Find us on Facebook Find us on LinkedIn Follow us on Twitter Subscribe to our YouTube channel Instagram

Marcel Scharth

Marcel Scharth


Lecturer

Rm 4161
H70 - Abercrombie Building
The University of Sydney
NSW 2006 Australia

Telephone +61 2 9036 9120
Fax +61 2 9351 6409
marcel.scharth@sydney.edu.au
Web


Bio

Marcel Scharth specialises in simulation based methodology for the estimation of high dimensional time series and panel data models.  Key techniques in his research are importance sampling, sequential Monte Carlo, Markov Chain Monte Carlo, and variance reduction methods. He holds a PhD in Econometrics from the VU University Amsterdam.

Current applied interests include discrete choice modelling, univariate and multivariate stochastic volatility models, modelling cognitive development, and structural macroeconometrics.

Marcel's research is published or forthcoming in the Journal of Econometrics, The Review of Economics and Statistics, The Journal of Business and Economics Statistics, among others

2016

4
Journal Article/s

Scharth M and Kohn R 2016 'Particle efficient importance sampling', Journal of Econometrics, vol.190:1, pp. 133-47 [Link]

Koopman SJ, Lucas A and Scharth M 2016 'Predicting Time-Varying Parameters with Parameter-Driven and Observation-Driven Models', Review of Economics and Statistics, vol.98:1, pp. 97-110 [Link]

5
Conference Paper/s

Jofre M, Scharth M and Gerlach R 2016 'Complete Subset Logistic Regression for Corporate Fraud Detection', Australian Statistical Conference ASC 2016, Canberra, Australia, 9th December 2016

2015

4
Journal Article/s

Koopman SJ, Lucas A and Scharth M 2015 'Numerically Accelerated Importance Sampling for Nonlinear Non-Gaussian State-Space Models', Journal of Business and Economic Statistics, vol.33:1, pp. 114-27 [Link]

5
Conference Paper/s

Scharth M and Kohn R 2015 'Bayesian inference in Structural Econometric Models with intractable likelihoods', 9th Conference of the Asian Regional Section of the International Association for Statistical Computing IASC-ARS 2015, Singapore, 19th December 2015

Mendes E, Scharth M and Kohn R 2015 'Markov Interacting Importance Samplers', 9th International Conference on Computational and Financial Econometrics CFE 15, London, United Kingdom, 14th December 2015

2014

4
Journal Article/s

Fernandes M, Medeiros MC and Scharth M 2014 'Modeling and predicting the CBOE market volatility index', Journal of Banking and Finance, vol.40, pp. 1-10

5
Conference Paper/s

Kohn R, Pitt M, Tran MN and Scharth M 2014 'Importance Sampling Squared for Bayesian Inference in Latent Variable Models', International Society for Bayesian Analysis World Meeting, Cancun, Mexico, 18th July 2014

Mendes E, Scharth M and Kohn R 2014 'Markov Interacting Importance Samplers', International Society for Bayesian Analysis World Meeting, Cancun, Mexico, 18th July 2014

2013

4
Journal Article/s

Koopman SJ and Scharth M 2013 'The Analysis of Stochastic Volatility in the Presence of Daily Realized Measures', Journal of Financial Econometrics, vol.11:1, pp. 76-115

5
Conference Paper/s

Koopman S, Lucas A and Scharth M 2013 'Numerically accelerated importance sampling for nonlinear non-Gaussian state space models', 7th International Conference on Computational and Financial Econometrics CFE 2013, University of London, United Kingdom, 16th December 2013

Scharth M and Kohn R 2013 'Particle efficient importance sampling', 7th International Conference on Computational and Financial Econometrics CFE 2013, University of London, United Kingdom, 16th December 2013

2010

5
Conference Paper/s

Scharth M, Koopman S and Lucas A 2010 'Fast, unbiased and efficient importance sampling for state space models', 4th International Conference on Computational and Financial Econometrics CFE 2010, University of London, United Kingdom, 12th December 2010

2009

4
Journal Article/s

Scharth M and Medeiros M 2009 'Asymmetric effects and long memory in the volatility of Dow Jones stocks', International Journal of Forecasting, vol.25:2, pp. 304-27

5
Conference Paper/s

Allen DE, McAleer M and Scharth M 2009 'Pricing options by simulation using realized volatility', MODSIM09 International Congress on Modelling and Simulation, Cairns, Australia, 17th July 2009

2007

5
Conference Paper/s

Scharth M and Medeiros MC 2007 'Asymmetric Effects and Long Memory in the Volatility of Dow Jones Stocks', 2007 Far Eastern Meeting of the Econometric Society, Taipei, Taiwan, 13th July 2007

Research Expertise

  • Monte Carlo methods
  • High-dimensional estimation
  • Bayesian statistics
  • State Space models
  • Sequential Monte Carlo
  • Financial econometrics

Recent Units Taught

  • QBUS2810 Statistical Modelling for Business

    2017: S1,
    2016: S1,

  • QBUS2820 Predictive Analysis

    2017: S2,

  • QBUS2820 Predictive Analytics

    2016: S2,
    2015: S2,

  • QBUS5001 Quantitative Methods for Business

    2016: S2,

  • QBUS6810 Statistical Learning and Data Mining

    2017: S2,