Advertisement

Environmental and Ecological Statistics

, Volume 24, Issue 2, pp 317–339 | Cite as

Validation of ecological state space models using the Laplace approximation

  • Uffe Høgsbro ThygesenEmail author
  • Christoffer Moesgaard Albertsen
  • Casper Willestofte Berg
  • Kasper Kristensen
  • Anders Nielsen
Article

Abstract

Many statistical models in ecology follow the state space paradigm. For such models, the important step of model validation rarely receives as much attention as estimation or hypothesis testing, perhaps due to lack of available algorithms and software. Model validation is often based on a naive adaptation of Pearson residuals, i.e. the difference between observations and posterior means, even if this approach is flawed. Here, we consider validation of state space models through one-step prediction errors, and discuss principles and practicalities arising when the model has been fitted with a tool for estimation in general mixed effects models. Implementing one-step predictions in the R package Template Model Builder, we demonstrate that it is possible to perform model validation with little effort, even if the ecological model is multivariate, has non-linear dynamics, and whether observations are continuous or discrete. With both simulated data, and a real data set related to geolocation of seals, we demonstrate both the potential and the limitations of the techniques. Our results fill a need for convenient methods for validating a state space model, or alternatively, rejecting it while indicating useful directions in which the model could be improved.

Keywords

Maximum likelihood estimation Model validation Residual analysis Statistical ecology State space methods Time series analysis 

References

  1. Akaike H (1974) A new look at the statistical model identification. IEEE Trans Autom Control AC–19:716–723 (system identification and time-series analysis)CrossRefGoogle Scholar
  2. Albertsen CM, Whoriskey K, Yurkowski D, Nielsen A, Mills Flemming J (2015) Fast fitting of non-Gaussian state-space models to animal movement data via template model builder. Ecology 96(10):2598–2604CrossRefPubMedGoogle Scholar
  3. Anscombe FJ, Tukey JW (1963) The examination and analysis of residuals. Technometrics 5(2):141–160. doi: 10.1080/00401706.1963.10490071 CrossRefGoogle Scholar
  4. Berg CW, Nielsen A (2016) Accounting for correlated observations in an age-based state-space stock assessment model. ICES J Mar Sci. doi: 10.1093/icesjms/fsw046
  5. Bolker BM, Gardner B, Maunder M, Berg CW, Brooks M, Comita L, Crone E, Cubaynes S, Davies T, Valpine P et al (2013) Strategies for fitting nonlinear ecological models in R, AD Model Builder, and BUGS. Methods Ecol Evol 4(6):501–512CrossRefGoogle Scholar
  6. Box GE, Draper NR (1987) Empirical model-building and response surfaces. Wiley, New YorkGoogle Scholar
  7. Box GEP, Jenkins GM (1970) Time series analysis: forecasting and control, 1976. ISBN: 0-8162-1104-3Google Scholar
  8. Cadigan N, Morgan M, Brattey J (2014) Improved estimation and forecasts of stock maturities using generalised linear mixed models with auto-correlated random effects. Fish Manag Ecol 21(5):343–356CrossRefGoogle Scholar
  9. Clark C, Mangel M (2000) Dynamic state variable models in ecology: methods and applications. Oxford University Press, OxfordGoogle Scholar
  10. Clark JS (2007) Models for ecological data: an introduction, vol 11. Princeton University Press, PrincetonGoogle Scholar
  11. Cox D, Hinkley D (1974) Theoretical statistics. Chapman & Hall, LondonCrossRefGoogle Scholar
  12. Cox DR, Snell EJ (1968) A general definition of residuals. J R Stat Soc Ser B (Methodol) 30(2):248–275, URL http://www.jstor.org/stable/2984505
  13. Dawid AP (1984) Present position and potential developments: Some personal views: Statistical theory: the prequential approach. J R Stat Soc Ser A (General) 147(2):278–292CrossRefGoogle Scholar
  14. de Valpine P, Hastings A (2002) Fitting population models incorporating process noise and observation error. Ecol Monogr 72(1):57–76CrossRefGoogle Scholar
  15. Dunn PK, Smyth GK (1996) Randomized quantile residuals. J Comput Graph Stat 5(3):236–244Google Scholar
  16. Evensen G (2003) The ensemble kalman filter: theoretical formulation and practical implementation. Ocean Dyn 53(4):343–367CrossRefGoogle Scholar
  17. Fournier DA, Skaug HJ, Ancheta J, Ianelli J, Magnusson A, Maunder MN, Nielsen A, Sibert J (2012) AD Model Builder: using automatic differentiation for statistical inference of highly parameterized complex nonlinear models. Optim Methods Softw 27(2):233–249CrossRefGoogle Scholar
  18. Frühwirth-Schnatter S (1996) Recursive residuals and model diagnostics for normal and non-normal state space models. Environ Ecol Stat 3(4):291–309CrossRefGoogle Scholar
  19. Gelman A, Carlin JB, Stern HS, Rubin DB (2014) Bayesian data analysis, vol 2. Taylor & Francis, AbingdonGoogle Scholar
  20. Gilks WR, Richardson S, Spiegelhalter DJ (1996) Markov chain Monte Carlo in practice. Interdisciplinary statistics. Chapman and Hall, LondonGoogle Scholar
  21. Griewank A, Walther A (2008) Evaluating derivatives: principles and techniques of algorithmic differentiation. SIAM, New DelhiCrossRefGoogle Scholar
  22. Harvey AC (1989) Forecasting, structural time series models and the Kalman filter. Cambridge University Press, CambridgeGoogle Scholar
  23. Jonsen I, Flemming J, Myers R (2005) Robust state-space modeling of animal movement data. Ecology 86(11):2874–2880CrossRefGoogle Scholar
  24. Jonsen I, Basson M, Bestley S, Bravington M, Patterson T, Pedersen MW, Thomson R, Thygesen UH, Wotherspoon S (2013) State-space models for bio-loggers: a methodological road map. Deep Sea Res Part II Top Stud Ocean 88:34–46CrossRefGoogle Scholar
  25. Kalliovirta L (2012) Misspecification tests based on quantile residuals. Econom J 15(2):358–393. doi: 10.1111/j.1368-423X.2011.00364.x CrossRefGoogle Scholar
  26. Kalman RE (1960) A new approach to linear filtering and prediction problems. J Basic Eng 82:35–45CrossRefGoogle Scholar
  27. Kristensen K, Nielsen A, Berg CW, Skaug H, Bell BM (2016) TMB: automatic differentiation and Laplace approximation. J Stat Softw 70(5):1–21. doi: 10.18637/jss.v070.i05 CrossRefGoogle Scholar
  28. Liu JS, Chen R (1998) Sequential monte carlo methods for dynamic systems. J Am Stat Assoc 93:1032–1044CrossRefGoogle Scholar
  29. Ljung GM, Box GEP (1978) On a measure of lack of fit in time series models. Biometrika 65(2):297. doi: 10.1093/biomet/65.2.297 CrossRefGoogle Scholar
  30. Ljung L (1999) System Identification—Theory for the User. Information and system sciences series, 2nd edn. Prentice-Hall, Upper Saddle RiverGoogle Scholar
  31. Madsen H (2007) Time series analysis. Chapman & Hall/CRC, LondonGoogle Scholar
  32. May RM (1974) Biological populations with nonoverlapping generations: stable points, stable cycles, and chaos. Science 186(4164):645–647CrossRefPubMedGoogle Scholar
  33. Murray J (1989) Mathematical Biology. Springer-Verlag, BerlinCrossRefGoogle Scholar
  34. Nielsen A, Berg CW (2014) Estimation of time-varying selectivity in stock assessments using state-space models. Fish Res 158:96–101CrossRefGoogle Scholar
  35. Øksendal B (2010) Stochastic differential equations—An Introduction with Applications, 6th edn. Springer-Verlag, BerlinGoogle Scholar
  36. Patterson T, Thomas L, Wilcox C, Ovaskainen O, Mathhiopoulos J (2008) State-space models of individual animal movement. Trends Ecol Evol 23(2):87–94CrossRefPubMedGoogle Scholar
  37. Pebesma EJ (2004) Multivariable geostatistics in s: the gstat package. Comput Geosci 30:683–691CrossRefGoogle Scholar
  38. Pedersen MW, Berg CW (2016) A stochastic surplus production model in continuous time. Fish Fish 18:226–243CrossRefGoogle Scholar
  39. Pedersen MW, Berg CW, Thygesen UH, Nielsen A, Madsen H (2011) Estimation methods for nonlinear state-space models in ecology. Ecol Model 222(8):1394–1400CrossRefGoogle Scholar
  40. R Core Team (2015) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria, URL http://www.R-project.org/
  41. Rall LB (1980) Applications of software for automatic differentiation in numerical computation. In: Alefeld G, Grigorieff RD (eds) Fundamentals of numerical computation (computer-oriented numerical analysis), Springer, pp 141–156Google Scholar
  42. Rosenblatt M (1952) Remarks on a multivariate transformation. Ann Math Stat 23(3):470–472CrossRefGoogle Scholar
  43. Rue H, Martino S, Chopin N (2009) Approximate bayesian inference for latent Gaussian models by using integrated nested laplace approximations. J R Stat Soc Ser B (Stat Methodol) 71(2):319–392CrossRefGoogle Scholar
  44. Shapiro SS, Wilk MB (1965) An analysis of variance test for normality (complete samples). Biometrika 52(3–4):591. doi: 10.1093/biomet/52.3-4.591 CrossRefGoogle Scholar
  45. Skaug HJ, Fournier DA (2006) Automatic approximation of the marginal likelihood in non-Gaussian hierarchical models. Comput Stat Data Anal 51(2):699–709CrossRefGoogle Scholar
  46. Smith J (1985) Diagnostic checks of non-standard time series models. J Forecast 4(3):283–291CrossRefGoogle Scholar
  47. Thygesen UH, Sommmer L, Evans K, Patterson TA (2016) Dynamic optimal foraging theory explains vertical migrations of bigeye tuna. Ecol Appear 97:1852–1861CrossRefGoogle Scholar
  48. Tierney L, Kadane JB (1986) Accurate approximations for posterior moments and marginal densities. J Am Stat Assoc 81(393):82–86CrossRefGoogle Scholar
  49. Waagepetersen R (2006) A simulation-based goodness-of-fit test for random effects in generalized linear mixed models. Scand J Stat 33(4):721–731CrossRefGoogle Scholar
  50. Wan EA, Van Der Merwe R (2000) The unscented Kalman filter for nonlinear estimation. In: Adaptive Systems for signal processing, communications, and control symposium 2000. AS-SPCC. The IEEE 2000, IEEE, pp 153–158Google Scholar
  51. Wasserstein RL, Lazar NA (2016) The ASA’s statement on p-values: context, process, and purpose. Am Stat 70:129–133CrossRefGoogle Scholar
  52. Zucchini W, MacDonald IL (2009) Hidden Markov models for time series: an introduction using R. CRC Press, Boca RatonCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Uffe Høgsbro Thygesen
    • 1
    Email author
  • Christoffer Moesgaard Albertsen
    • 1
  • Casper Willestofte Berg
    • 1
  • Kasper Kristensen
    • 1
  • Anders Nielsen
    • 1
  1. 1.National Institute of Aquatic ResourcesTechnical University of DenmarkCharlottenlundDenmark

Personalised recommendations