Annals of Statistics, 882–904.
  • Hjort, N. L., Holmes, C. C., Müller, P., and Walker, S. G. (2010). “Bayesian nonparametrics.” AMC, 10: 12.
  • Huerta, G. and West, M. (1999). “Bayesian inference on periodicities and component spectral structure in time series.” Journal of Time Series Analysis, 20: 401–416.
  • Hurvich, C. M. and Zeger, S. (1987). Frequency domain bootstrap methods for time series. New York University, Graduate School of Business Administration.
  • Jentsch, C. and Kreiss, J.-P. (2010). “The multiple hybrid bootstrap - Resampling multivariate linear processes.” Journal of Multivariate Analysis, 101(10): 2320–2345.
  • Jentsch, C., Kreiss, J.-P., Mantalos, P., and Paparoditis, E. (2012). “Hybrid bootstrap aided unit root testing.” Computational Statistics, 27(4): 779–797.
  • Kim, Y. M. and Nordman, D. J. (2013). “A frequency domain bootstrap for Whittle estimation under long-range dependence.” Journal of Multivariate Analysis, 115: 405–420.
  • Kirch, C. (2007). “Resampling in the frequency domain of time series to determine critical values for change-point tests.” Statistics & Decisions, 25(3/2007): 237–261.
  • Kirch, C. and Politis, D. N. (2011). “TFT-bootstrap: Resampling time series in the frequency domain to obtain replicates in the time domain.” Annals of Statistics, 39(3): 1427–1470.
  • Kirch, C., Edwards, M. C., Meier, A., and Meyer, R. (2018). “Supplementary material to ‘Beyond Whittle: Nonparametric Correction of a Parametric Likelihood with a Focus on Bayesian Time Series Analysis’.” Bayesian Analysis.
  • Kleijn, B. J. K., van der Vaart, A. W., et al. (2012). “The Bernstein-von-Mises theorem under misspecification.” Electronic Journal of Statistics, 6: 354–381.
  • Kreiss, J.-P. and Lahiri, S. N. (2012). “Bootstrap Methods for Time Series.” Handbook of Statistics, 30: 3–26.
  • Kreiss, J.-P. and Paparoditis, E. (2003). “Autoregressive-aided periodogram bootstrap for time series.” Annals of Statistics, 31(6): 1923–1955.
  • Kreiss, J.-P. and Paparoditis, E. (2011). “Bootstrap methods for dependent data: A review.” Journal of the Korean Statistical Society, 40(4): 357–378.
  • Kreiss, J.-P. and Paparoditis, E. (2012). “The hybrid wild bootstrap for time series.” Journal of the American Statistical Association, 107(499): 1073–1084.
  • Kreiss, J.-P., Paparoditis, E., and Politis, D. N. (2011). “On the range of validity of the autoregressive sieve bootstrap.” The Annals of Statistics, 2103–2130.
  • Le Cam, L. and Yang, G.. (1960). Asymptotics in Statistics. Springer.
  • Liseo, B. and Macaro, C. (2013). “Objective priors for causal AR (p) with partial autocorrelations.” Journal of Statistical Computation and Simulation, 83(9): 1613–1628.
  • Liseo, B., Marinucci, D., and Petrella, L. (2001). “Bayesian semiparametric inference on long-range dependence.” Biometrika, 88(4): 1089–1104.
  • Littenberg, T. B. and Cornish, N. J. (2015). “Bayesian inference for spectral estimation of gravitational wave detector noise.” Physical Review D, 91: 084034.
  • Littenberg, T. B., Coughlin, M., Farr, B., and M., F. W. (2013). “Fortifying the characterization of binary mergers in LIGO data.” Physical Review D, 88: 084044.
  • McCulloch, R. E. and Tsay, R. S. (1994). “Bayesian analysis of autoregressive time series via the Gibbs sampler.” Journal of Time Series Analysis, 15(2): 253–250.
  • Meier, A., Kirch, C., Edwards, M. C., and Meyer, R. (2017). beyondWhittle: Bayesian Spectral Inference for Stationary Time Series. R package.
  • Müller, P. and Mitra, R. (2013). “Bayesian nonparametric inference–why and how.” Bayesian Analysis (Online), 8(2).
  • Nam, C., Aston, J., and Johansen, A. (2014). “Parallel sequential Monte Carlo samplers and estimation of the number of states in a Hidden Markov Model.” Annals of the Institute of Statistical Mathematics, 66: 553–575.
  • Neumann, M. H. and Polzehl, J. (1998). “Simultaneous bootstrap confidence bands in nonparametric regression.” Journal of Nonparametric Statistics, 9(4): 307–333.
  • Petrone, S. (1999). “Random Bernstein polynomials.” Scandinavian Journal of Statistics, 26(3): 373–393.
  • Roberts, G. O. and Rosenthal, J. S. (2009). “Examples of adaptive MCMC.” Journal of Computational and Graphical Statistics, 18(2): 349–367.
  • Rousseau, J., Chopin, N., Liseo, B., et al. (2012). “Bayesian nonparametric estimation of the spectral density of a long or intermediate memory Gaussian process.” The Annals of Statistics, 40(2): 964–995.
  • Röver, C., Meyer, R., and Christensen, N. (2011). “Modelling coloured residual noise in gravitational-wave signal processing.” Classical and Quantum Gravity, 28: 015010.
  • Schuster, A. (1898). “On the investigation of hidden periodicities with application to a supposed 26 day period of meteorological phenomena.” Terrestrial Magnetism, 3(1): 13–41.
  • Sethuraman, J. (1994). “A constructive definition of Dirichlet priors.” Statistica Sinica, 639–650.
  • Shao, X. and Wu, B. W. (2007). “Asymptotic spectral theory for nonlinear time series.” Annals of Statistics, 35(4): 1773–1801.
  • Sørbye, S. H. and Rue, H. (2016). “Penalised complexity priors for stationary autoregressive processes.” arXiv preprint arXiv:1608.08941.
  • Steel, M. F. J. (2008). “The New Palgrave Dictionary of Economics, chapter Bayesian time series analysis.”
  • Sykulski, A., Olhede, S., Lilly, J., Guillaumin, A., and Early, J. (2017). “The de-biased Whittle likelihood.” arXiv preprint arXiv:1605.06718v2.
  • Szabó, B., van der Vaart, A., van Zanten, J., et al. (2015). “Frequentist coverage of adaptive nonparametric Bayesian credible sets.” The Annals of Statistics, 43(4): 1391–1428.
  • Van der Vaart, A. W. (1998). Asymptotic statistics, volume 3. Cambridge University Press.
  • Walker, S. (2013). Bayesian Theory and Applications, chapter Bayesian nonparametrics, 1–34. Oxford University Press.
  • Wasserman, L. (2006). All of nonparametric statistics. Springer.
  • Welch, P. D. (1967). “The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms.” IEEE Transactions on Audio and Electroacoustics, 15: 70–73.
  • Whittle, P. (1957). “Curve and periodogram smoothing.” Journal of the Royal Statistical Society. Series B (Methodological), 38–63.

Supplemental materials

  • Supplementary material to ‘Beyond Whittle: Nonparametric Correction of a Parametric Likelihood with a Focus on Bayesian Time Series Analysis’. The electronic supplement contains the proofs for this paper, some comments on the Bayesian autoregressive sampler, the full conditional distribution of missing values as well as some additional simulation results.