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:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20240101T000000
END:STANDARD
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20240506T130000
DTEND;TZID=UTC:20240523T161500
DTSTAMP:20260710T184955
CREATED:20231019T102955Z
LAST-MODIFIED:20240326T092120Z
UID:16124-1715000400-1716480900@crest.science
SUMMARY:Estimation of Functionals of High-Dimensional Parameters: Bias Reduction and Concentration\, Vladimir Koltchinskii (Georgia Institute of Technology)
DESCRIPTION:  \n\n\n\n  \n  \nSCHEDULE\n  \nMonday\n  \n6th May 2024 \n13th May 2024\n  \nFrom 13:00 to 16:15\n  \nRoom 2033\n\n\n  \nThursday\n  \n16th May 2024 \n23rd May 2024\n  \nFrom 13:00 to 16:15\n  \nRoom 2033\n\n\n\nAims and objectives\nThe aim of this course will be on a circle of problems related to estimation of real valued functionals of parameters of high-dimensional statistical models. In such problems\, it is of interest to estimate onedimensional features of a high-dimensional parameter that are often represented by nonlinear functionals of certain degree of smoothness defined on the parameter space. The functionals of interest could be estimated with faster convergence rates than the whole parameter (sometimes\, even with parametric rates). The examples include\, for instance\, such problems as estimation of linear functionals of principal components (that are nonlinear functionals of unknown covariance) in high-dimensional PCA. The goal is to discuss several mathematical methods that provide a way to develop estimators of functionals of highdimensional parameters with optimal error rates in classes of functionals of some Hölder smoothness.\nMoreover\, when the degree of smoothness of the functional is above certain threshold\, the estimators in question have parametric √𝑛 error rate and are asymptotically efficient\, whereas the error rates become slower than √𝑛 when the degree of smoothness is below the threshold.\nThe following topics will be covered (at least\, to some extent):\n• preliminaries in high-dimensional probability and analysis (concentration inequalities\, comparison inequalities\, Hölder smoothness of operator functions\, etc);\n• non-asymptotic bounds and concentration inequalities for sample covariance in high-dimensional and dimension-free frameworks;\n• some approaches to concentration inequalities for smooth functionals of statistical estimators;\n• higher order bias reduction methods in functional estimation;\n– methods based on Taylor expansion and estimation of polynomials with reduced bias;\n– iterative bias reduction and bootstrap chains;\n– linear aggregation of plug-in estimators with different sample sizes and jackknife estimators;\n• minimax lower bounds in functional estimation (applications of van Trees inequality\, Nemirovski’s construction of least favorable functionals\, etc);\n• Examples:\n– high-dimensional and infinite dimensional Gaussian models: functionals of mean and of covariance;\n– log-concave models\, in particular\, log-concave location families;\n– high-dimensional exponential families;\n– nonparametric models\, functionals of unknown density;\n– linear functionals of spectral projections of matrix parameters. \n\n
URL:https://crest.science/event/estimation-of-functionals-of-high-dimensional-parameters-bias-reduction-and-concentration-vladimir-koltchinskii-georgia-institute-of-technology/
LOCATION:2033
CATEGORIES:Doctoral Courses,Statistics
ORGANIZER;CN="Alexandre%20Tsybakov":MAILTO:alexandre.tsybakov@ensae.fr
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20240513
DTEND;VALUE=DATE:20240518
DTSTAMP:20260710T184956
CREATED:20240514T073119Z
LAST-MODIFIED:20240514T073119Z
UID:17019-1715558400-1715990399@crest.science
SUMMARY:6th Workshop on Sequential Monte Carlo Methods (SMC 2024)
DESCRIPTION:13 – 17 May 2024 \nWith the paprticipation of Nicolas Chopin \nhttps://www.icms.org.uk/SMC2024 \n
URL:https://crest.science/event/6th-workshop-on-sequential-monte-carlo-methods-smc-2024/
CATEGORIES:Conferences and Workshops,Statistics
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20240513T121500
DTEND;TZID=Europe/Helsinki:20240513T133000
DTSTAMP:20260710T184956
CREATED:20231117T101325Z
LAST-MODIFIED:20240506T080604Z
UID:16244-1715602500-1715607000@crest.science
SUMMARY:Sylvain CATHERINE (University of Pennsylvania) "Interest-rate risk and household portfolios"
DESCRIPTION:Macro seminar\nTime : 12h15 – 13h30 \nDate : 13 Mai 2023 \nSalle 3001 \nSylvain CATHERINE (University of Pennsylvania) “Interest-rate risk and household portfolios” \nAbstract: How are households exposed to interest-rate risk? When rates fall\, house-holds face lower future expected returns but those holding long-term assets— disproportionately the wealthy and middle-aged—experience capital gains. We study the hedging demand for long-term assets in a portfolio choice model.\nThe optimal interest-rate sensitivity of wealth is hump-shaped over the life cy-cle. Within cohorts\, it increases with wealth and earnings. These predictions fit observed patterns in the United States\, suggesting a relatively efficient dis-tribution of interest-rate risk. By protecting workers from rate fluctuations\, Social Security limits the welfare consequences of rising wealth inequality when rates fall. \nJoint work : Max Miller (Harvad University)\, James D. Paron (University of Pennsylvania)\, Natasha Sarin (Yale Law School). \nJean-Baptiste MICHAU (CREST) \n
URL:https://crest.science/event/sylvain-catherine-university-of-pennsylvania-t-b-a/
CATEGORIES:Macroeconomics,Seminars
ATTACH;FMTTYPE=:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20240513T161500
DTEND;TZID=Europe/Helsinki:20240513T173000
DTSTAMP:20260710T184956
CREATED:20240507T124609Z
LAST-MODIFIED:20240507T124851Z
UID:17005-1715616900-1715621400@crest.science
SUMMARY:Senay SOKULLU (Univ Bristol) - "Identification and Estimation of Demand Models with Endogenous Product Entry and Exit"
DESCRIPTION:Paris Econometrics Seminar CREST – PSE – Sciences Po\nTime: 04:15 pm – 05:30 pm\nDate: 13th of May\nRoom : 3001 \n  \nSenay SOKULLU (Univ Bristol) – “Identification and Estimation of Demand Models with Endogenous Product Entry and Exit” \nAbstract : This paper deals with the endogeneity of firms’ entry and exit decisions in demand estimation. Product entry decisions lack a single crossing property in terms of demand unobservables\, which causes the inconsistency of conventional methods dealing with selection. We present a novel and straightforward two-step approach to estimate demand while addressing endogenous product entry. In the first step\, our method estimates a finite mixture model of product entry accommodating latent market types. In the second step\, it estimates demand controlling for the propensity scores of all latent market types. We apply this approach to data from the airline industry. \nCoauthored with Jonathan Roth \n  \nOrganizers:\nElia Lapenta – CREST/ENSAE\nPhilipp Ketz – CNRS/PSE\nClément de Chaisemartin – Sciences Po \nSponsors:\nCREST \n
URL:https://crest.science/event/senay-sokullu-univ-bristol-identification-and-estimation-of-demand-models-with-endogenous-product-entry-and-exit/
CATEGORIES:Paris Econometrics Seminar,Seminars
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR