Sage Journals: Discover world-class research

Abstract

Latent autoregressive models are useful time series models for the analysis of infectious disease data. Evaluation of the likelihood function of latent autoregressive models is intractable and its approximation through simulation-based methods appears as a standard practice. Although simulation methods may make the inferential problem feasible, they are often computationally intensive and the quality of the numerical approximation may be difficult to assess. We consider instead a weighted pairwise likelihood approach and explore several computational and methodological aspects including estimation of robust standard errors and the role of numerical integration. The suggested approach is illustrated using monthly data on invasive meningococcal disease infection in Greece and Italy.

Keywords

Infectious disease data latent autoregressive model numerical integration pairwise likelihood time series

Get full access to this article

View all access options for this article.

References

Lessler

Azman

Grabowski

, et al. Trends in the mechanistic and dynamic modeling of infectious diseases. Current Epidemiol Rep 2016; 3: 212–222.

Kermack

McKendrick

Contribution to the mathematical theory of epidemics. Proc Royal Soc Lond Ser A 1927; 115: 700–721.

Held

Paul

Statistical modeling of infectious disease surveillance data. In: M’ikanatha NM, Lynfield R, Van Beneden CA and de Valk H (eds) Infectious disease surveillance, 2nd ed. Oxford, UK: John Wiley & Sons Ltd, 2013.

Unkel

Farrington

Garthwaite

, et al. Statistical methods for the prospective detection of infectious disease outbreaks: a review. J Royal Stat Soc Ser A 2012; 175: 49–82.

Zeger

Irizarry

Peng

RD.

On time series analysis of public health and biomedical data.

Ann Rev Public Health 2006; 27: 57–79.

Noufaily

Enki

Farrington

, et al. An improved algorithm for outbreak detection in multiple surveillance systems. Stat Med 2013; 32: 1206–1222.

Zeger

SL.

A regression model for time series of counts. Biometrika 1988; 75: 621–629.

Davis

Dunsmuir

WTM

Wang

Modelling time series of count data. In: Ghosh

(ed.) Asymptotics, nonparametrics, and time series. New York, NY: Marcel-Dekker, 1999, pp.63–114.

Cox

DR.

Statistical analysis of time series: some recent developments. Scand J Stat 1981; 8: 93–115.

10.

Durbin

Koopman

SJ.

Time series analysis by state space methods. Oxford, UK: Oxford University Press, 2012.

11.

Davis

Dunsmuir

WTM.

State space models for count time series. In: Davis , et al. (eds) Handbook of discrete-valued time series. Boca Raton, FL: CRC Press, 2016.

12.

Varin

Reid

Firth

An overview of composite likelihood methods. Statistica Sinica 2011; 21: 5–42.

13.

Varin

Vidoni

Pairwise likelihood inference for general state space models. Econometric Rev 2009; 28: 170–85.

14.

Davis

Yau

CY.

Comments on pairwise likelihood in time series models. Statistica Sinica 2011; 21: 255–77.

15.

Joe

Karlis

, et al. Composite likelihood for time series models with a latent autoregressive process. Statistica Sinica 2011; 21: 279–305.

16.

R Core Team. R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing, 2018.

17.

Imai

Armstrong

Chalabi

, et al. Time series regression model for infectious disease and weather. Environment Res 2009; 142: 319–327.

18.

Cagnone

Bartolucci

Adaptive quadrature for maximum likelihood estimation of a class of dynamic latent variable models. Computat Economics 2017; 49: 599–622.

19.

Newey

West

KD.

Automatic lag selection in covariance matrix estimation. Rev Economic Studies 1994; 61: 631–653.

20.

Bianconcini

Asymptotic properties of adaptive maximum likelihood estimators in latent variable models. Bernoulli 2014; 20: 1507–1531.

21.

Rabe-Hesketh

Skrondal

Pickles

Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects. J Econometric 2005; 128: 301–323.

22.

Lesaffre

Spiessens

On the effect of the number of quadrature points in a logistic random-effects model: an example. Appl Stat 2001; 50: 325–335.

23.

Liu

Pierce

DA.

A note on Gauss–Hermite quadrature. Biometrika 1994; 81: 624–629.

24.

Genz

Malik

AA.

An adaptive algorithm for numeric integration over an N-dimensional rectangular region. J Computat Appl Math 1980; 6: 295–302.

25.

Berntsen

Espelid

Genz

An adaptive algorithm for the approximate calculation of multiple integrals. ACM Transact Math Software 1991; 17: 437–451.

26.

Narasimhan

Koller

Johnson

SG.

cubature: Adaptive multivariate integration over hypercubes. 2017. R package version 1.3-11.

27.

Rue

Martino

Chopin

Approximate Bayesian inference for latent Gaussian models using integrated nested Laplace approximations (with discussion). J Royal Stat Soc Ser B 2009; 71: 319–392.

28.

Davis

Rodriguez-Yam

Estimation for state-space models based on a likelihood approximation. Stat Sinica 2005; 15: 381–406.

29.

Rosenstein

Perkins

Stephens

, et al. Meningococcal disease. New Engl J Med 2001; 344: 1378–1388.

30.

Pascucci

Di Gregori

Frasca

, et al. Impact of meningococcal C conjugate vaccination campaign in Emilia-Romagna, Italy. Human Vaccines Immunotherapeutics 2014; 10: 671–676.

31.

Stefanelli

Fazio

Sofia

, et al. Serogroup C meningococci in Italy in the era of conjugate menC vaccination. BMC Infect Dis 2009; 9: 135.

32.

Stefanelli

Fazio

Sofia

, et al. Increased incidence of invasive meningococcal disease of serogroup C/clonal complex 11, Tuscany, Italy, 2015 to 2016. Euro Surveillance 2009; 21: 12.

33.

Bevilacqua

Gaetan

Mateu

, et al. Estimating space and space-time covariance functions for large data sets: a weighted composite likelihood approach. J Am Stat Assoc 2012; 107: 268–280.

34.

Baker

White

Mengersen

, et al. Joint modelling of potentially avoidable hospitalisation for five diseases accounting for spatiotemporal effects: a case study in New South Wales, Australia. PLoS ONE 2017; 12: e0183653.

35.

Heiss

Winschel

Likelihood approximation by numerical integration on sparse grids. J Econometrics 2008; 144: 62–80.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.20 MB

Pairwise likelihood estimation of latent autoregressive count models

Abstract

Keywords

Get full access to this article

References

Supplementary Material