BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;VALUE=DATE:20250403
DTEND;VALUE=DATE:20250404
DTSTAMP:20260710T102450
CREATED:20250106T140704Z
LAST-MODIFIED:20250106T140704Z
UID:17726-1743638400-1743724799@crest.science
SUMMARY:Alessandra Luati (Imperial College London): "Inference in Time-Varying Parameter Models"
DESCRIPTION:Alessandra Luati (Imperial College London): “Inference in Time-Varying Parameter Models \n31/03/2025 – 03/04/2025 – 07/04/2025 – 10/04/2025 \nReferent: Christian Francq \n
URL:https://crest.science/event/alessandra-luati-imperial-college-london-inference-in-time-varying-parameter-models-3/
CATEGORIES:Doctoral Courses,Finance
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20250403T100000
DTEND;TZID=Europe/Helsinki:20250403T110000
DTSTAMP:20260710T102450
CREATED:20250321T103705Z
LAST-MODIFIED:20250326T082419Z
UID:17985-1743674400-1743678000@crest.science
SUMMARY:Alessandra LUATI ( Imperial College) "Unobserved Component Models\, Approximate Filters and Dynamic Adaptive Mixture Models"
DESCRIPTION:Finance-Insurance\nTime: 10.00 am\nDate: 03th of April 2025\nRoom 3001 \nAlessandra LUATI ( Imperial College) “Unobserved Component Models\, Approximate Filters and Dynamic Adaptive Mixture Models” \nAbstract : State estimation in unobserved component models with parameter uncertainty is traditionally performed through approximate filters\, where Gaussian distributions with given moments are employed to replace otherwise intractable conditional densities. This paper re-examines signal-plus-noise models where parameter uncertainty is induced by a latent variable that may assume a fixed number of states. First\, it is shown that\, for these models\, the approximate filters commonly adopted in the literature can be obtained as linear combinations of minimum variance linear unbiased estimators. Second\, it is observed that they coincide with filters implied by a novel class of dynamic adaptive mixture models\, where the parameters of a mixture of distributions evolve over time following a recursion that is based on the score of the one-step-ahead predictive distribution. Focusing on a robust specification\, where the mixture components are Student’s t distributions\, we prove existence\, stationarity and ergodicity of the data generating process as well as invertibility of the filter\, and consistency and asymptotic normality of the maximum likelihood estimator of the static parameters. An application to energy spot prices is discussed\, where the novel specification is compared with\, and showed to outperform\, robust score-driven filters and the related class of mixture autoregressive models.\n\n \nJoint work : Leopoldo Catania (Aarhus) and Enzo D’Innocenzo (Bologna) \nOrganizers:  Zakoian Jean-Michel \n  \n
URL:https://crest.science/event/alessandra-luati-imperial-college-t-b-a/
CATEGORIES:Finance-Insurance,Seminars
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20250403T110000
DTEND;TZID=Europe/Helsinki:20250403T120000
DTSTAMP:20260710T102450
CREATED:20250321T104006Z
LAST-MODIFIED:20250331T063946Z
UID:17986-1743678000-1743681600@crest.science
SUMMARY:Mattheo BARIGOZZI  (Università di Bologna)  "Score-Driven High-Dimensional Approximate Dynamic Factor Models: Estimation and Inference"
DESCRIPTION:Finance-Insurance\nTime: 11.00 am\nDate: 03th of April 2025\nRoom 3001 \nMattheo BARIGOZZI (Università di Bologna) “Score-Driven High-Dimensional Approximate Dynamic Factor Models: Estimation and Inference” \nAbstract : We propose a dynamic factor model for high-dimensional time series where the dynamics of the latent factors is non-linear and generated by a multivariate score-driven model\, thus allowing to model non-linearities and heavy tails. Estimation is in two-steps: first the factors are extracted either via Principal Components or via Diversified Projections and then the parameters of the score-driven model for the estimated factors are estimated via Maximum Likelihood. Models for the conditional mean and the conditional variance are considered. Consistency and asymptotic normality for the parameters hold as both the number of time series and the sample size diverge to infinity. Moreover\, valid asymptotic prediction intervals are built for the latent factors. Numerical results confirm the goodness of our estimator. \n \nJoint work : Enzo D’Innocenzo \nOrganizers:  Zakoian Jean-Michel \n  \n
URL:https://crest.science/event/mattheo-barigozzi-universita-di-bologna-t-b-a/
CATEGORIES:Finance-Insurance,Seminars
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR